Dissertations / Theses on the topic 'Image'
To see the other types of publications on this topic, follow the link: Image.
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 'Image.'
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
Suri, Sahil. "Automatic image to image registration for multimodal remote sensing images." kostenfrei, 2010. https://mediatum2.ub.tum.de/node?id=967187.
2
Mennborg, Alexander. "AI-Driven Image Manipulation : Image Outpainting Applied on Fashion Images." Thesis, Luleå tekniska universitet, Institutionen för system- och rymdteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-85148.
Abstract:
The e-commerce industry frequently has to deal with displaying product images in a website where the images are provided by the selling partners. The images in question can have drastically different aspect ratios and resolutions which makes it harder to present them while maintaining a coherent user experience. Manipulating images by cropping can sometimes result in parts of the foreground (i.e. product or person within the image) to be cut off. Image outpainting is a technique that allows images to be extended past its boundaries and can be used to alter the aspect ratio of images. Together with object detection for locating the foreground makes it possible to manipulate images without sacrificing parts of the foreground. For image outpainting a deep learning model was trained on product images that can extend images by at least 25%. The model achieves 8.29 FID score, 44.29 PSNR score and 39.95 BRISQUE score. For testing this solution in practice a simple image manipulation pipeline was created which uses image outpainting when needed and it shows promising results. Images can be manipulated in under a second running on ZOTAC GeForce RTX 3060 (12GB) GPU and a few seconds running on a Intel Core i7-8700K (16GB) CPU. There is also a special case of images where the background has been digitally replaced with a solid color and they can be outpainted even faster without deep learning.
3
Dalkvist, Mikael. "Image Completion Using Local Images." Thesis, Linköpings universitet, Informationskodning, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-70940.
Abstract:
Image completion is a process of removing an area from a photograph and replacing it with suitable data. Earlier methods either search for this relevant data within the image itself, or extends the search to some form of additional data, usually some form of database. Methods that search for suitable data within the image itself has problems when no suitable data can be found in the image. Methods that extend their search has in earlier work either used some form of database with labeled images or a massive database with photos from the Internet. For the labels in a database to be useful they typically needs to be entered manually, which is a very time consuming process. Methods that uses databases with millions of images from the Internet has issues with copyrighted images, storage of the photographs and computation time. This work shows that a small database of the user’s own private, or professional, photos can be used to improve the quality of image completions. A photographer today typically take many similar photographs on similar scenes during a photo session. Therefore a smaller number of images are needed to find images that are visually and structurally similar, than when random images downloaded from the internet are used. Thus, this approach gains most of the advantages of using additional data for the image completions, while at the same time minimizing the disadvantages. It gains a better ability to find suitable data without having to process millions of irrelevant photos.
4
Schilling, Lennart. "Generating synthetic brain MR images using a hybrid combination of Noise-to-Image and Image-to-Image GANs." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166034.
Abstract:
Generative Adversarial Networks (GANs) have attracted much attention because of their ability to learn high-dimensional, realistic data distributions. In the field of medical imaging, they can be used to augment the often small image sets available. In this way, for example, the training of image classification or segmentation models can be improved to support clinical decision making. GANs can be distinguished according to their input. While Noise-to-Image GANs synthesize new images from a random noise vector, Image-To-Image GANs translate a given image into another domain. In this study, it is investigated if the performance of a Noise-To-Image GAN, defined by its generated output quality and diversity, can be improved by using elements of a previously trained Image-To-Image GAN within its training. The data used consists of paired T1- and T2-weighted MR brain images. With the objective of generating additional T1-weighted images, a hybrid model (Hybrid GAN) is implemented that combines elements of a Deep Convolutional GAN (DCGAN) as a Noise-To-Image GAN and a Pix2Pix as an Image-To-Image GAN. Thereby, starting from the dependency of an input image, the model is gradually converted into a Noise-to-Image GAN. Performance is evaluated by the use of an independent classifier that estimates the divergence between the generative output distribution and the real data distribution. When comparing the Hybrid GAN performance with the DCGAN baseline, no improvement, neither in the quality nor in the diversity of the generated images, could be observed. Consequently, it could not be shown that the performance of a Noise-To-Image GAN is improved by using elements of a previously trained Image-To-Image GAN within its training.
5
Murphy, Brian P. "Image processing techniques for acoustic images." Thesis, Monterey, California. Naval Postgraduate School, 1991. http://hdl.handle.net/10945/26585.
Abstract:
Approved for public release; distribution is unlimitedThe primary goal of this research is to test the effectiveness of various image processing techniques applied to acoustic images generated in MATLAB. The simulated acoustic images have the same characteristics as those generated by a computer model of a high resolution imaging sonar. Edge Detection and Segmentation are the two image processing techniques discussed in this study. The two methods tested are a modified version of the Kalman filtering and median filtering
6
Zeng, Ziming. "Medical image segmentation on multimodality images." Thesis, Aberystwyth University, 2013. http://hdl.handle.net/2160/17cd13c2-067c-451b-8217-70947f89164e.
Abstract:
Segmentation is a hot issue in the domain of medical image analysis. It has a wide range of applications on medical research. A great many medical image segmentation algorithms have been proposed, and many good segmentation results were obtained. However, due to the noise, density inhomogenity, partial volume effects, and density overlap between normal and abnormal tissues in medical images, the segmentation accuracy and robustness of some state-of-the-art methods still have room for improvement. This thesis aims to deal with the above segmentation problems and improve the segmentation accuracy. This project investigated medical image segmentation methods across a range of modalities and clinical applications, covering magnetic resonance imaging (MRI) in brain tissue segmentation, MRI based multiple sclerosis (MS) lesions segmentation, histology based cell nuclei segmentation, and positron emission tomography (PET) based tumour detection. For the brain MRI tissue segmentation, a method based on mutual information was developed to estimate the number of brain tissue groups. Then a unsupervised segmentation method was proposed to segment the brain tissues. For the MS lesions segmentation, 2D/3D joint histogram modelling were proposed to model the grey level distribution of MS lesions in multimodality MRI. For the PET segmentation of the head and neck tumours, two hierarchical methods based on improved active contour/surface modelling were proposed to segment the tumours in PET volumes. For the histology based cell nuclei segmentation, a novel unsupervised segmentation based on adaptive active contour modelling driven by morphology initialization was proposed to segment the cell nuclei. Then the segmentation results were further processed for subtypes classification. Among these segmentation approaches, a number of techniques (such as modified bias field fuzzy c-means clustering, multiimage spatially joint histogram representation, and convex optimisation of deformable model, etc.) were developed to deal with the key problems in medical image segmentation. Experiments show that the novel methods in this thesis have great potential for various image segmentation scenarios and can obtain more accurate and robust segmentation results than some state-of-the-art methods.
7
Khan, Preoyati. "Cluster Based Image Processing for ImageJ." Kent State University / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=kent1492164847520322.
8
Tummala, Sai Virali, and Veerendra Marni. "Comparison of Image Compression and Enhancement Techniques for Image Quality in Medical Images." Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-15360.
9
Asplund, Raquel. "Evaluation of a cloud-based image analysis and image display system for medical images." Thesis, Umeå universitet, Institutionen för tillämpad fysik och elektronik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-105984.
10
Karlsson, Simon, and Per Welander. "Generative Adversarial Networks for Image-to-Image Translation on Street View and MR Images." Thesis, Linköpings universitet, Institutionen för medicinsk teknik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-148475.
Abstract:
Generative Adversarial Networks (GANs) is a deep learning method that has been developed for synthesizing data. One application for which it can be used for is image-to-image translations. This could prove to be valuable when training deep neural networks for image classification tasks. Two areas where deep learning methods are used are automotive vision systems and medical imaging. Automotive vision systems are expected to handle a broad range of scenarios which demand training data with a high diversity. The scenarios in the medical field are fewer but the problem is instead that it is difficult, time consuming and expensive to collect training data. This thesis evaluates different GAN models by comparing synthetic MR images produced by the models against ground truth images. A perceptual study is also performed by an expert in the field. It is shown by the study that the implemented GAN models can synthesize visually realistic MR images. It is also shown that models producing more visually realistic synthetic images not necessarily have better results in quantitative error measurements, when compared to ground truth data. Along with the investigations on medical images, the thesis explores the possibilities of generating synthetic street view images of different resolution, light and weather conditions. Different GAN models have been compared, implemented with our own adjustments, and evaluated. The results show that it is possible to create visually realistic images for different translations and image resolutions.
11
Tu, Guoyun. "Image Captioning On General Data And Fashion Data : An Attribute-Image-Combined Attention-Based Network for Image Captioning on Mutli-Object Images and Single-Object Images." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-282925.
Abstract:
Image captioning is a crucial field across computer vision and natural language processing. It could be widely applied to high-volume web images, such as conveying image content to visually impaired users. Many methods are adopted in this area such as attention-based methods, semantic-concept based models. These achieve excellent performance on general image datasets such as the MS COCO dataset. However, it is still left unexplored on single-object images.In this paper, we propose a new attribute-information-combined attention- based network (AIC-AB Net). At each time step, attribute information is added as a supplementary of visual information. For sequential word generation, spatial attention determines specific regions of images to pass the decoder. The sentinel gate decides whether to attend to the image or to the visual sentinel (what the decoder already knows, including the attribute information). Text attribute information is synchronously fed in to help image recognition and reduce uncertainty.We build a new fashion dataset consisting of fashion images to establish a benchmark for single-object images. This fashion dataset consists of 144,422 images from 24,649 fashion products, with one description sentence for each image. Our method is tested on the MS COCO dataset and the proposed Fashion dataset. The results show the superior performance of the proposed model on both multi-object images and single-object images. Our AIC-AB net outperforms the state-of-the-art network, Adaptive Attention Network by 0.017, 0.095, and 0.095 (CIDEr Score) on the COCO dataset, Fashion dataset (Bestsellers), and Fashion dataset (all vendors), respectively. The results also reveal the complement of attention architecture and attribute information.Bildtextning är ett avgörande fält för datorsyn och behandling av naturligt språk. Det kan tillämpas i stor utsträckning på högvolyms webbbilder, som att överföra bildinnehåll till synskadade användare. Många metoder antas inom detta område såsom uppmärksamhetsbaserade metoder, semantiska konceptbaserade modeller. Dessa uppnår utmärkt prestanda på allmänna bilddatamängder som MS COCO-dataset. Det lämnas dock fortfarande outforskat på bilder med ett objekt.I denna uppsats föreslår vi ett nytt attribut-information-kombinerat uppmärksamhetsbaserat nätverk (AIC-AB Net). I varje tidsteg läggs attributinformation till som ett komplement till visuell information. För sekventiell ordgenerering bestämmer rumslig uppmärksamhet specifika regioner av bilder som ska passera avkodaren. Sentinelgrinden bestämmer om den ska ta hand om bilden eller den visuella vaktposten (vad avkodaren redan vet, inklusive attributinformation). Text attributinformation matas synkront för att hjälpa bildigenkänning och minska osäkerheten.Vi bygger en ny modedataset bestående av modebilder för att skapa ett riktmärke för bilder med en objekt. Denna modedataset består av 144 422 bilder från 24 649 modeprodukter, med en beskrivningsmening för varje bild. Vår metod testas på MS COCO dataset och den föreslagna Fashion dataset. Resultaten visar den överlägsna prestandan hos den föreslagna modellen på både bilder med flera objekt och enbildsbilder. Vårt AIC-AB-nät överträffar det senaste nätverket Adaptive Attention Network med 0,017, 0,095 och 0,095 (CIDEr Score) i COCO-datasetet, modedataset (bästsäljare) respektive modedatasetet (alla leverantörer). Resultaten avslöjar också komplementet till uppmärksamhetsarkitektur och attributinformation.
12
Karelid, Mikael. "Image Enhancement over a Sequence of Images." Thesis, Linköping University, Department of Electrical Engineering, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-12523.
Abstract:
This Master Thesis has been conducted at the National Laboratory of Forensic Science (SKL) in Linköping. When images that are to be analyzed at SKL, presenting an interesting object, are of bad quality there may be a need to enhance them. If several images with the object are available, the total amount of information can be used in order to estimate one single enhanced image. A program to do this has been developed by studying methods for image registration and high resolution image estimation. Tests of important parts of the procedure have been conducted. The final results are satisfying and the key to a good high resolution image seems to be the precision of the image registration. Improvements of this part may lead to even better results. More suggestions for further improvementshave been proposed.
Detta examensarbete har utförts på uppdrag av Statens Kriminaltekniska Laboratorium (SKL) i Linköping. Då bilder av ett intressant objekt som ska analyseras på SKL ibland är av dålig kvalitet finns det behov av att förbättra dessa. Om ett flertal bilder på objektet finns tillgängliga kan den totala informationen fråndessa användas för att skatta en enda förbättrad bild. Ett program för att göra detta har utvecklats genom studier av metoder för bildregistrering och skapande av högupplöst bild. Tester av viktiga delar i proceduren har genomförts. De slutgiltiga resultaten är goda och nyckeln till en bra högupplöst bild verkar ligga i precisionen för bildregistreringen. Genom att förbättra denna del kan troligtvis ännu bättre resultat fås. Även andra förslag till förbättringar har lagts fram.
13
Moëll, Mattias. "Digital image analysis for wood fiber images /." Uppsala : Swedish Univ. of Agricultural Sciences (Sveriges lantbruksuniv.), 2001. http://epsilon.slu.se/avh/2001/91-576-6309-2.pdf.
14
Anco, Layme Marleny, Córdova Bárbara Llerena, and Reynaga Kenia Milagros Mendoza. "Asesoría de imagen online Style & Image." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2018. http://hdl.handle.net/10757/625372.
Abstract:
Style & Image es una empresa de servicios dedicada a la asesoría de imagen, dirigido a hombres y mujeres que tienen la dificultad para elegir sus prendas de vestir para distintas ocasiones. A través de nuestra plataforma virtual se podrá acceder a los diferentes servicios de asesoría virtual y presencial. Asimismo, el cliente tendrá la alternativa de alquilar carteras, vestidos y trajes de estreno en la página web. Nuestros servicios están a cargo de las asesoras de imagen que brindarán una atención personalizada.
Nuestra propuesta de valor es brindar un servicio virtual personalizado para que el cliente aprenda a seleccionar las prendas a usar de acuerdo a su estilo e imagen.
La propuesta de negocio de Style & Imagen es viable ya que el comercio de la moda se encuentra en crecimiento en el mercado peruano y somos los únicos en ofrecer el servicio de asesoría de imagen virtual.
De acuerdo a la investigación realizada en el mercado peruano, se determinó que nuestro público objetivo son los hombres y mujeres de 22 a 35 años, que trabajan y pertenecen a los niveles socio económico B y C de Lima y Callao, con interés en servicios que van de la mano con la tecnología y la calidad a un buen precio.
Por último, se realizó la evaluación financiera donde se determinó una inversión inicial de S/. 40,880 soles, recuperándose en el primer año de operaciones.Style & Image is a service company dedicated to image consulting, for men and women who have difficulty choosing their clothing for different occasions. Through our virtual platform you can access the different virtual and face-to-face counseling services. Likewise, the client will have the alternative of renting portfolios, dresses and premiere suits on the website. Our services are in charge of image consultants who will provide personalized attention. Our value proposition is to provide a personalized virtual service so that the client learns to select the clothes to be used according to their style and image. The business proposal of Style & Imagen is viable since the fashion trade is growing in the peruvian market and we are the only ones to offer the virtual image consulting service. According to the research carried out in the peruvian market, it was determined that our target audience is men and women from 22 to 35 years old, who work and belong to socioeconomic levels B and C of Lima and Callao, with an interest in services that they go hand in hand with technology and quality at a good price. Finally, the financial evaluation was carried out where an initial investment of S /. 40,880 soles, recovering in the first year of operations.
Trabajo de investigación
15
Ahmad, Fauzi Mohammad Faizal. "Content-based image retrieval of museum images." Thesis, University of Southampton, 2004. https://eprints.soton.ac.uk/261546/.
Abstract:
Content-based image retrieval (CBIR) is becoming more and more important with the advance of multimedia and imaging technology. Among many retrieval features associated with CBIR, texture retrieval is one of the most difficult. This is mainly because no satisfactory quantitative definition of texture exists at this time, and also because of the complex nature of the texture itself. Another difficult problem in CBIR is query by low-quality images, which means attempts to retrieve images using a poor quality image as a query. Not many content-based retrieval systems have addressed the problem of query by low-quality images. Wavelet analysis is a relatively new and promising tool for signal and image analysis. Its time-scale representation provides both spatial and frequency information, thus giving extra information compared to other image representation schemes. This research aims to address some of the problems of query by texture and query by low quality images by exploiting all the advantages that wavelet analysis has to offer, particularly in the context of museum image collections. A novel query by low-quality images algorithm is presented as a solution to the problem of poor retrieval performance using conventional methods. In the query by texture problem, this thesis provides a comprehensive evaluation on wavelet-based texture method as well as comparison with other techniques. A novel automatic texture segmentation algorithm and an improved block oriented decomposition is proposed for use in query by texture. Finally all the proposed techniques are integrated in a content-based image retrieval application for museum image collections.
16
MAURY, ARNAUD. "Qualite image et rectification des images meteosat." Nice, 1993. http://www.theses.fr/1993NICE4654.
Abstract:
Cette these traite de la rectification des images du satellite meteosat ; soit la methode d'allouer a chaque pixel de l'image sa localisation geographique. Meteosat est un satellite meteorologique geostationnaire manoeuvre par l'agence spatiale europeenne. Dans sa configuration nominale, le satellite meteosat permet la saisie d'images pour lesquelles les lignes sont orientees parfaitement en est-ouest et avec la terre parfaitement centree. De petites deviations de cette situation nominale induisent l'apparition de distorsions geometriques. L'ensemble des causes de ces distorsions sont decrites et definies. Afin de rectifier les images un modele de deformation est elabore, ses parametres etant estimes. Les images une fois rectifiees, l'erreur de rectification residuelle est quantifiee a partir de la localisation d'amers par un procede de correlation. L'ensemble des resultats et methodes ont ete valides a partir de donnees operationnelles au moyen de simulations informatiques; ce pour l'ensemble du processus de traitement image: des images brutes aux images rectifiees et re-echantillonnees
17
Allen, Elizabeth. "Image quality evaluation in lossy compressed images." Thesis, University of Westminster, 2017. https://westminsterresearch.westminster.ac.uk/item/q0vq5/image-quality-evaluation-in-lossy-compressed-images.
Abstract:
This research focuses on the quantification of image quality in lossy compressed images, exploring the impact of digital artefacts and scene characteristics upon image quality evaluation. A subjective paired comparison test was implemented to assess perceived quality of JPEG 2000 against baseline JPEG over a range of different scene types. Interval scales were generated for both algorithms, which indicated a subjective preference for JPEG 2000, particularly at low bit rates, and these were confirmed by an objective distortion measure. The subjective results did not follow this trend for some scenes however, and both algorithms were found to be scene dependent as a result of the artefacts produced at high compression rates. The scene dependencies were explored from the interval scale results, which allowed scenes to be grouped according to their susceptibilities to each of the algorithms. Groupings were correlated with scene measures applied in a linked study. A pilot study was undertaken to explore perceptibility thresholds of JPEG 2000 of the same set of images. This work was developed with a further experiment to investigate the thresholds of perceptibility and acceptability of higher resolution JPEG 2000 compressed images. A set of images was captured using a professional level full-frame Digital Single Lens Reflex camera, using a raw workflow and carefully controlled image-processing pipeline. The scenes were quantified using a set of simple scene metrics to classify them according to whether they were average, higher than, or lower than average, for a number of scene properties known to affect image compression and perceived image quality; these were used to make a final selection of test images. Image fidelity was investigated using the method of constant stimuli to quantify perceptibility thresholds and just noticeable differences (JNDs) of perceptibility. Thresholds and JNDs of acceptability were also quantified to explore suprathreshold quality evaluation. The relationships between the two thresholds were examined and correlated with the results from the scene measures, to identify more or less susceptible scenes. It was found that the level and differences between the two thresholds was an indicator of scene dependency and could be predicted by certain types of scene characteristics. A third study implemented the soft copy quality ruler as an alternative psychophysical method, by matching the quality of compressed images to a set of images varying in a single attribute, separated by known JND increments of quality. The imaging chain and image processing workflow were evaluated using objective measures of tone reproduction and spatial frequency response. An alternative approach to the creation of ruler images was implemented and tested, and the resulting quality rulers were used to evaluate a subset of the images from the previous study. The quality ruler was found to be successful in identifying scene susceptibilities and observer sensitivity. The fourth investigation explored the implementation of four different image quality metrics. These were the Modular Image Difference Metric, the Structural Similarity Metric, The Multi-scale Structural Similarity Metric and the Weighted Structural Similarity Metric. The metrics were tested against the subjective results and all were found to have linear correlation in terms of predictability of image quality.
18
Feng, Sitao. "Image Analysis on Wood Fiber Cross-Section Images." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-156428.
Abstract:
Lignification of wood fibers has a significant impact on wood properties. To measure the distribution of lignin in compression wood fiber cross-section images, a crisp segmentation method had been developed. It segments the lumen, the normally lignified cell wall and the highly lignified cell wall of each fiber. In order to refine this given segmentation the following two fuzzy segmentation methods were evaluated in this thesis: Iterative Relative Multi Objects Fuzzy Connectedness and Weighted Distance Transform on Curved Space. The crisp segmentation is used for the multi-seed selection. The crisp and the two fuzzy segmentations are then evaluated by comparing with the manual segmentation. It shows that Iterative Relative Multi Objects Fuzzy Connectedness has the best performance on segmenting the lumen, whereas Weighted Distance Transform on Curved Space outperforms the two other methods regarding the normally lignified cell wall and the highly lignified cell wall.
19
Yallop, Marc Richard. "Image processing techniques for passive millimetre wave images." Thesis, University of Reading, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.409545.
20
Boukouvala, Erisso. "Image restoration techniques and application on astronomical images." Thesis, University of Reading, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.414571.
21
Gieffers, Amy Christina 1975. "Image alignment algorithms for ultrasound images with contrast." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/46193.
Abstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998.Includes bibliographical references (leaves 70-74).
by Amy Christina Gieffers.
M.Eng.
22
Nasir, Haidawati Mohamad. "Super-resolution image reconstruction from low-resolution images." Thesis, University of Strathclyde, 2012. http://oleg.lib.strath.ac.uk:80/R/?func=dbin-jump-full&object_id=17814.
Abstract:
The thesis addresses the problem of obtaining high-resolution image from a set of one or more low-resolution images. The thesis focused on three building blocks of super-resolution algorithms i.e., image registration for super-resolution, image fusion for super-resolution and super-resolution image reconstruction. These three parts are addressed separately and singular value decomposition-based fusion is introduced before performing interpolation or single-image super-resolution. An accurate image registration is crucial for super-resolution. An image registration approach for super-resolution based on a combination of Scale Invariant Feature Transform (SIFT), Belief Propagation (BP) and Random Sampling Consensus (RANSAC) is described to automatically register the low-resolution images. The results have shown effective for the removal of the mismatched features in the image. A novel SVD-based image fusion for super-resolution is developed for integrating the significant features from low-resolution images. The SVD-based image fusion is shown to enhance the super-resolution results. The implementation of a novel interpolation method based on a linear combination of the bicubic interpolation and their first-order derivates and the use of first-order difference equation to extract the features from the low-resolution images are described and shown to improve the method of single image super-resolution using sparse representation. The proposed method has shown to reduces the computational time and enhance the prior estimation of the high-resolution image as well as the final super-resolution results. The performance of the algorithms is evaluated using synthetic sequences and also on real sequences subjectively and objectively.
23
Richardson, Richard Thomas. "Image Enhancement of Cancerous Tissue in Mammography Images." NSUWorks, 2015. http://nsuworks.nova.edu/gscis_etd/39.
Abstract:
This research presents a framework for enhancing and analyzing time-sequenced mammographic images for detection of cancerous tissue, specifically designed to assist radiologists and physicians with the detection of breast cancer. By using computer aided diagnosis (CAD) systems as a tool to help in the detection of breast cancer in computed tomography (CT) mammography images, previous CT mammography images will enhance the interpretation of the next series of images. The first stage of this dissertation applies image subtraction to images from the same patient over time. Image types are defined as temporal subtraction, dual-energy subtraction, and Digital Database for Screening Mammography (DDSM). Image enhancement begins by applying image registration and subtraction using Matlab 2012a registration for temporal images and dual-energy subtraction for dual-energy images. DDSM images require no registration or subtraction as they are used for baseline analysis. The image data are from three different sources and all images had been annotated by radiologists for each image type using an image mask to identify malignant and benign.
The second stage involved the examination of four different thresholding techniques. The amplitude thresholding method manipulates objects and backgrounds in such a way that object and background pixels have grey levels grouped into two dominant and different modes. In these cases, it was possible to extract the objects from the background using a threshold that separates the modes. The local thresholding introduced posed no restrictions on region shape or size, because it maximized edge features by thresholding local regions separately. The overall histogram analysis showed minima and maxima of the image and provided four feature types--mean, variance, skewness, and kurtosis. K-means clustering provided sequential splitting, initially performing dynamic splits. These dynamic splits were then further split into smaller, more variant regions until the regions of interest were isolated. Regional-growing methods used recursive splitting to partition the image top-down by using the average brightness of a region. Each thresholding method was applied to each of the three image types.
In the final stage, the training set and test set were derived by applying the four thresholding methods on each of the three image types. This was accomplished by running Matlab 2012a grey-level, co-occurrence matrix (GLCM) and utilizing 21 target feature types, which were obtained from the Matlab function texture features. An additional four feature types were obtained from the state of the histogram-based features types. These 25 feature types were applied to each of the two classifications malignant and benign. WEKA 3.6.10 was used along with classifier J48 and cross-validation 10 fold to find the precision, recall, and f-measure values. Best results were obtained from these two combinations: temporal subtraction with amplitude thresholding, and temporal subtraction with regional-growing thresholding. To summarize, the researcher's contribution was to assess the effectiveness of various thresholding methods in the context of a three-stage approach, to help radiologists find cancerous tissue lesions in CT and MRI mammography images.
24
Hillman, Peter. "Segmentation of motion picture images and image sequences." Thesis, University of Edinburgh, 2002. http://hdl.handle.net/1842/15026.
Abstract:
For Motion Picture Special Effects, it is often necessary to take a source image of an actor, segment the actor from the unwanted background, and then composite over a new background. The resultant image appears as if the actor was filmed in front of the new background. The standard approach requires the unwanted background to be a blue or green screen. While this technique is capable of handling areas where the foreground (the actor) blends into the background, the physical requirements present many practical problems. This thesis investigates the possibility of segmenting images where the unwanted background is more varied. Standard segmentation techniques tend not to be effective, since motion picture images have extremely high resolution and high accuracy is required to make the result appear convincing. A set of novel algorithms which require minimal human interaction to initialise the processing is presented. These algorithms classify each pixel by comparing its colour to that of known background and foreground areas. They are shown to be effective where there is a sufficient distinction between the colours of the foreground and background. A technique for assessing the quality of an image segmentation in order to compare these algorithms to alternative solutions is presented. Results are included which suggest that in most cases the novel algorithms have the best performance, and that they produce results more quickly than the alternative approaches. Techniques for segmentation of moving images sequences are then presented. Results are included which show that only a few frames of the sequence need to be initialised by hand, as it is often possible to generate automatically the input required to initialise processing for the remaining frames. A novel algorithm which can produce acceptable results on image sequences where more conventional approaches fail or are too slow to be of use is presented.
25
Baabd, A., M. Y. Tymkovich, and О. Г. Аврунін. "Image Processing of Panoramic Dental X-Ray Images." Thesis, ХГУ, 2018. http://openarchive.nure.ua/handle/document/6204.
Abstract:
The panoramic image allows to clearly see the state of the teeth, the
dental rudiments, which are located in the jaw, temporomandibular joints,
as well as the maxillary sinuses. It is noted that this type of study
has a small dose of radiation. Indications for this type of study are dental
implantation, bite correction, suspicion of bone tissue inflammation, control
of the growth and development of the teeth, as well as the diagnosis of
other dental problems.
26
AbouRayan, Mohamed. "Real-time Image Fusion Processing for Astronomical Images." University of Toledo / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1461449811.
27
Nahar, Vikas. "Content based image retrieval for bio-medical images." Diss., Rolla, Mo. : Missouri University of Science and Technology, 2010. http://scholarsmine.mst.edu/thesis/pdf/Nahar_09007dcc80721e0b.pdf.
Abstract:
Thesis (M.S.)--Missouri University of Science and Technology, 2010.Vita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed Dec. 23, 2009). Includes bibliographical references (p. 82-83).
28
Thornström, Johan. "Domain Adaptation of Unreal Images for Image Classification." Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-165758.
Abstract:
Deep learning has been intensively researched in computer vision tasks like im-age classification. Collecting and labeling images that these neural networks aretrained on is labor-intensive, which is why alternative methods of collecting im-ages are of interest. Virtual environments allow rendering images and automaticlabeling, which could speed up the process of generating training data and re-duce costs.This thesis studies the problem of transfer learning in image classificationwhen the classifier has been trained on rendered images using a game engine andtested on real images. The goal is to render images using a game engine to createa classifier that can separate images depicting people wearing civilian clothingor camouflage. The thesis also studies how domain adaptation techniques usinggenerative adversarial networks could be used to improve the performance ofthe classifier. Experiments show that it is possible to generate images that canbe used for training a classifier capable of separating the two classes. However,the experiments with domain adaptation were unsuccessful. It is instead recom-mended to improve the quality of the rendered images in terms of features usedin the target domain to achieve better results.
29
Jorna, Gerard C. "Modulation transfer function measurements, image quality metrics, and subjective image quality for soft-copy color images." Diss., This resource online, 1993. http://scholar.lib.vt.edu/theses/available/etd-10022007-145249/.
30
Kim, Younhee. "Towards lower bounds on distortion in information hiding." Fairfax, VA : George Mason University, 2008. http://hdl.handle.net/1920/3403.
Abstract:
Thesis (Ph.D.)--George Mason University, 2008.Vita: p. 133. Thesis directors: Zoran Duric, Dana Richards. Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science. Title from PDF t.p. (viewed Mar. 17, 2009). Includes bibliographical references (p. 127-132). Also issued in print.
31
Mortimer, Victoria G. "Image description and image comparison." Thesis, University of Oxford, 2003. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.400340.
32
Ackerman, Wesley. "Semantic-Driven Unsupervised Image-to-Image Translation for Distinct Image Domains." BYU ScholarsArchive, 2020. https://scholarsarchive.byu.edu/etd/8684.
Abstract:
We expand the scope of image-to-image translation to include more distinct image domains, where the image sets have analogous structures, but may not share object types between them. Semantic-Driven Unsupervised Image-to-Image Translation for Distinct Image Domains (SUNIT) is built to more successfully translate images in this setting, where content from one domain is not found in the other. Our method trains an image translation model by learning encodings for semantic segmentations of images. These segmentations are translated between image domains to learn meaningful mappings between the structures in the two domains. The translated segmentations are then used as the basis for image generation. Beginning image generation with encoded segmentation information helps maintain the original structure of the image. We qualitatively and quantitatively show that SUNIT improves image translation outcomes, especially for image translation tasks where the image domains are very distinct.
33
Zhang, Jiachao. "Image denoising for real image sensors." University of Dayton / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1437954286.
34
Srinivas, Umamahesh Bose N. K. "Thermal image superresolution and higher order whitening of images." [University Park, Pa.] : Pennsylvania State University, 2009. http://etda.libraries.psu.edu/theses/approved/WorldWideIndex/ETD-3979/index.html.
35
Lee, Jungwon. "Efficient image compression system using a CMOS transform imager." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/31825.
Abstract:
Thesis (Ph.D)--Electrical and Computer Engineering, Georgia Institute of Technology, 2010.Committee Chair: Anderson, David; Committee Member: Dorsey, John; Committee Member: Hasler, Paul; Committee Member: Kang, Sung Ha; Committee Member: Romberg, Justin. Part of the SMARTech Electronic Thesis and Dissertation Collection.
36
Munechika, Curtis K. "Merging panchromatic and multispectral images for enhanced image analysis /." Online version of thesis, 1990. http://hdl.handle.net/1850/11366.
37
Sun, Ning. "HDR image construction from multi-exposed stereo LDR images." Thesis, University of British Columbia, 2012. http://hdl.handle.net/2429/40130.
Abstract:
The vast majority of cameras in the market nowadays can only capture a limited dynamic
range of a scene. To generate high dynamic range (HDR) images, most existing methods use
multiple images obtained from a single low dynamic range (LDR) camera at consecutive instances. These methods can obtain good quality HDR images for still or slow motion scenes but not for scenes with fast motion.
In this thesis, we propose the use of two LDR cameras which have different exposures. To
generate an HDR image, the two differently exposed LDR images of the same scene are used. The two LDR images should be captured at the same instance, so as to deal with scenes with fast motion. The most challenging step in this approach is to obtain accurate estimates of the disparity maps of the scenes. This will allow us to correctly align the pixels from the two differently exposed pictures when forming the HDR images. Very few state-of-the-art stereo matching algorithms can deal with the problem of obtaining accurate estimates of the disparity map from two differently exposed images. This is because the input LDR images that are used to construct HDR images have large radiometric changes. In addition, the two input LDR images usually have saturations in different areas. To obtain accurate disparity maps, we present a novel algorithm that obtains an initial estimate of the disparity map. Then a refinement step is used to minimize the edge effect and interpolates the values in the saturated regions.
Compared to other state-of-the-art methods, our algorithm has a simpler set up with only two standard commercial LDR cameras. The offline processing of the LDR images has a simpler cost function, especially the cost function we use in the refinement step of the disparity map. This reduces the computational complexity and thus the processing time of the LDR images to form the HDR image. Moreover, the disparity map computed by our algorithm can tolerate greater radiometric changes and saturations. Therefore, the HDR images constructed by our algorithm are smoother and have fewer defects than those constructed by other methods.
38
Kim, Jin-Seo. "Evaluation of image quality for still and moving images." Thesis, University of Leeds, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.496538.
39
BATISTA, LEONARDO VIDAL. "COMPARING AUTOMATIC IMAGE CLASSIFICATION TECHNIQUES OF REMOTE SENSING IMAGES." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 1993. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=8870@1.
Abstract:
CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICONeste trabalho, diversas técnicas de classificação automática de imagens de sensoriamento remoto são investigadas. Na análise, incluem-se um método não- paramétrico, denominado K-Médias. Adaptativos Hierárquico (KMAH), e seis paramétricos: o Classificador de Máxima Verossimilhança (MV), o de Máxima Probabilidade a Posteriori (MAP), o MAP Adaptativo (MAPA), por Subimagens (MAPSI), o Contextual Tilton-Swain (CXTS) e o Contextual por Subimagens (CXSI). O treinamento necessário à implementação das técnicas paramétricas foi realizado de forma não-supervisionada, usando-se para tanto a classificação efetuada pelo KMAH. Considerações a respeito das vantagens e desvantagens dos classificadores, de acordo com a observação das taxas de erros e dos tempos de processamento, apontaram as técnicas MAPA e MAPSI com as mais convenientes
In this thesis, several techniques of automatic classfication of remote sensing impeages are investigated. Included in the analysis are ane non-parametric method, known as Adaptative hierarchical K-means (KMAH), and six parametric ones: the Maximum Likelihood (MV), the Maximum a Posteriori Probability (MAP), the Adaptative MAP (MAPA), the Subimages MAP (MAPSI), the tilton-Swain Contextual, (CXTS) and the Subimages Contextual (CXSI) classifiers. The necessary training for the parametric case was done in a non-supervised form, by using the KMAH classification. Considerations about the advantages and disadvantages of the classifiers were made and, based on the observation of the error rates and processing time, the MAPA and MAPSI have shown the best performances.
40
RIBEIRO, FRANCISCO TAUNAY COSTA. "VJING: THE IMAGES COMMUNICATION AND THE INTERACTION MAN-IMAGE." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2007. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=10407@1.
Abstract:
COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOREste trabalho investiga a ação do Vj, o Vjing e seus desdobramentos e relações com a evolução da produção e recepção das imagens cinéticas. O Vjing, que ocorre geralmente em festas e eventos de música eletrônica, se caracteriza pela manipulação de imagens no ato da apresentação, acompanhando a música do Dj, e serve como paradigma para pensar a interação (influência recíproca) entre homem e imagem, bem como a relação entre música e imagem. A imagem cinética, pensada sob a perspectiva de sua plástica- rítmica, evanescente, que atua no eixo espaço-temporal tal qual a música, é característica do Vjing, com sua narrativa fragmentária e sua desconstrução e manipulação do movimento e do tempo nas imagens projetadas. A partir dessa ação, a forma de comunicar das imagens em movimento pode ser investigada, desviando-se daquela narrativa dramática encontrada no cinema clássico. O aparecimento de novas tecnologias de criação e manipulação de imagens e sons possibilita uma explosão de criatividade e da expressão das subjetividades através do meio audiovisual, com o surgimento e o resgate de diferentes formas narrativas.
This work investigates the Vj s performance, the Vjing and its derivatives, in relation with the evolution of production and reception of moving pictures. The Vjing, which generally happens in parties and electronic music events, is characterized by manipulation of images in the act of presentation, matching the Dj s music. And it also works as a paradigm to explore the interaction (mutual influence) between image and man, as well as the relation between music and image. The moving picture, seen under the perspective of its evanescent plastic and rhythmics, acting in the spacetime axis just like music, is part of Vjing, with its fragmentary narrative and its deconstruction and manipulation of movement and time in the projected images. From this action, the way images communicate can be researched, deviating from the dramatic narrative of classical cinema. The rise of new Technologies of image and sound creation and manipulation enables an explosion of creativity and expression of personal subjectivity through the audiovisual media, with the emergence and the rescue of different narrative forms.
41
Murphy, Sean Daniel. "Medical image segmentation in volumetric CT and MR images." Thesis, University of Glasgow, 2012. http://theses.gla.ac.uk/3816/.
Abstract:
This portfolio thesis addresses several topics in the field of 3D medical image analysis. Automated methods are used to identify structures and points of interest within the body to aid the radiologist. The automated algorithms presented here incorporate many classical machine learning and imaging techniques, such as image registration, image filtering, supervised classification, unsupervised clustering, morphology and probabilistic modelling. All algorithms are validated against manually collected ground truth. Chapter two presents a novel algorithm for automatically detecting named anatomical landmarks within a CT scan, using a linear registration based atlas framework. The novel scans may contain a wide variety of anatomical regions from throughout the body. Registration is typically posed as a numerical optimisation problem. For this problem the associated search space is shown to be non-convex and so standard registration approaches fail. Specialised numerical optimisation schemes are developed to solve this problem with an emphasis placed on simplicity. A semi-automated algorithm for finding the centrelines of coronary arterial trees in CT angiography scans given a seed point is presented in chapter three. This is a modified classical region growing algorithm whereby the topology and geometry of the tree are discovered as the region grows. The challenges presented by the presence of large organs and other extraneous material in the vicinity of the coronary trees is mitigated by the use of an efficient modified 3D top-hat transform. Chapter four compares the accuracy of three unsupervised clustering algorithms when applied to automated tissue classification within the brain on 3D multi-spectral MR images. Chapter five presents a generalised supervised probabilistic framework for the segmentation of structures/tissues in medical images called a spatially varying classifier (SVC). This algorithm leverages off non-rigid registration techniques and is shown to be a generalisation of atlas based techniques and supervised intensity based classification. This is achieved by constructing a multivariate Gaussian classifier for each voxel in a reference scan. The SVC is applied in the context of tissue classification in multi-spectral MR images in chapter six, by simultaneously extracting the brain and classifying the tissues types within it. A specially designed pre-processing pipeline is presented which involves inter-sequence registration, spatial normalisation and intensity normalisation. The SVC is then applied to the problem of multi-compartment heart segmentation in CT angiography data with minimal modification. The accuracy of this method is shown to be comparable to other state of the art methods in the field.
42
Cabrera, Gil Blanca. "Deep Learning Based Deformable Image Registration of Pelvic Images." Thesis, KTH, Skolan för kemi, bioteknologi och hälsa (CBH), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279155.
Abstract:
Deformable image registration is usually performed manually by clinicians,which is time-consuming and costly, or using optimization-based algorithms, which are not always optimal for registering images of different modalities. In this work, a deep learning-based method for MR-CT deformable image registration is presented. In the first place, a neural network is optimized to register CT pelvic image pairs. Later, the model is trained on MR-CT image pairs to register CT images to match its MR counterpart. To solve the unavailability of ground truth data problem, two approaches were used. For the CT-CT case, perfectly aligned image pairs were the starting point of our model, and random deformations were generated to create a ground truth deformation field. For the multi-modal case, synthetic CT images were generated from T2-weighted MR using a CycleGAN model, plus synthetic deformations were applied to the MR images to generate ground truth deformation fields. The synthetic deformations were created by combining a coarse and fine deformation grid, obtaining a field with deformations of different scales. Several models were trained on images of different resolutions. Their performance was benchmarked with an analytic algorithm used in an actual registration workflow. The CT-CT models were tested using image pairs created by applying synthetic deformation fields. The MR-CT models were tested using two types of test images. The first one contained synthetic CT images and MR ones deformed by synthetically generated deformation fields. The second test set contained real MR-CT image pairs. The test performance was measured using the Dice coefficient. The CT-CT models obtained Dice scores higherthan 0.82 even for the models trained on lower resolution images. Despite the fact that all MR-CT models experienced a drop in their performance, the biggest decrease came from the analytic method used as a reference, both for synthetic and real test data. This means that the deep learning models outperformed the state-of-the-art analytic benchmark method. Even though the obtained Dice scores would need further improvement to be used in a clinical setting, the results show great potential for using deep learning-based methods for multi- and mono-modal deformable image registration.
43
Wang, Kang. "Image Transfer Between Magnetic Resonance Images and Speech Diagrams." Thesis, Université d'Ottawa / University of Ottawa, 2020. http://hdl.handle.net/10393/41533.
Abstract:
Realtime Magnetic Resonance Imaging (MRI) is a method used for human
anatomical study. MRIs give exceptionally detailed information about soft-tissue
structures, such as tongues, that other current imaging techniques cannot achieve.
However, the process requires special equipment and is expensive. Hence, it is not quite
suitable for all patients.
Speech diagrams show the side view positions of organs like the tongue, throat,
and lip of a speaking or singing person. The process of making a speech diagram is like
the semantic segmentation of an MRI, which focuses on the selected edge structure.
Speech diagrams are easy to understand with a clear speech diagram of the tongue and
inside mouth structure. However, it often requires manual annotation on the MRI
machine by an expert in the field.
By using machine learning methods, we achieved transferring images between
MRI and speech diagrams in two directions. We first matched videos of speech diagram
and tongue MRIs. Then we used various image processing methods and data
augmentation methods to make the paired images easy to train. We built our network
model inspired by different cross-domain image transfer methods and applied
reference-based super-resolution methods—to generate high-resolution images. Thus,
we can do the transferring work through our network instead of manually. Also,
generated speech diagram can work as an intermediary part to be transferred to other
medical images like computerized tomography (CT), since it is simpler in structure
compared to an MRI.
We conducted experiments using both the data from our database and other MRI
video sources. We use multiple methods to do the evaluation and comparisons with
several related methods show the superiority of our approach.
44
Montayne, Amanda. "Fitspirational Images, Body Image, Disordered Eating, and Compulsive Exercise." Thesis, Southern Illinois University at Edwardsville, 2017. http://pqdtopen.proquest.com/#viewpdf?dispub=10275337.
Abstract:
The purpose of this study was to examine the relationship between viewing fitspirational content and women's body image, exercise attitudes, and eating attitudes. It was hypothesized that viewing fitspirational content would lead to a reduction in body image and an increase in eating disorder-related thoughts and guilt or sadness related to exercising. One significant interaction was found, which implied that individuals who had viewed the fitspirational content had more guilt and depressive feelings related to exercise than individuals in the control group when comparing to the pre-test. None of the remaining hypotheses were supported.
45
Sarangi, Ishan Kumar, and Sudarshan Nayak. "Image mosaicing of panoramic images." Thesis, 2014. http://ethesis.nitrkl.ac.in/6455/1/E-58.pdf.
Abstract:
Image mosaicing is combining or stitching several images of a scene or object taken from different angles into a single image with a greater angle of view. This is practised a developing field. Recent years have seen quite a lot of advancement in the field. Many algorithms have been developed over the years. Our work is based on feature based approach of image mosaicing. The steps in image mosaic consist of feature point detection, feature point descriptor extraction and feature point matching. RANSAC algorithm is applied to eliminate variety of mismatches and acquire transformation matrix between the images. The input image is transformed with the right mapping model for image stitching. Therefore, this paper proposes an algorithm for mosaicing two images efficiently using Harris-corner feature detection method, RANSAC feature matching method and then image transformation, warping and by blending methods.
46
Suri, Sahil [Verfasser]. "Automatic image to image registration for multimodal remote sensing images / Sahil Suri." 2010. http://d-nb.info/1001408209/34.
47
Bloomquist, James D. "Hierarchical image segmentation to infrared images." Thesis, 1985. http://hdl.handle.net/10945/21362.
48
江文尉. "Digital image enhancement on chromatic images." Thesis, 1990. http://ndltd.ncl.edu.tw/handle/60366945930676014945.
49
Tsai, Chi-Shien, and 蔡繼賢. "Image Quality Improvement for JPEG Images." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/07438556114344329220.
Abstract:
碩士淡江大學
資訊工程學系資訊網路與通訊碩士班
101
In this paper we proposed a method to enhance the quality of the decompressed JPEG images, which is an improved version of the method proposed by Chang et.al.. A so-called Modified Coefficient Adjustment Block is used to record the round off situation while DCT coefficients in a block are quantized according to a given quantization block. In the decompression stage, the information recorded in the Modified Coefficient Adjustment Block is then referred to adjust the de-quantized DCT coefficients before the Inverse DCT transformation. We provide two choices of parameter setting, fixed and adaptive parameters. Experimental results show that no matter whether fixed or adaptive parameters are used, our method provides significantly better results than The method proposed by Chang et al..
50
Sahu, Sangeeta. "Image registration techniques for medical images." Thesis, 2014. http://ethesis.nitrkl.ac.in/6452/1/E-60.pdf.
Abstract:
In this research work, approaches for image registration are proposed. The image registration methods can be grouped into two classes. One is intensity based method which is based on gray values of the pair of images and the second one is based on image feature which is done by obtaining some features or landmarks in the images like points, lines or surfaces. Edges in the images can be detected very easily in the images. Thus, using these edges some features can be obtained by which we can accomplish feature based registration. But, feature based registration has some limitations as well as advantages. The proposed method employs feature based registration technique to obtain a coarsely registered image which can be given as input to intensity based registration technique to get a fine registration result. It helps to reduce the limitations of intensity based technique. i.e. it takes less time for registration. To achieve this task, the mutual information is selected as similarity parameter. Mutual information (MI) is used widely as a similarity measure for registration. In order to improve the robustness of this similarity measure, spatial information is combined with normalized mutual information(NMI). MI is multiplied with a gradient term to integrate spatial information to mutual information and this is taken as similarity measure. The registration function is less affected if sampling resolution is low. It contains correct global maxima which are sometimes not found in case of mutual information. For optimization purpose, Fast Convergence Particle Swarm Optimization technique (FCPSO) is used. In this optimization method, the diversity of position of single particle is balanced by adding a new variable, particle mean dimension (pmd) of all particles to the existing position and velocity equation. It reduces the convergence time by reducing the number of iterations for optimization.