To see the other types of publications on this topic, follow the link: Age estimation.
Dissertations / Theses on the topic 'Age estimation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Age estimation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Khan, Muhammad Aurangzeb. "Automatic facial age estimation." Thesis, Lancaster University, 2015. http://eprints.lancs.ac.uk/76420/.
Full textAbstract:
The reliability of automatically estimating human ages, by processing input facial images, has generally been found to be poor. On other hand, various real world applications, often relating to safety and security, depend on an accurate estimate of a person’s age. In such situations, Face Image based Automatic Age Estimation (FI-AAE) systems which are more reliable and may ideally surpass human ability, are of importance as and represent a critical pre-requisite technology. Unfortunately, in terms of estimation accuracy and thus performance, contemporary FI-AAE systems are impeded by challenges which exist in both of the two major FI-AAE processing phases i.e. i) Age based feature extraction and representation and ii) Age group classification. Challenges in the former phase arise because facial shape and texture change independently and the magnitude of these changes vary during the different stages of a person’s life. Additionally, contemporary schemes struggle to exploit age group specific characteristics of these features, which in turn has a detrimental effect on overall system performance. Furthermore misclassification errors which occur in the second processing phase and are caused by the smooth inter-class variations often observed between adjacent age groups, pose another major challenge and are responsible for low overall FI-AAE performance. In this thesis a novel Multi-Level Age Estimation (ML-AE) framework is proposed that addresses the aforementioned challenges and improves upon state-of-the-art FI-AAE system performance. The proposed ML-AE is a hierarchical classification scheme that maximizes and then exploits inter-class variation among different age groups at each level of the hierarchy. Furthermore, the proposed scheme exploits age based discriminating information taken from two different cues (i.e. facial shape and texture) at the decision level which improves age estimation results. During the process of achieving our main objective of age estimation, this research work also contributes to two associated image processing/analysis areas: i) Face image modeling and synthesis; a process of representing face image data with a low dimensionality set of parameters. This is considered as precursor to every face image based age estimation system and has been studied in this thesis within the context of image face recognition ii) measuring face image data variability that can help in representing/ranking different face image datasets according to their classification difficulty level. Thus a variability measure is proposed that can also be used to predict the classification performance of a given face recognition system operating upon a particular input face dataset. Experimental results based on well-known face image datasets revealed the superior performance of our proposed face analysis, synthesis and face image based age classification methodologies, as compared to that obtained from conventional schemes.
2
Danielsson, Oscar. "Multimodal Brain Age Estimation." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281834.
Full textAbstract:
Machine learning models trained on MRI brain scans of healthy subjects can be used to predict age. Accurate estimation of brain age is important for reliably detecting abnormal aging in the brain. One way to increase the accuracy of predicted brain age is through using multimodal data. Previous research using multimodal data has largely been non-deep learning-based; in this thesis, we examine a deep learning model that can effectively utilize several modalities. Three baseline models were trained. Two used T1-weighted and T2- weighted data, respectively. The third model was trained on both T1- and T2- weighted data using high-level fusion. We found that using multimodal data reduced the mean absolute error of predicted ages. Afourth model utilized disentanglement to create a representation robust to missing T1- or T2-weighted data. Our results showed that this model performed similarly to the baselines, meaning that it is robust to missing data and at no significant cost of prediction accuracy.Maskininlärningsmodeller tränade på MR-data av friska personer kan användas för att estimera ålder. Noggrann uppskattning hjärnans ålder är viktigt för att pålitligt upptäcka onormalt åldrande av hjärnan. Ett sätt att öka noggrannheten är genom att använda multimodal data. Tidigare forskning gjord med multimodal data har till stor del inte varit baserad på djupinlärning; i detta examensarbete undersöker vi en djupinlärningsmodell som effektivt kan utnyttja flera modaliteter. Tre basmodeller tränades. Två använde T1-viktad respektive T2-viktad data. Den tredje modellen tränades på både T1- och T2-viktad data genom högnivå-fusion. Vi fann att användning av multimodal data minskade det genomsnittliga absoluta felet för estimerade åldrar. En fjärde modell använde separering (eng. disentanglement) för att skapa en representation som är robust vid avsaknad av T1- eller T2-viktad data. Resultaten var lika för denna modell och basmodellerna, vilket innebär att modellen är robust mot avsaknad av data, utan någon betydande försämring i noggranhet.
3
Buckberry, Jo, and M. Brickley. "Estimation of juvenile age at death." CIFA, 2018. http://hdl.handle.net/10454/17519.
Full text
4
CASTRO, JOSE DAVID BERMUDEZ. "AGE ESTIMATION FROM FACIALS IMAGES." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2015. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=25755@1.
Full textAbstract:
PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIROCOORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR
PROGRAMA DE EXCELENCIA ACADEMICA
Esta dissertação tem por objetivo investigar métodos de estimação da idade a partir de imagens faciais. Avalia-se o impacto de distintos fatores sobre a acurácia da estimativa, especificamente, a acurácia da localização de pontos fiduciais, métodos de extração de atributos, de redução de dimensionalidade, e técnicas de regressão. Adicionalmente, foi estudada a influência da raça e do sexo na acurácia da estimação da idade desenvolvido. Consideraram-se cinco métricas de desempenho do sistema, especificamente, o erro médio absoluto (MAE), o erro médio absoluto por década (MAE/D), o erro médio absoluto por idade (MAE/A), o escore acumulado (CS), e os intervalos de confiança (IC). Os experimentos foram realizados empregando dois bancos de dados públicos, cujas imagens estão rotuladas com a idade da face. Os resultados indicaram que o método automático para detecção de pontos fiduciais da face tem uma repercussão moderada sobre a acurácia das estimativas. Entre as variantes analisadas, a que apresentou a melhor acurácia foi o sistema que emprega os AAMs (Active Appearance Models) como método de extração de atributos, o PCA (Principal Components Analysis) como método para reduzir dimensionalidade, e as SVRs (Support Vector Regression) como técnica para fazer regressão.
This thesis aims to investigate methods for age estimation from facial images. The impact of distinct factors over the estimate’s accuracy is assessed, specifically the accuracy in the location of face fiducial points, feature extraction and dimensionality reduction methods, and regression techniques. Additionally, the dependence on race and gender in the accuracy of age estimation is assessed. Five performance metrics have been considered: the mean absolute error (MAE), the mean absolute error per decade (MAE / D), the mean absolute error for age (MAE / A), the cumulative score (CS) and confidence intervals (CI). The experiments were performed using two public databases, whose images are labeled with the age of the face. The results showed the impact of the automatic method for detection of fiducial points of the face has a moderate impact on the accuracy of the estimates. Among the analyzed variants, the one with the best accuracy was the system that employs the Active Appearance Models (AAMs) as feature extraction method, the Principal Components Analysis (PCA) as dimensionality reduction method, and Support Vector Regression (SVRs) as a technique to do regression.
5
Heydenrych, Matthew James. "Epigenetic age estimation of cetaceans." Thesis, Curtin University, 2021. http://hdl.handle.net/20.500.11937/84801.
Full textAbstract:
Age is an important biological parameter which can be used to guide conservation. It is difficult to assess in wild populations, however, and especially in many cetacean species. Epigenetic analyses now offer an alternative for age estimation. In this thesis, I identified the benefits and considerations of epigenetic age estimators for cetaceans, developed a novel high-throughput sequencing workflow for homology-based epigenetic analyses, and successfully built age estimation assays for both sperm and Southern right whales.
6
Wu, Yang-Huang. "Sequential estimation of age replacement policies." Thesis, Monterey, California : Naval Postgraduate School, 1990. http://handle.dtic.mil/100.2/ADA226614.
Full textAbstract:
Thesis (M.S. in Operations Research)-- Naval Postgraduate School, March 1990.Thesis Advisor(s): Whitaker, Lyn R. Second Reader: Esary, James D. "March 1990." Description based on signature page as viewed on August 26, 2009. Author(s) subject terms: Sequential Estimation Procedure, Age Replacement Policy, Optimal Replacement, Preventive Maintenance. Includes bibliographical references (p. 54-55). Also available online.
7
Ng, Choon Ching. "Face age estimation using wrinkle patterns." Thesis, Manchester Metropolitan University, 2015. http://e-space.mmu.ac.uk/595499/.
Full textAbstract:
Face age estimation is a challenging problem due to the variation of craniofacial growth, skin texture, gender and race. With recent growth in face age estimation research, wrinkles received attention from a number of research, as it is generally perceived as aging feature and soft biometric for person identification. In a face image, wrinkle is a discontinuous and arbitrary line pattern that varies in different face regions and subjects. Existing wrinkle detection algorithms and wrinkle-based features are not robust for face age estimation. They are either weakly represented or not validated against the ground truth. The primary aim of this thesis is to develop a robust wrinkle detection method and construct novel wrinkle-based methods for face age estimation. First, Hybrid Hessian Filter (HHF) is proposed to segment the wrinkles using the directional gradient and a ridge-valley Gaussian kernel. Second, Hessian Line Tracking (HLT) is proposed for wrinkle detection by exploring the wrinkle connectivity of surrounding pixels using a cross-sectional profile. Experimental results showed that HLT outperforms other wrinkle detection algorithms with an accuracy of 84% and 79% on the datasets of FORERUS and FORERET while HHF achieves 77% and 49%, respectively. Third, Multi-scale Wrinkle Patterns (MWP) is proposed as a novel feature representation for face age estimation using the wrinkle location, intensity and density. Fourth, Hybrid Aging Patterns (HAP) is proposed as a hybrid pattern for face age estimation using Facial Appearance Model (FAM) and MWP. Fifth, Multi-layer Age Regression (MAR) is proposed as a hierarchical model in complementary of FAM and MWP for face age estimation. For performance assessment of age estimation, four datasets namely FGNET, MORPH, FERET and PAL with different age ranges and sample sizes are used as benchmarks. Results showed that MAR achieves the lowest Mean Absolute Error (MAE) of 3.00 ( 4.14) on FERET and HAP scores a comparable MAE of 3.02 ( 2.92) as state of the art. In conclusion, wrinkles are important features and the uniqueness of this pattern should be considered in developing a robust model for face age estimation.
8
Dissanayake, Lekamlage Dilukshi Charitha Subashini Dissanayake, and Fabia Afzal. "AI-based Age Estimation from Mammograms." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-20108.
Full textAbstract:
Background: Age estimation has attracted attention because of its various clinical and medical applications. There are many studies on human age estimation from biomedical images such as X-ray images, MRI, facial images, dental images etc. However, there is no research done on mammograms for age estimation. Therefore, in our research, we focus on age estimation from mammogram images. Objectives: The purpose of this study is to make an AI-based model for estimating age from mammogram images based on the pectoral muscle segment and check its accuracy. At first, we segment the pectoral muscle from mammograms. Then we extract deep learning features and handcrafted features from the pectoral muscle segment as well as other regions for comparison. From these features, we built models to estimate the age. Methods: We have selected an experiment method to answer our research question. We have used the U-net model for pectoral muscle segmentation. After that, we have extracted handcrafted features and deep learning features from pectoral muscle using ResNet-50 and Xception. Then we trained Support Vector Regression and Random Forest models to estimate the age based on the pectoral muscle of mammograms. Finally, we observed how accurately these models are in estimating the age by comparing the MSE and MAE values. We have considered breast region (BR) and the whole MLO to answer our research question. Results: The MAE values for both SVR and RF models from handcrafted features is around 10 in years in all cases. On the other hand, with deep learning features MAE is less as compared to handcrafted features. In our experiment, the least observed error value for MAE was around 8.4656 years for the model that extracted the features from the whole MLO using ResNet50 and SVR as the regression model. Conclusions: We have concluded that the breast region (BR) is more accurate in estimating the age compared to PM by having least MAE and MSE values in its models. Moreover, we were able to observe that handcrafted feature models are not as accurate as deep feature models in estimating the age from mammograms.
9
Hackman, S. Lucina M. R. "Age estimation in the living : a test of 6 radiographic methods." Thesis, University of Dundee, 2012. https://discovery.dundee.ac.uk/en/studentTheses/b8281974-f44c-444d-b958-001ccfea451f.
Full textAbstract:
There is a growing recognition that there is a requirement for methods of age estimation of the living to be rigorously tested to ensure that they are accurate, reliable and valid for use in forensic and humanitarian age estimation. The necessity for accurate and reliable methods of age estimation are driven both by humanitarian, political and judicial need. Age estimation methods commonly in use today are based on the application of reference standards, known as atlases, which were developed using data collected from children who participated in longitudinal studies in the early to mid-1900s. The standards were originally developed to provide a baseline to which radiographs could be compared in order to assess the child’s stage of skeletal development in relation to their chronological age, a purpose for which they are still utilised in the medical community. These atlases provide a testable link between skeletal age and chronological age which has been recognised by forensic practitioners who have essentially hijacked this medical capability and applied it to their fields. This has resulted in an increased use of these standards as a method of predicting the chronological age from the skeletal age of a child when the former is unknown. This novel use of the atlases on populations who are distinct, ethnically, temporally and geographically, from those whose data was gathered and was used in the design of the standard leaves the forensic outcomes vulnerable to challenge in court. This study aims to examine the reliability and accuracy of these standards in relation to a modern population, providing a sound statistical base for the use of these standards for forensic purposes. Radiographs were collected from the local hospital from children who had been X-rayed for investigation during attendance at the local A&E department. Four body areas were selected for investigation; the hand-wrist, the elbow, the knee and the foot-ankle and tests were undertaken to assess the radiographs using six commonly uses methods of age estimation. Further images of the wrist and elbow were collected from children in New Delhi, India. These images were subject to age estimation utilising the methods described.
10
Kemp, Bryn. "Gestational age estimation in resource poor settings." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:d9ce6416-c6b6-4c06-9992-90ddeaec14e7.
Full textAbstract:
Background and objectives: The incidence of preterm birth (PTB), and the extent to which it results in perinatal mortality in sub-Saharan Africa (sSA) is unclear, partly because reliable estimates of gestational age (GA) at birth are lacking. This research: 1) Describes how clinical and ultrasound (US) estimates of gestational age (GA) influence PTB rates and perinatal mortality amongst a population in Kilifi, Kenya; 2) Implements a novel PTB classification system as proof of concept that such systems are feasible in low-income settings, and 3) Presents two novel approaches for estimating GA for women presenting >24 weeks’ gestation. Methods: Objectives 1) and 2) used a perinatal surveillance platform developed at the KEMRI/Wellcome Trust Research Programme in Kilifi, Kenya. Ultrasound (US) was offered for GA estimation in women ≤24 weeks’ gestation clinically. To achieve objective 3), two candidate US dating equations were derived by combining a machine learning algorithm with polynomial regression analyses. Lastly, an entirely automated model with the capacity to estimate GA using computational image analysis of the fetal cerebral cortex was developed and tested. Results: 1) Between November 2011 and July 2013, 3630 women presented for antenatal care, 1107 women had US and data were available for 950 (86%) of these. The PTB rate by US (US-GA) was 10.0% compared to 17.1% by a best clinical estimate of GA (C-GA), although the number of perinatal deaths that were preterm by US and C-GA were similar; 2) Implementation of a novel PTB classification system is feasible, and 3) New dating equations and an automated model provide estimates in the 3rd trimester with a prediction error at 34 weeks of 12.4 and 14.2 days, respectively. Conclusion: Clinical estimates of GA significantly overestimate the rate of PTBs. Despite this, the proportion of perinatal deaths in those identified as preterm by clinical and US methods was similar, suggesting that US may be a better predictor of PTB and its associated mortality. Novel dating methods can estimate GA at 34 weeks’ gestation with an error equivalent to that provided by routine clinical methods at 22 weeks’. This has important implications and may extend capacity to provide GA estimates amongst a large group of women whose birth phenotypes remain poorly described.
11
Uyar, Olcay. "Sequential estimation of optimal age replacement policies." Thesis, Monterey, California : Naval Postgraduate School, 1990. http://handle.dtic.mil/100.2/ADA238696.
Full textAbstract:
Thesis (M.S. in Operations Research)--Naval Postgraduate School, September 1990.Thesis Advisor(s): Whitaker, Lyn R. Second Reader: Read, Robert R. "September 1990." Description based on title screen as viewed on December 18, 2009. DTIC Identifier(s): Replacement Theory, Cost Analysis, Weibull Distribution Function, Gamma Distribution Functions, Theses. Author(s) subject terms: Sequential Estimation Procedure, Age Replacement Policy, Optimal Replacement, Preventive Maintenance. Includes bibliographical references (p. 72-73). Also available in print.
12
Bukar, Ali M. "Automatic age progression and estimation from faces." Thesis, University of Bradford, 2017. http://hdl.handle.net/10454/17348.
Full textAbstract:
Recently, automatic age progression has gained popularity due to its numerous applications. Among these is the frequent search for missing people, in the UK alone up to 300,000 people are reported missing every year. Although many algorithms have been proposed, most of the methods are affected by image noise, illumination variations, and facial expressions. Furthermore, most of the algorithms use a pattern caricaturing approach which infers ages by manipulating the target image and a template face formed by averaging faces at the intended age. To this end, this thesis investigates the problem with a view to tackling the most prominent issues associated with the existing algorithms. Initially using active appearance models (AAM), facial features are extracted and mapped to people’s ages, afterward a formula is derived which allows the convenient generation of age progressed images irrespective of whether the intended age exists in the training database or not. In order to handle image noise as well as varying facial expressions, a nonlinear appearance model called kernel appearance model (KAM) is derived. To illustrate the real application of automatic age progression, both AAM and KAM based algorithms are then used to synthesise faces of two popular long missing British and Irish kids; Ben Needham and Mary Boyle. However, both statistical techniques exhibit image rendering artefacts such as low-resolution output and the generation of inconsistent skin tone. To circumvent this problem, a hybrid texture enhancement pipeline is developed. To further ensure that the progressed images preserve people’s identities while at the same time attaining the intended age, rigorous human and machine based tests are conducted; part of this tests resulted to the development of a robust age estimation algorithm. Eventually, the results of the rigorous assessment reveal that the hybrid technique is able to handle all existing problems of age progression with minimal error.National Information Technology Development Agency of Nigeria (NITDA)
13
Åkesson, Emil. "Age of the Cremated : On the estimation of age of burnt human remains." Thesis, Stockholms universitet, Osteoarkeologiska forskningslaboratoriet, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-182048.
Full textAbstract:
The estimation of age is an important aspect in osteoarchaeological analysis. In order to understand people and their fates in past societies, researchers must turn to palaeodemography. Therefore, it is vital that the methods of age estimation, which the foundations of palaeodemographic reconstructions rest upon, are as accurate and reliable as possible. In current Swedish cremation-osteoarchaeology, two methods of age estimation are commonly used: suture closure and relative thickness of the diploë. However, no substantial evaluation of these two methods have been undertaken. This study aims to evaluate the two methods of age estimation of cremated remains, suture closure and relative thickness of the diploë. This was done by testing the two methods on two unburnt populations, Mediaeval city-dwellers from Helgeandsholmen, Stockholm, Sweden, and Middle-Neolithic hunter-gatherers from Ajvide, Gotland, Sweden. Suture closure and proportion of diploë was observed in comparison with age-related changes of the auricular surface of the ilium and the pubic symphysis. Based on the results of the study, possible courses of action were proposed and then applied on cremated remains from a Late Iron Age burial ground on Lovö, Stockholm, Sweden. The results showed significant moderate correlation with age for both methods (0.61 for suture closure and 0.58 for proportion of diploë). However, early stage of suture closure could identify a group consisting of juveniles and young adults, while advanced suture closure could identify a group consisting of middle adults and old adults. These results, which proved to be more reliable than existing methods, can, hopefully, lead to improvements of the assessment of age in cremated remains, and increase our understanding of the fates of people of the past.
14
Gómez, García-Donas Julia. "Age estimation on two Mediterranean samples using rib histomorphometry." Thesis, University of Edinburgh, 2018. http://hdl.handle.net/1842/31496.
Full textAbstract:
Estimation of age is a crucial step for the identification of unknown individuals. Age is commonly assessed through macroscopic analytical methods based on the gross-examination of age degenerative changes in the skeleton. The choice of the methods relies on the taphonomic condition of the human remains and/or the skeletal element that is available. In cases of very fragmented bones, microscopic techniques remain one of the few approaches to estimate age. Thus, many histological age estimation methods have been developed for different bones and on different samples in the last forty years. Numerous intrinsic and extrinsic factors influence bone remodelling rates and have shown to affect the accuracy of histological aging methods. The present study investigates rib thin-sections from two Mediterranean samples, aiming to explore the applicability and reliability of histological methods in estimating age within these samples. Standard ribs were obtained from males and females (N = 88, Mean age = 60, SD = 17.90) from two samples, Cretans (Greece) and Greek- Cypriots (Republic of Cyprus). The costal elements were processed histologically according to standard protocols and thirteen raw and composite histomorphometric parameters (frequency number of intact and fragmentary osteons, total osteons, osteon population densities - including OPD(I) and OPD(F) - cortical area, total area, endosteal area, relative cortical area, osteon area, osteon perimeter and osteon circularity) were assessed. Intra- and inter-observer errors were examined. Due to the fragmented nature of the costal elements, sampling error was calculated as a means to explore whether the histological variables vary among six different topographical locations along the rib length. A validation study was carried out by applying four existing histological age prediction equations on the entire dataset and on the sub-datasets (sex and samples separately) in order to verify whether population-specific formulae are required for the Mediterranean samples. The relationship between the histological variables and age, as well as sex and samples, was determined through several statistical tests. Lastly, simple and multiple regression analyses were performed testing all possible combinations of variables. The best models ii were finally selected according to prediction power and goodness of fit indicators. The results from intra- and inter-observer errors indicated that most of the histological parameters achieved high levels of repeatability. The preliminary outcome from the sampling error pilot study suggested low variability among the six thin-sections from each rib. According to the validation study, three of the four age prediction equations resulted in high underestimation of age, indicating that population-specific formulae are needed to provide more accurate age estimates. Most of the histological variables showed a statistically significant correlation with age with some differences observed by sex and by sample. Forty-one models were generated concluding that osteon densities along with rib and osteon measurements formulae produced the most accurate results. The best model generated from the entire dataset included OPD and osteon circularity with a standard error of the estimate of 10.45 years. When sex and samples were separated, the best model selected included OPD and osteon perimeter producing a standard error of the estimate of 8 years for Cypriots. This research demonstrates that quantitative bone histology is a feasible method to estimate age on the Mediterranean samples obtaining errors rates that are in accordance with macroscopic ageing techniques. Inter-population variation in remodeling rates is suggested; however, the inclusion of other bones presenting different remodelling dynamics (such as femora) is recommended to further explore this hypothesis. This study contributes to the creation of population-specific standards for Cretans and Cypriots.
15
Ingraham, Mark R. "Histological age estimation of the midshaft clavicle using a new digital technique." Thesis, University of North Texas, 2004. https://digital.library.unt.edu/ark:/67531/metadc4604/.
Full textAbstract:
Histological methods to estimate skeletal age at death, in forensic cases, are an alternative to the more traditional gross morphological methods. Most histological methods utilize counts of bone type within a given field for their estimation. The method presented in this paper uses the percentage area occupied by unremodeled bone to estimate age. The percentage area occupied by unremodeled bone is used in a linear regression model to predict skeletal age at death. Additionally, this method uses digital software to measure area rather than the traditional technique in which a gridded microscope is used to estimate area. The clavicle was chosen as a sample site since it is not a weight bearing bone and has little muscular insertion. These factors reduce the variation seen as a result of differences in lifestyle or activity pattern.
16
Sanders, Jennifer Ellen. "Age Estimation of Fetal Skeletal Remains from the Forensic Context." The University of Montana, 2010. http://etd.lib.umt.edu/theses/available/etd-12162009-131218/.
Full textAbstract:
This study tested the efficacy of the traditional method (Fazekas and Kosa, 1978) of aging fetal remains from the forensic context against ultrasound (Chevernak et al., 1998)and radiographic (Sherwood et al., 2000) methods to determine which was most accurate. Two data sets were used in this study. The first consisted of measurements from historic (1902-1917) fetal remains of known age. The second consisted of measurements from modern fetal remains of known age from the forensic context. Using these samples in the different prediction models for aging fetal remains, the accuracy of each was determined.
17
Sensor, Jennifer Dawn. "HEARING AND AGE ESTIMATION IN TWO SPECIES OF ARCTIC WHALE." Kent State University / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=kent1512125887991219.
Full text
18
McGuire, Christy L. "Age differences in recall, strategies and estimation accuracy on free recall task." Thesis, Georgia Institute of Technology, 1997. http://hdl.handle.net/1853/29198.
Full text
19
Barette, Tammy S. "A Bayesian approach to the estimation of adult skeletal age assessing the facility of multifactorial and three-dimensional methods to improve accuracy of age estimation /." Columbus, Ohio : Ohio State University, 2007. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1180543680.
Full text
20
McBride, David Glynn. "Longitudinal assessment of age-related change in the dental pulp chamber and age estimation using dental radiographs." Diss., Columbia, Mo. : University of Missouri-Columbia, 2007. http://hdl.handle.net/10355/4745.
Full textAbstract:
Thesis (Ph. D.)--University of Missouri-Columbia, 2007.The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on September 28, 2007) Vita. Includes bibliographical references.
21
Liversidge, Helen Mary. "Human tooth development in an archaeological population of known age." Thesis, University College London (University of London), 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.318134.
Full textAbstract:
This thesis documents dental maturation in a mid C18, early C19 population where age at death is known (N=63, age range birth and 5.4 years). Emphasis is placed on the mineralization of individual deciduous and certain permanent teeth. In the first part of this thesis, the literature on dental maturation is reviewed with special reference to radiographic studies of populations, methodology and statistical analysis. Quantitative data on developing teeth, population differences and age estimation are also reviewed. In the second part of the thesis the Spitalfields material is described and used to investigate the accuracy of five types of age estimating methods that make use of the developing dentition. It emerges that the atlas method of Schour and Massler (1941) predicted age best. The third part of the thesis documents dental development in the Spitalfields Collection. New data for human deciduous anterior teeth and early stages of permanent anterior teeth are presented. In this study, few permanent anterior tooth crowns were complete before 5 years of age, contrary to published data from radiographic studies. Alveolar eruption of deciduous teeth and measurements of tooth length and weight are presented and discussed in context with published standards. The fourth part of this thesis is a preliminary investigation of cranial and postcranial development in this population. The fifth part is an appendix of data.
22
Davies, Catriona Mairead. "Skeletal age estimation and the epiphyseal scar : challenging the status quo." Thesis, University of Dundee, 2013. https://discovery.dundee.ac.uk/en/studentTheses/3a8569f0-eb7c-4cb7-a063-2e5006ba4b2e.
Full text
23
Islam, Mofakharul. "Age estimation and illicit image detection using a stochastic vision model." Thesis, University of Ballarat, 2013. http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/44503.
Full textAbstract:
The main objective of this research is to investigate and implement a robust approach with a view to provide the Law Enforcement Agencies (LEAs) with a dedicated forensic tool in future for inspecting confiscated PCs from the suspected paedophile to detect pedophilic images automatically and prevent children viewing pornographic and age-inappropriate images at their home and school and adults at their workplace while they are on the Internet. To achieve this goal, we use a novel face descriptor to differentiate child face from adult face based on categorical age specific contextual cues that are based on new knowledge in terms of features or contexts representatives of child and adult face. Given that the craniofacial cues contain enough structural information on visual cues on human face encoded in the form of high level features we can categorize age into adult and children in tandem with low level features. Finally, we will present a novel stochastic vision model based on Markov Random Fields (MRF) prior, which learned the pornographic contextual constraints from the training pornographic images and eventually introduce knowledge on pornography into our proposed stochastic classifier allowing classification of images into pornographic or benign.Doctor of Philosophy
24
FitzGerald, Charles Michael. "Tooth crown formation and the variation of enamel microstructural growth markers in modern humans." Thesis, University of Cambridge, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.360038.
Full text
25
Kirk, Jason Dale. "Cranial suture closure: A quantitative method for age estimation using laser instrumentation." Thesis, Wichita State University, 2007. http://hdl.handle.net/10057/1520.
Full textAbstract:
Cranial suture closure has long been recognized as a character of human development related to aging. For this reason, it has been utilized for forensic and archaeological studies to determine the age at death of unidentified and skeletonized individuals. Despite remaining a popular age indicator today, studies dating back to the 19th Century have published contradictory results on the nature of this relationship. Many authors have concluded that cranial suture closure exhibits, at most, a sketchy relationship with age and should not be used as an age indicator, whereas others have supported its inclusion despite a wide range of variability. Traditional methods for assessing cranial suture closure all defined degrees of obliteration and assigned discrete scores. However, with the development of technology, new techniques may be capable of better assessing the association of cranial suture closure in age. The current study is an attempt to address cranial suture closure with a new quantitative method that utilizes laser technology. 196 black male crania from the Hamann-Todd Collection were observed. The suture landmarks established by Meindl and Lovejoy were recorded standard scores and were also scanned with the laser device, which quantifies the amount of reflected light off of a surface. The results showed that the laser device accurately and consistently quantifies light reflected through a suture joint, especially when calibrated to the surrounding bone. A general trend for the laser measurements to decrease with age was observed. It was concluded that a relationship between suture closure and age does exist, but other factors affecting suture closure should not be overlooked. Further application of the laser method, through the refinement of data collection techniques and the device used, may increase what is known on the structure and development of the skull, and may be able to more precisely
elucidate the tenuous relationship between suture closure and age.Thesis [M.A]: Wichita State University, College of College of Liberal Arts and Sciences, Dept. of Anthropology
"December 2007."
26
Kirk, Jason Dale Moore-Jansen Peer H. "Cranial suture closure: A quantitative method for age estimation using laser instrumentation /." Thesis, A link to full text of this thesis in SOAR, 2007. http://hdl.handle.net/10057/1520.
Full text
27
Anderson, Melissa Fay. "Estimation of adult skeletal age-at-death using the Sugeno fuzzy integral." Diss., Columbia, Mo. : University of Missouri-Columbia, 2008. http://hdl.handle.net/10355/5750.
Full textAbstract:
Thesis (M.A.)--University of Missouri-Columbia, 2008.The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on July 7, 2009) Includes bibliographical references.
28
Elgamri, Alya Isam Eldin Gafar. "A Comparison of the dental age estimation methods of Phillips and Proffit in a sample of South African children at the Tygerberg Dental Faculty." University of the Western Cape, 2015. http://hdl.handle.net/11394/5036.
Full textAbstract:
Magister Scientiae Dentium - MSc(Dent)Background: Dental age is an indicator of the physiological maturity of growing children. Different methods for estimating the dental age in comparison to the chronological age were proposed in the literature. Objective: The aim of this study was to compare the accuracy of two methods i.e. the Phillips and Proffit methods in estimating the dental age in a sample of South African children at the Tygerberg dental faculty. Methods: A retrospective study was conducted by randomly selecting 100 panoramic radiographs with known chronological age. The sample contained an equal number of girls and boys (50 in each group) and the chronological age ranged between 6 and 11 years. Dental age for each radiograph was estimated using the Phillips and the Proffit methods respectively. The mean difference between dental and chronological age was calculated. Dental and chronological ages were compared using overall bias and random errors. Results: The results showed that for the girls’ sample, the Phillips method underestimated the age by 4 months which is statistically significant (p-value =0.03). The Proffit method underestimated the age by 2 days which is not statistically significant (p-value =0.97). Both methods however have the same frequency of random errors. For the boys’ sample, Phillips’ method underestimated the age by 6 months which is statistically significant (p-value <0.0001). Proffit’s method underestimated the age by 2 months which is not statistically significant (p-value= 0.15). The Phillips method was shown to have fewer random errors in boys. Discussion: The above mentioned results showed that for dental age estimation for girls, Proffit’s method would be more appropriate. This rationale is explained by the conclusion that it only underestimates the age by 2 days and has the same frequency of random errors as Phillips’ method. However, if one had to choose between the two methods for boys, the situation should be evaluated carefully. For boys, the Phillips method has fewer random errors but a larger overall bias (6 months) whereas Proffit’s method has more random errors but less overall bias (2 months). The choice between the two methods should therefore depend on the purpose of the estimation. If the method is used for estimating the age in a single individual with an unknown chronological age, Phillips’ method would be more preferable. However, if the method is used for age estimation in populations with a known mean chronological age, Proffit is preferred. Conclusion: Proffit’s description for dental development has been shown to be accurate in estimating the DA. It may therefore be considered to be a legitimate DA estimation method and not just a developmental description for the dentition.
29
Renström, Klara. "Automatic age estimation of children based on brain matter composition using quantitative MRI." Thesis, Linköpings universitet, Medicinsk informatik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-119431.
Full textAbstract:
The development of a child can be monitored by studying the changes in physical appearance or the development of capabilities e.g. walking and talking. But is it possible to find a quantitative measure for brain development? The aim of this thesis work is to investigate that possibility using quantitative magnetic resonance imaging (qMRI) images by answering the following questions: Can brain development be determined using qMRI? If so, what properties of the brain can be used? Can the age of a child be automatically detected with an algorithm? If so, how can this algorithm function? With what accuracy? Previous studies have shown that it is possible to detect properties in the brain changing with age, based on MRI images. These properties have e.g. been changes in T1 and T2 relaxation time, i.e. properties in water signal behavior that can be measured using multiple MR acquisitions. In the literature this was linked to a rapid myelination process that occurs after birth. Furthermore the organization and growth of the brain is a property that can be measured and monitored. This thesis have investigated several different properties in the brain based on qMRI images in order to identify those who have a strong correlation with age in the range 0-20 years. The properties that were found to have a high correlation were: Position of the first histogram peak in T1 weighted qMRI images, Fraction of white matter in the brain, Mean pixel value of PD weighted qMRI images, Volume of white matter in the brain, Curves on the form f(x) = ae^(-bx) +c are fitted to the data sets and confidence intervals are calculated to frame the statistical insecurity of the curve. The mean error in percent for the different properties can be seen in the list below: Property, Mean error [%] 0-20 years, Mean error [%] 0-3 years Peak position: 53.84, 98.17 Fraction of WM: 118.97, 71.67 Mean pixel value: 200.89, 126.28 Volume of WM: 241.72, 72.58 The conclusions drawn based on the presented results are that there are properties in the brain that correlates well to aging, but the error is too large for making a valid prediction of age over the entire range of 0-20 years. When decreasing the age range to 0-3 years the mean error becomes smaller, but it is still too large. More data is needed to evaluate and improve this result.
30
Liversidge, H. M., Jo Buckberry, and N. Marquez-Grant. "Age estimation [editorial]." Master's thesis, 2015. http://hdl.handle.net/10454/7448.
Full textAbstract:
yesAssessing and interpreting dental and skeletal age-related changes in both the living and the dead is of interest to a wide range of disciplines (e.g. see Bittles and Collins 1986) including human biology, paediatrics, public health, palaeodemography, archaeology, palaeontology, human evolution, forensic anthropology and legal medicine. ... This special issue of Annals of Human Biology arises from the 55th annual symposium of the Society for the Study of Human Biology in association with the British Association for Biological Anthropological and Osteoarchaeology held in Oxford, UK, from 9–11 December 2014. Only a selection of the presentations are included here which encompass some of the major recent advances in age estimation from the dentition and skeleton.
31
Al-Romaithy, Nawwar Ali Jassim, and 羅智光. "Age and Gender Estimation." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/82872692200161963335.
Full textAbstract:
碩士國立臺灣大學
資訊工程學研究所
102
A method for estimating age and gender using multiple local patches is proposed in this thesis. We use the histogram of rotation-invariant local binary pattern as our features to train the SVM model. We further introduce the shifting and scaling of the local patches to enhance the accuracy of the estimation. Our proposed method not only provides accurate results but also can be incorporated with other methods to further improve their accuracy.
32
Wu, Mei-yao, and 吳美瑤. "Age, attention, and time estimation." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/84659089151689819970.
Full textAbstract:
碩士國立政治大學
心理學研究所
93
The purpose of this study was to investigate the effects of the attention and age on time estimation based on the prospective timing paradigm. Four timing tasks, with different degrees of attentional requirement, were utilized to test timing of reproducing the target intervals in three groups of different ages including the lower-grade (M= 7.5 years), higher-grade (M= 11.2 years) elementary school students and adult (M= 20.1 years). The subjects in this work were asked to estimate a stimulus duration lasting for 7 or 14 s, during which they are required to either do or do not perform a concurrent non-temporal task. Thus, the experimental design for the present study was mixed with between-subject factors (age and task) and a within-subject factor (target interval). The results showed (1) the lower-grade children performed less accurate than the higher-grade children; (2) all subjects had worse timing performance in the dual-task condition than the single-task or control condition, which effect was most evident in the lower-grade children; (3) all subjects reproduced shorter interval as compared to the target interval, which effect was most apparently observed from the dual-task for the lower-grade children; (4) the lower-grade children had less reliability in timing; and (5) the effect of age on the single-task and control condition is not significant. Together, these data indicate that concurrent non-temporal task cause temporal reproduction shorter, especially under high attention demand in lower-grade children. In addition to the influence by the task complexity, the accuracy of timing estimation depends on the age. Keywords: time reproduction、age and development、dual task、attention、elementary school student、Scalar expectancy theory(SET)
33
Bukar, Ali M., and Hassan Ugail. "Convnet features for age estimation." 2017. http://hdl.handle.net/10454/12860.
Full textAbstract:
NoResearch in facial age estimation has been active for over a decade. This is due to its numerous applications. Recently, convolutional neural networks (CNNs) have been used in an attempt to solve this age old problem. For this purpose, researchers have proposed various CNN architectures. Unfortunately, most of the proposed techniques have been based on relatively ‘shallow’ networks. In this work, we leverage the capability of an off-the-shelf deep CNN model, namely the VGG-Face model, which has been trained on millions of face images. Interestingly, despite being a simple approach, features extracted from the VGG-Face model, when reduced and fed into linear regressors, outperform most of the state-of-the-art CNNs. e.g. on both FGNET-AD and Morph II benchmark databases. Furthermore, contrary to using the last fully connected (FC) layer of the trained model, we evaluate the activations from different layers of the architecture. In fact, our experiments show that generic features learnt from intermediate layer activations carry more ageing information than the FC layers.
34
Xu, Minle. "Bayesian ridge estimation of age-period-cohort models." Thesis, 2014. http://hdl.handle.net/2152/26250.
Full textAbstract:
Age-Period-Cohort models offer a useful framework to study trends of time-specific phenomena in various areas. Yet the perfect linear relationship among age, period, and cohort induces a singular design matrix and brings about the identification issue of age, period, and cohort model due to the identity Cohort = Period -- Age. Over the last few decades, multiple methods have been proposed to cope with the identification issue, e.g., the intrinsic estimator (IE), which may be viewed as a limiting form of ridge regression. This study views the ridge estimator from a Bayesian perspective by introducing a prior distribution(s) for the ridge parameter(s). Data used in this study describe the incidence rate of cervical cancer among Ontario women from 1960 to 1994. Results indicate that a Bayesian ridge model with a common prior for the ridge parameter yields estimates of age, period, and cohort effects similar to those based on the intrinsic estimator and to those based on a ridge estimator. The performance of Bayesian models with distinctive priors for the ridge parameters of age, period, and cohort effects is affected more by the choice of prior distributions. In sum, a Bayesian ridge model is an alternative way to deal with the identification problem of age, period, and cohort model. Future studies should further investigate the influences of different prior choices on Bayesian ridge models.text
35
高登威. "Deep transfer learning for age estimation." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/5d7h6f.
Full textAbstract:
碩士國立臺南大學
資訊工程學系碩士班
106
Deep transfer learning for age estimation Student：Teng-Wei Kao Advisors：Jiann-Shu Lee Department of Computer Science and Information Engineering National University of Tainan There are many consumer activities or commercial advertisement dependent on the age of a person. Therefore, computer vision based age estimation methods, without the need of subject’s deliberate cooperation, has attracted widespread attention. However, the process of human facial aging is affected by the both internal and external factors. Hence, it is a challenging issue. To improve the accuracy of facial age estimation, we propose a new method using a deep learning architecture combined with transfer learning strategy. This method can effectively extract low to high level features from facial images. Correlation based feature polishing approach was developed to extract the effective features with lower dimensions but with expressibility. The experimental results show that the proposed method can achieve more accurate age estimation results. Keywords: Age estimation, Convolutional neural network, Transfer learning
36
Wei, Shih-Min, and 魏士閔. "Age Estimation Based on Facial Aging Patterns." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/57927135262031031622.
Full textAbstract:
碩士淡江大學
資訊工程學系資訊網路與通訊碩士班
102
This paper proposes an age estimation method that improves the method proposed by Xin Geng et al. in some respects: (1). Time efficiency is improved by using 2DPCA instead of PCA. (2). To solve the problem of having infinitely many solutions inherent in the system for solving the projection vectors, we modified the coefficient matrix of the system so the unique solution can be easily evaluated. (3). The proposed method was tested in several fashions to analyze possible factors that cause some problems.
37
Chang, Chun-Te, and 章春德. "Age Estimation via Modern Convolutional Neural Networks." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/37y672.
Full textAbstract:
碩士國立臺中科技大學
資訊工程系碩士班
107
Age estimation has versatile applications. For example, department stores could stimulate buying for different age customers passed by with age-oriented advertisements or the surveillance systems at public area could filter the unattended children or elders and provide assistance. This study uses convolutional neural networks for age estimation. Firstly, the system detects faces in the image, and gets the positions of eyes, then crops the face area and aligns the face. Finally, the cropped image is input into convolutional neural network for extracting features and estimating the face age. The study uses Xception’s Depthwise Separable Convolution for reducing computation complexities and multi-paths convolution for enforcing features extracting abilities, uses label distribution age encoding and KLD loss function for enhancing the neural network learning abilities, uses highest probability, expected value and KLD similarity for final age estimation. The IMDB-WIKI dataset is used as pre-training dataset. The APPA-REAL (including training set and validation set) is used as finetune dataset. The APPA-REAL, FG-NET and MORPH-II are the target datasets which have become new benchmarks on age estimation. We achieve the state-of-the-art results of mean absolute error (MAE) 3.385, 2.78, and 2.88 years on APPA-REAL, FG-NET, and MORPH-II test sets, and ϵ-error 0.2589 on LAP-2016 test set respectively.
38
Lin, Chun-Man, and 林君蔓. "Apparent Age Estimation Based on CNN Model." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/g9wspb.
Full textAbstract:
碩士國立東華大學
資訊工程學系
107
Age estimation has been one of hot topics in computer vision. Identifying personal characteristics such as age, personal identity, gender, and ethnicity through images is an interesting but challenging problem. In recent years, age estimation has become an attractive research topic because it can be widely applied to human life. For example: (1) devices with age recognition can automatically filter age-restricted products, such as cigarettes and alcohol. (2) Since shopping habit and preferences of different age groups are very different, the automatic collection of age data can provide relevant information for market analysis, such as Electronic customer relationship management (ECRM). (3) Age is a biological feature that can be used to assist major biometrics to improve the accuracy of human recognition, verification or authentication applications. As deep learning is widely used in the computer vision, the accuracy of age estimation is also increasing. Early CNN-based works used four to five layers for depth; however, current works adopts a deeper structure and it results in more accurate results. This thesis proposes an age estimation system based on CNN deep learning architecture. The proposed system is modified from DEX system of which VGG16 is adopted as the learning core. We incorporate a multi-loss function which takes into accout the losses of softmax, mean and variance. In the experiments, we show the performance on the apparent database ChaLearn LAP (2015). Moreover, the proposed system is also tested on the real age databases, i.e. AFAD and MORPH II. Experimental results show that the system has a better performance in both the apparent and real age databases.
39
Bukar, Ali M., and Hassan Ugail. "On automatic age estimation from facial profile view." 2017. http://hdl.handle.net/10454/13041.
Full textAbstract:
YesIn recent years, automatic facial age estimation has gained popularity due to its numerous applications. Much work has been done on frontal images and lately, minimal estimation errors have been achieved on most of the benchmark databases. However, in reality, images obtained in unconstrained environments are not always frontal. For instance, when conducting a demographic study or crowd analysis, one may get profile images of the face. To the best of our knowledge, no attempt has been made to estimate ages from the side-view of face images. Here we exploit this by using a pre-trained deep residual neural network (ResNet) to extract features. We then utilize a sparse partial least squares regression approach to estimate ages. Despite having less information as compared to frontal images, our results show that the extracted deep features achieve a promising performance.
40
Liou, Yu-Min, and 劉育岷. "Human Face Age Estimation with Adaptive Hybrid Features." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/e94v68.
Full textAbstract:
碩士國立臺灣科技大學
電機工程系
99
The thesis proposed an approach of human face age estimation based on human appearance. In recent years, face age estimation has raised attentions, and thus relative research and application are derived from that. Yet, it is a challenging issue to classify the age with computer vision. The main problems can be blamed that everybody is suffered from diverse of factors during their aging process, such as health state, working environment, inheritance, pressure, disease, dramatic changes in body weight, exposure in severe climate. In addition, smoking behavior also accelerates the aging process. Most former researches on human face age estimation simply employ one feature for classification. However, the shapes and textures of faces vary across various stages of age. Consequently, the thesis proposed a method caters different features for the different ranges of age, in which the features of shape, texture characteristics and frequency distributions are considered using Active Shape Model (ASM), Radon conversion, and Discrete Cosine Transform (DCT), respectively. In the identification stage, the Support Vector Machine (SVM), Support Vector Regression (SVR), and the proposed hierarchical classification structure are used for estimatimation. The well-known FG-NET database is employed as the samples for training and testing in the experiment. The FG-NET is a public and popular database for the research of age estimation, which includes 1002 color and gray human face images. As documented in the experimental results, the proposed scheme provides superior performance than that of the former schemes. Moreover, this study implements a practical system using notebook, video capture card, PTZ camera and RS232 transmission cable to combine the face detection (Adaboost) and the age estimation two fields.
41
Hu, Kai-Hung, and 胡凱閎. "Gender-Oriented Age Estimation Using Masked Gabor Features." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/63eujz.
Full textAbstract:
碩士國立臺灣科技大學
機械工程系
100
It is recently proven that face-based age estimation can be improved if the gender of the face is known. Given the gender of a face, the estimation of the age of the face is called Gender-Oriented Age Estimation (GOAE). Few works are available as references on GOAE, and this thesis is dedicated to deepening our understanding in this regard by proposing an algorithm for GOAE. Unlike the few previous works that verify the performance on the YGA database, which is not publically accessible, this work selects the public databases, the FG-NET and MORPH, for performance evaluation. Given a training set, the proposed algorithm first extracts the low frequency parts of the masked Gabor features, and selects the age-related components by an AdaBoost scheme to train an SVM classifier. It is proven in our experiments that the proposed algorithm yields a performance competitive to the state-of-the-art approaches. Because of the ethnic differences between the FG-NET and MORPH, it is also experimentally proven that the age estimation is better undertaken within the same ethnic group. The age features from one ethnic group can substantially downgrade the performance when used to estimate the age of a different ethnic group. To efficiently collect a good scope of samples of the same ethnic group, a social network is exploited for the first time to meet the requirements.
42
Txia, Jun-Da, and 蔡俊達. "Age Estimation using AAM and Local Facial Features." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/44965555584453261598.
Full textAbstract:
碩士國立清華大學
電機工程學系
97
In the thesis, a new method of using AAM to extract regions of age features is proposed. The goal of this thesis is to extract exactly the regions of age features. Our system consists of four modules: (1) Detecting people by using Adaboost. (2) Searching facial features by using AAM. (3) Finding regions of age features by using facial features. (4) Age estimation by using SVM. The experimental results will demonstrate that the proposed region of age features can be applied to estimate the age of a facial image. We testing our system by using Intel C2D 6300 CPU and the frame size is 200*240 pixels. It requires 3~4 s to fitting a face and the recognition accuracy is about 72.52% in our system.
43
Zhu, Zhong-Xin, and 朱忠信. "Age Estimation Using Fractal Dimension-based Wrinkle Texture." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/48257987548060162053.
Full textAbstract:
碩士國立暨南國際大學
電機工程學系
101
Derived from rapid advances in computer graphics and machine vision, computer-based age estimation via facial wrinkle characteristics has become a prevalent topic as well as an interesting study. In this paper, we use the fractal dimension as the basis for estimating the age, and pre-processing of the image to improve the age estimation. This system contains one pre-processing module, one fractal process module and one determination module. The images are input to this system. The pre-processing module detects the face area via Haar-like method. The wrinkle area is positioned by locating organs on the the face and pre-treated. Then, fractal dimension calculation on the wrinkle area is proceeded by means of DBC, Shifting-DBC, and Scanning BC. Finally, based on the changes in the of fractal dimension, conversion functions are used for estimating the age of the human face. The experimental results demonstrate that the estimation accuracy reaches 72%. In this thesis, all experimental results are tested on FG-NET database. Each image in this database is recorded with ages and growth background of a person. The database does help to test our age estimation system.
44
Dooley, Ellen V. "Age estimation from features of the first rib." Thesis, 2020. https://hdl.handle.net/2144/41215.
Full textAbstract:
Several techniques for estimating adult age-at-death are used in biological and forensic anthropology, including morphological changes of the ribs. However, due to human variation and taphonomic damage, it remains difficult to produce accurate and meaningful age-at-death estimations based on skeletal remains. This research further explores morphological changes to the first rib, which is easily identifiable and relatively robust, including the costal face and tubercle facet identified by Kunos’ (1999) and modified by DiGangi et al. (2009). A total of 400 European American individuals (f=200; m=200) from the William M. Bass Donated Skeletal Collection at the University of Tennessee, Knoxville, were observed using modified descriptions for Kunos’ (1999) five traits of the costal face and tubercle facet, on an ordinal scale of 1-8. Additionally, bone quality was assessed on an ordinal scale of 1-3 and was incorporated as a variable in order to improve estimations. Exploratory statistical analysis demonstrates that all eleven traits correlate with age at a statistically significant level, with bone quality being the most significant feature for both sexes. Female and male differences were found, and cross-validated ordinal logistic regression equations are presented for each. The resulting AIC table estimates 100% of the male and female sample correctly, though the produced ranges are too large to be forensically relevant. The results of this research underscore the importance of developing age estimation methods on skeletal regions that are under researched and for those that are more resistant to taphonomic damage.
45
Chan, Pak-Ki, and 陳柏棋. "Facial Age Estimation by Deep Neural Networks Fusion." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/9k23pb.
Full textAbstract:
碩士國立中興大學
電機工程學系所
106
In this thesis, we proposed a stacked deep network fusion model for the apparent human facial age estimation. Three well-performed deep architectures are utilized in the first three stages and the estimation results for each architecture are fused in the last stage to boost the overall performance. In the first stage, a pre-trained deep CNN model is fine-tuned for the gender classification task. For the second stage, two gender-specific age groupers are built to classify the facial images into two non-overlapping age groups. In the third stage, ages are estimated from the three deep networks and fed to the fuser of the last stage to refine age estimation results. Experimental results demonstrate a significant performance improvement of the proposed approach over the state-of-the-art deep CNN models. Afterward, I presented a deep Depthwise Separable Convolutional Neural Network (DSCNN) fusion system for human facial age estimation. This system includes the following four stages. In the first stage, a data augmentation procedure is utilized to enrich the dataset. In the second stage, a pre-trained deep CNN model is fine-tuned for the gender classification task. For the third stage, three new well-performed DSCNN age estimators are designed to conduct gender-specific age estimation for gender grouped facial images from the previous stage. These three deep architectures also aim to lower computing complexity. In the last stage, estimated ages from three DSCNN age estimators are fed to the fuser to boost the overall age estimation performance. In the experimental results, on two benchmark datasets, IMDBWIKI, MORPH-II, Apparent age V1 and Apparent age V2 the proposed framework demonstrates a significant performance improvement. Finally, I challenge low-quality and very low-resolution facial images for age estimation. We propose a new architecture based on deep neural networks. In the architecture, we use the mature neural network technique by the Xception and DenseNet, which have shown great classification results on the ImageNet competition. Simultaneously, we redesign the neural network layers from Xception and DenseNet121. Moreover, we improve neural network accuracy. We utilize deep learning on the Super-Resolution to exaltation low-resolution images quality. At the same time, we use different images processing to exaltation low-resolution images quality, including Bicubic Interpolation and Sharpness Enhanced. Afterward, we use traditional data augmentation (including vertical flip and horizontal flip) to generate triple data amount, resulting in enough data. At the same time, we also resize images to very low-resolution as 32×32 pixels and 64×64 pixels in the experiment. In experimental results, we show very impressive performances.
46
Fan, Bo-Chun, and 范博鈞. "Computerized Bone Age Estimation Using the Carpal-Bone Images." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/86588519825563627774.
Full textAbstract:
碩士國立清華大學
電機工程學系
87
Bone age (BA) estimation is one of the important applications in the area of pediatrics, especially in the diagnosis of endocrinological problems and growth disorders. Because manual BA estimation (BAE) is tedious and time consuming and heavily dependent upon doctor's experiences, we attempt to construct a computerized BAE system to help reduce the doctor's burden. It is known that sex, race, and nutrition will affect the results of BAE. So far to now, most of BAE standards are American standards. There is no BAE standard for Taiwanese people. With the aid of the proposed computerized BAE system, a standard for Taiwanese people can be easily built which will greatly help doctors to estimate BA in Taiwan. Our BAE system is based on the carpal-bone information. In 1993, Ewa Pietka, Lotfi Kaabi, M.L. Kuo and H.K. Huang had developed a feature extraction method for carpal-bone[3]. They use two-step local thresholding method to extract the area of a carpal bone. However, the method did not work well in our database. Carpal bones can not be extracted simply by the local thresholding method. Therefore, we develop a new method for carpal-bone feature extraction, which we call the two-stage edge detection algorithm, and a new method for carpal-bone ROI division. After the image is manually equalized, our BAE system can extract the features of the carpal-bone and estimate the bone age automatically. Three different classifiers: the minimum distance classifier, Bayes classifier, and a neural network classifier are tested in our experiments. The results of our feature extraction are quite satisfactory. More than 90% of the classification are acceptable in our experiments.
47
Lin, Chia-Wei, and 林嘉薇. "Estimation Mortgage Termination Rates with Separate Loan Age Functions." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/70373266621856193374.
Full textAbstract:
碩士國立清華大學
科技管理研究所
93
In Asian Countries or some countries with high saving rates, partial prepayment, curtailment, is a common payment behavior. When borrowers have extra money more than the basic living needs, they usually use that additional amount to repay the principle early in order to curtail the loan balance and also reduce the interest payment. Based on mortgage loan-level data obtained from a commercial bank in Taiwan, we find the curtailment effect is material. Therefore, we incorporate the curtailment factor into the explanatory variables in analysis. More specifically, the aging patterns of prepayment rate and default rate are different. The prepayment rate exhibits a “S” shape; whereas the default rates initially increase progressively and then decrease thereafter similar to a Gamma distribution. By using the separate logit model with age functions accordingly, we can capture the borrowers’ payment behavior, and accurately estimate the prepayment and default rates.
48
Castro, Pedro Vieira de. "Age Estimation using Deep Learning on 3D Facial Features." Master's thesis, 2018. https://repositorio-aberto.up.pt/handle/10216/115799.
Full textAbstract:
Intelligent Systems are designed to substitute the human component therefore they have a need to emulate a human's ability to quickly estimate biological traits of others, which is an integral part of social interactions. Age is one of the key characteristics used by marketing, entertainment and security tools. Existing age estimation systems can be easily fooled due to their reliance on human appearance based features, which can be easily manipulated. Over the years, while the complexity of models increased, the data fed to our systems was kept the same: a single 2D RGB image. This thesis addresses the current lack of studies made on the uses of 3D facial information ion the context of age estimation. This thesis encompasses a comprehensive study of how different 3D facial features can be used to improve current state of the art age estimation approaches using Deep Learning. Along with extensions to a baseline Convolutional Neural Network (CNN) model with a 2D image input, it is introduced a novel Multi-View CNN model which combines face descriptors from multiple perspectives within the model's architecture. Due to lack of 3D facial datasets aimed at age estimation, 2D age estimation datasets were synthetically augmented with landmark localization, 3DMM parametrization and 3D facial point cloud reconstruction. The last one was subsequently used to create a new synthetic dataset composed of renderings of each point cloud from different camera positions. A fully customizable data processing tool was introduced which supports image pre-processing, dataset splitting, image augmentation and synthetic feature extraction. Quantitative results show improvement of the 3D methods over traditional 2D although somewhat constrained by data quality.
49
Chen, Jiun-Hung, and 陳俊宏. "Age estimation via facial images by ordinal probit model." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/06475940738987286703.
Full textAbstract:
碩士國立中興大學
統計學研究所
101
Recently many researches of age estimation by using facial images are widely developed , Age estimation is an interesting and challenging problem in the area of computer vision. This paper proposes an age estimation method named Ordinal Probit Model, which estimates human ages via facial images, we employ the relative order of age labels because it provides more stable information than exact age values and performed age estimation experiments of FG-NET databases.
50
Cheng, Yi-Tseng, and 鄭亦曾. "Landmark Oriented Generalized Biologically Inspired Features for Age Estimation." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/75001536503865780052.
Full textAbstract:
碩士國立臺灣科技大學
機械工程系
104
We propose the Generalized Biologically Inspired Features (GBIFs) and a moving segmentation scheme followed by soft boundary regression for age estimation. The GBIF is more advantageous than the Bio-Inspired Feature (BIF) for capturing age-related facial traits. The moving segmentation is proposed to better determine the age groups, leading to an improvement on the age estimation accuracy. Different from most approaches that segment the age groups in an ad-hoc way, the moving segmentation allows one to define age groups using the local minima in the misclassification rate across ages. The extraction of the GBIF depends on the partition of component regions defined by facial landmarks. In addition to the partition of component regions, we also study the appropriate age grouping and hierarchical classification, and determine the best configuration for age estimation. The proposed approach with the most appropriate settings outperforms most of the state of the art on two benchmarks, FG-NET and MORPH.