Dissertations / Theses on the topic 'Fingerprints Classification'
To see the other types of publications on this topic, follow the link: Fingerprints Classification.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 33 dissertations / theses for your research on the topic 'Fingerprints Classification.'
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
Massimiliani, Lorenzo. "Classification and clustering of video fingerprints: preliminary results." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/22973/.
Full textAbstract:
Many photos and videos are produced and uploaded to the Internet every day. Even though this is a small part of the total, a large amount of them is illegal.
Once digital content has been distributed online, it is often difficult to re-associate the photo or video to the device that produced it or to the user who initially shared it.
To counter the spread of illegal content, there is a branch of studies called “source camera identification”, which aims to reconnect a photo or video to the device that developed it. The idea behind source camera identification is that each camera, having imperfections that make it unique, gives a digital fingerprint to the content it produces. The noise of a digital content, which represents a variation of intensity that cannot be found in the recorded content, contains the fingerprint along with some random factors.
The noises, which are extracted through denoising algorithms, can be used directly to identify the device that produced the content, or they can be used to estimate the fingerprint. This thesis works in the source camera identification of video content.
Two datasets are considered: one called Vision, which is considered the reference dataset in this area and one made available by the University of Bologna.
The work carried out in this thesis was to extract the noises on those datasets, and calculate the fingerprints, comparing different approaches present in the state of the art. The approach that was chosen has yielded the best results through a classi-
fication algorithm. Once the noises were extracted and the fingerprints calculated, classification and clustering techniques were applied. Two classification techniques have been developed one through convolutional neural network and another using a function called Peak-to-correlation energy. Clustering
algorithms have been applied, already developed to work in this area, one that considers a known number of cameras and another that considers an unknown number.
2
Sutanto, Kevin. "RNA Sequence Classification Using Secondary Structure Fingerprints, Sequence-Based Features, and Deep Learning." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/41876.
Full textAbstract:
RNAs are involved in different facets of biological processes; including but not limited to controlling and inhibiting gene expressions, enabling transcription and translation from DNA to proteins, in processes involving diseases such as cancer, and virus-host interactions. As such, there are useful applications that may arise from studies and analyses involving RNAs, such as detecting cancer by measuring the abundance of specific RNAs, detecting and identifying infections involving RNA viruses, identifying the origins of and relationships between RNA viruses, and identifying potential targets when designing novel drugs.
Extracting sequences from RNA samples is usually not a major limitation anymore thanks to sequencing technologies such as RNA-Seq. However, accurately identifying and analyzing the extracted sequences is often still the bottleneck when it comes to developing RNA-based applications.
Like proteins, functional RNAs are able to fold into complex structures in order to perform specific functions throughout their lifecycle. This suggests that structural information can be used to identify or classify RNA sequences, in addition to the sequence information of the RNA itself. Furthermore, a strand of RNA may have more than one possible structural conformations it can fold into, and it is also possible for a strand to form different structures in vivo and in vitro. However, past studies that utilized secondary structure information for RNA identification purposes have relied on one predicted secondary structure for each RNA sequence, despite the possible one-to-many relationship between a strand of RNA and the possible secondary structures. Therefore, we hypothesized that using a representation that includes the multiple possible secondary structures of an RNA for classification purposes may improve the classification performance.
We proposed and built a pipeline that produces secondary structure fingerprints given a sequence of RNA, that takes into account the aforementioned multiple possible secondary structures for a single RNA. Using this pipeline, we explored and developed different types of secondary structure fingerprints in our studies. A type of fingerprints serves as high-level topological representations of the RNA structure, while another type represents matches with common known RNA secondary structure motifs we have curated from databases and the literature. Next, to test our hypothesis, the different fingerprints are then used with deep learning and with different datasets, alone and together with various sequence-based features, to investigate how the secondary structure fingerprints affect the classification performance.
Finally, by analyzing our findings, we also propose approaches that can be adopted by future studies to further improve our secondary structure fingerprints and classification performance.
3
Späth, Bastian, Matthias Philipp, and Thomas Bartnitzki. "Machine performance and acoustic fingerprints of cutting and drilling." TU Bergakademie Freiberg, 2017. https://tubaf.qucosa.de/id/qucosa%3A23182.
Full textAbstract:
‘It is always dark ahead of the pick!’ This centuries-old miners’ expression still reveals the uncertainty about the upcoming rock properties during exploration and extraction processes. It is still tough to predict what a drill rig or a cutting machine will experience during operation. However, in terms of safety, energy consumption and the performance of the whole machine it would be beneficial to be able to monitor such an extraction process. Hence, different sensors or sensor combinations are tested during cutting and drilling processes within RealTime Mining project. First aim is to depict the machine performance of the machine at any time. In a second step sensor information is also used to conclude on mechanical rock properties during the process.
Measuring the machine performance for cutting and drilling is quite similar and has been condensed under the terms Monitoring-While-Cutting (MWC) respectively Monitoring-While-Drilling (MWD). Both monitoring systems contain a bundle of sensors to depict the whole process. As an example, the energy demand of such a machine can be determined by measuring the power consumption of the engines constantly. Furthermore, the process parameters like advance rates and drilling or cutting speed have to be evaluated as well to be able to depict the whole extraction machine.
To conclude on mechanical rock properties several other sensor solutions have been tested and finally integrated into those monitoring systems. One of the most important rock properties for drilling and cutting is the rock strength. Increasing rock strength during an extraction process leads to increasing forces that are needed to break a certain amount of rock. Hence, e.g. measuring the torque of a drill string or the cutting forces can be an indicator on rock resistance or rock strength. Not minor important, is the characteristic rock breakage behavior which can be classified by the use of ‘acoustic’ sensors. Dependent on the rock properties that currently is drilled or cut through a characteristic fracture occurs in front of the tool. This results in audible and also inaudible characteristic acoustic waves that propagate through the machine body and can be gathered on the machine by piezo-electric sensors. The interpretation of these signals could lead to a material classification already during the extraction process.
Several tests of these sensor technologies have been conducted in laboratory environment as well in field tests. The most promising results are going to be presented.
4
Tian, Ye. "Développement d'une méthode de géolocalisation à l'intérieur de bâtiments par classification des fingerprints GSM et fusion de données de capteurs embarqués." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066027/document.
Full textAbstract:
L’objet de cette thèse est l’étude de la localisation et de la navigation à l’intérieur de bâtiments à l’aide des signaux disponibles dans les systèmes mobiles cellulaires et, en particulier, les signaux GSM.Le système GPS est aujourd’hui couramment utilisé en extérieur pour déterminer la position d’un objet, mais les signaux GPS ne sont pas adaptés à la localisation en intérieurIci, la localisation en intérieur est obtenue à partir de la technique des «empreintes» de puissance des signaux reçus sur les canaux utilisés par les réseaux GSM. Elle est réalisée à l’échelle de la pièce. Une classification est effectuée à partir de machines à vecteurs supports et les descripteurs utilisés sont les puissances de toutes les porteuses GSM. D’autres capteurs physiques disponibles dans les téléphones portables fournissent des informations utiles pour déterminer la position ou le déplacement de l’utilisateur. Celles-ci, ainsi que la cartographie de l’environnement, sont associées aux résultats obtenus à partir des «empreintes» GSM au sein de filtres particulaires afin d’obtenir une localisation plus précise, et sous forme de coordonnées continues.Les résultats obtenus montrent que l’utilisation des seules empreintes GSM permet de déterminer la pièce correcte dans 94% des cas sur une durée courte et que les performances restent stables pendant plusieurs mois, de l’ordre de 80%, si les données d’apprentissage sont enregistrées sur quelques jours. L’association de la cartographie du lieu et des informations issues des autres capteurs aux données de classification permettent d’obtenir les coordonnées de la trajectoire du système mobile avec une bonne précision et une bonne fiabilitéGPS has long been used for accurate and reliable outdoor localization, but it cannot operate in indoor environments, which suggests developing indoor localization methods that can provide seamless and ubiquitous services for mobile users.In this thesis, indoor localization is realized making use of received signal strength fingerprinting technique based on the existing GSM networks. A room is defined as the minimum location unit, and support vector machine are used as a mean to discriminate the rooms by classifying received signal strengths from very large number of GSM carriers. At the same time, multiple sensors, such as accelerometer and gyroscope, are widely available for modern mobile devices, which provide additional information that helps location determination. The hybrid approach that combines the GSM fingerprinting results with mobile sensor and building layout information using a particle filter provides a more accurate and fine-grained localization result.The results of experiments under realistic conditions demonstrate that correct room number can be obtained 94% of the time provided the derived model is used before significant received signal strength drift sets in. Furthermore, if the training data is sampled over a few days, the performance can remain stable exceeding 80% over a period of months, and can be further improved with various post-processing techniques. Moreover, including the mobile sensors allows the system to localize the mobile trajectory coordinates with high accuracy and reliability
5
Zhang, Fan. "Fingerprint classification with combined neural networks." Thesis, University of Surrey, 2009. http://epubs.surrey.ac.uk/2216/.
Full textAbstract:
Biometric identification has been widely used in identifying a genuine person from an impostor. Fingerprint identification is becoming a very popular biometric identification technique because it has special properties: fingerprints are unique and unchangeable. With increased processing capability of computers and larger the size of fingerprint databases are increased, the demand for higher speed processing and greater processing capacity for automatic fingerprint identification systems (AFIS) has increased. APIS consists of fingerprint feature acquisition, fingerprint classification and fingerprint matching. Fingerprint classification plays a key role in fingerprint identification as efficient and accurate algorithms cannot only reduce the search time for searching large fingerprint databases, but they can also reduce the number of fingerprints that need to be searched.
6
Mohamed, Suliman M. "Fingerprint-based biometric recognition allied to fuzzy-neural feature classification." Thesis, Sheffield Hallam University, 2002. http://shura.shu.ac.uk/20071/.
Full textAbstract:
The research investigates fingerprint recognition as one of the most reliable biometrics identification methods. An automatic identification process of humans-based on fingerprints requires the input fingerprint to be matched with a large number of fingerprints in a database. To reduce the search time and computational complexity, it is desirable to classify the database of fingerprints into an accurate and consistent manner so that the input fingerprint is matched only with a subset of the fingerprints in the database. In this regard, the research addressed fingerprint classification. The goal is to improve the accuracy and speed up of existing automatic fingerprint identification algorithms. The investigation is based on analysis of fingerprint characteristics and feature classification using neural network and fuzzy-neural classifiers. The methodology developed, is comprised of image processing, computation of a directional field image, singular-point detection, and feature vector encoding. The statistical distribution of feature vectors was analysed using SPSS. Three types of classifiers, namely, multi-layered perceptrons, radial basis function and fuzzy-neural methods were implemented. The developed classification systems were tested and evaluated on 4,000 fingerprint images on the NIST-4 database. For the five-class problem, classification accuracy of 96.2% for FNN, 96.07% for MLP and 84.54% for RBF was achieved, without any rejection. FNN and MLP classification results are significant in comparison with existing studies, which have been reviewed.
7
Kim, Dae Wook. "Data-Driven Network-Centric Threat Assessment." Wright State University / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=wright1495191891086814.
Full text
8
Wang, Yi, and alice yi wang@gmail com. "Ridge Orientation Modeling and Feature Analysis for Fingerprint Identification." RMIT University. Computer Science and Information Technology, 2009. http://adt.lib.rmit.edu.au/adt/public/adt-VIT20091009.152317.
Full textAbstract:
This thesis systematically derives an innovative approach, called FOMFE, for fingerprint ridge orientation modeling based on 2D Fourier expansions, and explores possible applications of FOMFE to various aspects of a fingerprint identification system. Compared with existing proposals, FOMFE does not require prior knowledge of the landmark singular points (SP) at any stage of the modeling process. This salient feature makes it immune from false SP detections and robust in terms of modeling ridge topology patterns from different typological classes. The thesis provides the motivation of this work, thoroughly reviews the relevant literature, and carefully lays out the theoretical basis of the proposed modeling approach. This is followed by a detailed exposition of how FOMFE can benefit fingerprint feature analysis including ridge orientation estimation, singularity analysis, global feature characterization for a wide variety of fingerprint categories, and partial fin gerprint identification. The proposed methods are based on the insightful use of theory from areas such as Fourier analysis of nonlinear dynamic systems, analytical operators from differential calculus in vector fields, and fluid dynamics. The thesis has conducted extensive experimental evaluation of the proposed methods on benchmark data sets, and drawn conclusions about strengths and limitations of these new techniques in comparison with state-of-the-art approaches. FOMFE and the resulting model-based methods can significantly improve the computational efficiency and reliability of fingerprint identification systems, which is important for indexing and matching fingerprints at a large scale.
9
Wescher, Agnes. "Molekularbiologische Typisierung von Streptococcus canis isoliert aus subklinisch mastitiskranken Kühen in hessischen Milchviehbetrieben." Doctoral thesis, Universitätsbibliothek Leipzig, 2009. http://nbn-resolving.de/urn:nbn:de:bsz:15-20090609-095913-0.
Full textAbstract:
In der vorliegenden Arbeit wurden 2460 Viertelgemelksproben aus 16 hessischen Milcherzeugerbetrieben untersucht. 115 S. canis-Isolate konnten gefunden und auf ihre morphologischen, biochemischen und bei molekularbiologischen Eigenschaften untersucht werden. Die Isolate stammten von Viertelgemelksproben bzw. Tankproben, die zu einem oder mehreren Zeitpunkten in den Betrieben genommen wurden. Die Untersuchung der biochemischen Eigenschaften erbrachte 24 verschiedene Reaktionsmuster. Der Vergleich dieser 24 Biotypen mit einem S. canis-Referenzstamm mittels tDNA-PCR und 16S-RNA-PCR ergab eine völlige Übereinstimmung (100%) und damit eine sichere Spezies-Identifizierung. Zur Aufklärung epidemiologischer Zusammenhänge und zur Intra-Spezies-Identifizierung wurde von allen 115 Isolaten mittels PFGE nach Makrorestriktionsverdau mit SmaI ein DNA-Fingerprint erstellt. Dabei ergaben sich 21 verschiedene Restriktionsmuster. Von den 21 nach Makrorestriktion mit Sma I und anschließender PFGE unterscheidbaren Restriktionsmustern wurde je ein Isolat zur Bestimmung der Differenzierungsfähigkeit der Restriktionsenzyme Cla I und Apa I sowie der RAPD-PCR weitergehend untersucht. Für die Beurteilung epidemiologischer Zusammenhänge bei S. canis erwies sich die PFGE nach Makrorestriktion mittels Sma I als die differenzierteste Variante. Die mittels PFGE nach Makrorestriktionsverdau mit Sma I durchgeführten Untersuchungen der 115 Isolate zeigten, dass zu einem Probennahme-Termin gewonnene Isolate identisch waren; vom gleichen Betrieb zu unterschiedlichen Zeiten entnommene Proben zeigten z.T. deutliche Unterschiede, und bei Isolaten von verschiedenen Betrieben konnten keine Verwandtschaftsbeziehungen nachgewiesen werden. Aufgrund dieser genotypischen Eigenschaften der Kulturen konnte gezeigt werden, dass es sich bei durch S. canis verursachte Mastitiden um ein infektiöses Bestandsproblem handelt, bei dem der Erreger von Viertel zu Viertel und von Kuh zu Kuh übertragen wird.
10
Eschenhagen, Martin. "Molekulare Untersuchung zweier Belebtschlammanlagen unter besonderer Berücksichtigung der biologischen Phosphorelimination." Doctoral thesis, Technische Universität Dresden, 2003. https://tud.qucosa.de/id/qucosa%3A24360.
Full textAbstract:
Aufgrund der ökologischen und ökonomischen Problematik der chemischen Phosphatfällung ist eine Optimierung der Effizienz und Stabilität der biologischen Verfahren zur Phosphat-elimination erforderlich. Hierfür ist jedoch ein fundiertes Wissen über die daran beteiligten Organismen eine entscheidende Vorraussetzung. Das Ziel der vorliegenden Arbeit war es, die mikrobielle Populationstruktur von zwei Belebtschlamm-anlagen im Labormaßstab mit Hilfe von drei unterschiedlichen 16S rDNA basierenden molekular-biologischen Methoden zu charakterisieren. Ein besonderer Schwer-punkt ist hierbei die Analyse der Bakterien, die mit der erhöhten biologischen Phosphat-elimination in Verbindung gebracht werden. Dies sind Vertreter der Rhodocyclus-Gruppe, der Gattung Tetrasphaera und der Gattung Acinetobacter. Als Untersuchungsobjekte wurden zwei Hauptstromverfahren zur erhöhten biologischen Phosphatelimination gewählt, die sich im Schlamm-alter, der Schlammbelastung und der sich daraus resultierenden Nitrifikationsleistung unterscheiden. Aufgrund der gewählten Verfahrensweisen wurde der Einfluss der Nitrifikation auf die Zusammensetzung der Belebtschlammbiozönose ebenfalls untersucht. Um praxisnahe Verhältnisse zu erreichen, wurden die Anlagen mit kommunalem Abwasser beschickt. Für einen Vergleich sollten Proben aus kommunalen Kläranlagen mit deutlich anderen Verfahrensweisen in die Untersuchungen mit einbezogen werden.
11
Bleul, Catrin. "Molekularbiologische Analyse mikrobieller Gemeinschaften in Talsperrensedimenten." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2004. http://nbn-resolving.de/urn:nbn:de:swb:14-1097570982718-83940.
Full textAbstract:
Mikrobielle Prozesse spielen eine wichtige Rolle im Sediment von Talsperren und Seen. Demgegenüber stehen nur unzureichende Erkenntnisse über die Zusammensetzung mikrobieller Biozönosen in Sedimenten sowie deren Aktivität zur Verfügung. Das Ziel dieser Studie war die Untersuchung und der Vergleich der Zusammensetzung und der Struktur mikrobieller Gemeinschaften in Sedimenten um eine Abschätzung der mikrobiellen Diversität in Talsperrensedimenten unterschiedlicher Trophie zu erreichen. Durch die Kombination der in dieser Arbeit verwendeten Methoden (Vergleichende 16S rDNA Analyse, Fingerprinttechniken, klassische Methoden) konnte eine Charakterisierung der mikrobiellen Zusammensetzung der obersten 5 cm von den Talsperrensedimenten Neunzehnhain, Muldenberg, Quitzdorf und Saidenbach erzielt werden. Die vergleichende 16S rDNA Analyse offenbarte in 2541 analysierten rekombinanten Klonen 528 verschiedene Sequenztypen, welche zu 293 OTUs zusammengefaßt werden konnten. Obwohl die Gemeinschaften der verschiedenen Talsperren nur schwach auf der Ebene der phylogenetischen Gruppen differierten, konnte durch die Verwendung von Ähnlichkeitsindices gezeigt werden, dass jede Talsperre eine spezifische mikrobielle Sedimentgemeinschaft aufweist. Über 60% aller Klone zeigten Ähnlichkeiten von mehr als 97% zu 16S rDNA-Sequenzen kultivierter Organismen oder phylogenetisch eingeordneten Sequenzen (14 bekannte phylogenetische Gruppen). Alle anderen Klone zeigten hohe Sequenzhomologien zu unidentifizierten, phylogenetisch bisher nicht eingeordneten Bakterien. Diese Bakterien waren mit Anteilen zwischen 19,8% (Muldenberg) und 54,6% (Saidenbach) in den 16S rDNA Bibliotheken repräsentiert. Mittels Fingerprinttechniken (DGGE, T-RFLP, ARISA) konnten komplexe Muster der mikrobiellen Diversität erzeugt werden. Dabei konnten die Ergebnisse der 16S rDNA Analyse bestätigt werden. Durch die verwendeten Methoden konnte eine komplexe mikrobielle Diversität in den Sedimenten aufgedeckt werden und die Ergebnisse weisen darauf hin, dass die mikrobielle Diversität in Sedimenten wesentlich höher ist als bisher angenommen.
12
Varga, Adam. "Identifikace a charakterizace škodlivého chování v grafech chování." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2021. http://www.nusl.cz/ntk/nusl-442388.
Full textAbstract:
Za posledné roky je zaznamenaný nárast prác zahrňujúcich komplexnú detekciu malvéru. Pre potreby zachytenia správania je často vhodné pouziť formát grafov. To je prípad antivírusového programu Avast, ktorého behaviorálny štít deteguje škodlivé správanie a ukladá ich vo forme grafov. Keďže sa jedná o proprietárne riešenie a Avast antivirus pracuje s vlastnou sadou charakterizovaného správania bolo nutné navrhnúť vlastnú metódu detekcie, ktorá bude postavená nad týmito grafmi správania. Táto práca analyzuje grafy správania škodlivého softvéru zachytené behavioralnym štítom antivírusového programu Avast pre proces hlbšej detekcie škodlivého softvéru. Detekcia škodlivého správania sa začína analýzou a abstrakciou vzorcov z grafu správania. Izolované vzory môžu efektívnejšie identifikovať dynamicky sa meniaci malware. Grafy správania sú uložené v databáze grafov Neo4j a každý deň sú zachytené tisíce z nich. Cieľom tejto práce bolo navrhnúť algoritmus na identifikáciu správania škodlivého softvéru s dôrazom na rýchlosť skenovania a jasnosť identifikovaných vzorcov správania. Identifikácia škodlivého správania spočíva v nájdení najdôležitejších vlastností natrénovaných klasifikátorov a následnej extrakcie podgrafu pozostávajúceho iba z týchto dôležitých vlastností uzlov a vzťahov medzi nimi. Následne je navrhnuté pravidlo pre hodnotenie extrahovaného podgrafu. Diplomová práca prebehla v spolupráci so spoločnosťou Avast Software s.r.o.
13
吳宜龍. "A Wavelet-Based Fingerprints Classification System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/80955253641628571144.
Full textAbstract:
碩士中華大學
電機工程學系碩士班
92
One of the objectives of this thesis is to find a set of more suitable features via wavelet transform to identify fingerprints images on-line. A wavelet-based fingerprints classification system had been designed, in which, the fingerprints features are extracted from the wavelet coefficients of the gray-scale fingerprints images. The system parameters are adjusted on the basis of a training set of fingerprints images. Since the pre-processing tasks such as the image enhancement, directional filtering, and ridge thinning that are usually performed on the classical minutiae-based fingerprints classification methods can be eliminated, the wavelet approach provides an efficient way to the fingerprints classification system.
14
Chen, Chun-Liang, and 陳俊良. "A study on efficient preprocessing and classification for fingerprints." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/80947327177553012199.
Full textAbstract:
碩士淡江大學
資訊工程學系
89
For most of the automatic fingerprint identification systems(AFIS), the performance of identification is significantly affected by that of preprocessing step which is a necessary step for almost all the AFIS’s. Such a preprocessing step includes segmentation, enhancement, noise reduction, binarization and thinning ,etc. An improved preprocessing technique is proposed in this thesis.Firstly, we partition a fingerprint image into small blocks with size 8 x 8 pixels. The variance of gray values in each block is evaluated to distinguish the fingerprint area from the background area, and then the fingerprint area is smoothed to reduce noise. A ridge direction computation algorithm is proposed, which calculates a few pixels locating at ridges or a valleys, instead of all pixels in the block, so that the unnecessary computation is reduced.Fingerprint classification is to assign a given fingerprint to a specific category, which can be done according to the number and locations of the singular points in the fingerprint. This fingerprint classification is used to facilitate the management of large fingerprint databases and to speed up the process of fingerprint matching. Singular points can be found using the ridge direction map and some specific masks, and can be classified into five types : left loop, right loop, whorl , arch and tented arch.The experimental results indicate that the proposed preprocessing method has demonstrated good performance in both the processing speed and the degree of correctness for feature extraction.
15
Jen, Cheng-Lin, and 任正麟. "Fingerprint Classification Using Singularities." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/67813355446298106764.
Full textAbstract:
碩士國立清華大學
資訊工程學系
89
Fingerprint is an important biometric feature because it’s believed that fingerprint is unique and easiness and the research is studied for a long time. Fingerprint classification provides information for identification. According to the definition of the FBI, fingerprints are classified to eight classes. In the thesis, we only classify fingerprints to four classes: Arch, Left Loop, Right Loop, and Whorl. The thesis describes a set of algorithms using directional image and singularities for fingerprint classification. The approach consists of four major steps. (i)Enhancement, (ii)Directional image computing, (iii)Singular points detection, and (iv)Classification We test the algorithm for the first 800 thumb fingerprint images from NIST Special Database 14. The average recognition rate is 87%.
16
Yeh, Chun-Nan, and 葉俊男. "A study on Fingerprint Classification." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/27620304293167355153.
Full textAbstract:
碩士國立交通大學
電資學院學程碩士班
90
Fingerprint classification provides an important indexing mechanism in a fingerprint database. An accurate and consistent classification can greatly reduce the fingerprint matching time for a large database. In this thesis, we present a new classification method for fingerprint images. In the proposed method, we classify fingerprints into five classes: arch, left loop, right loop, whorl, and tented arch. The major steps of this method include image enhancement, direction matrix extraction, singular points extraction and classification. Finally, we use the 1900 thumb fingerprints of NIST-4 database to evaluate the performance of the proposed method. The experimental result shows that we are able to achieve a classification accuracy of 88 percent (with 10% rejection).
17
Lu, Nan-Zone, and 盧南彰. "Minutiae Based Fingerprint Classification System." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/97401644914423900514.
Full textAbstract:
碩士國立清華大學
電機工程學系
97
Fingerprint Classification is a key technique in automatic fingerprint identification systems (AFIS). How to reduce the time of computing in an AFIS with a huge database is an important and necessary issue. Since on July 2006, the international standards organization (ISO) established the standard data format (template) of fingerprint based on minutiae (ISO 19794-2). The minutiae based fingerprint template becomes the international standard of fingerprint authentication/identification systems. However, handling image-based classification system into minutiae-based classification system is still a problem. This thesis present a fingerprint classification algorithm based on minutiae . The fingerprint category is clasified into one of the three classes:right loop, left loop and arch/whorl. Experimental results on live-scan database FVC2002-db1a demonstrate the validity of the proposed algorithm.
18
Yunn-Ruey, Perng, and 彭韻瑞. "A Study on Fingerprint Classification." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/75883844453924266573.
Full textAbstract:
碩士中原大學
電子工程研究所
86
In this paper, we propose a fingerprints classification method, using the ridge directional map on fingerprints, which is the necessary information in minutiae matching, without adding the other data for classification, and classify the input fingerprint patterns to seven genus: plain arch, tended arch, radial loop, ulnar loop, double loop and accidental. The technique is using characteristic mask to search the three kinds of characteristics: delta, core and whorl in the input fingerprint then classify the input fingerprint patterns for increase the accuracy at minutiae matching and decrease the matching time. A part of the fingerprints image we treat for input patterns are from the database of NIST(National Institute of Standard Technical) and the others are scanned on paper, totally 31 patterns. The input patterns can be successfully classified while their characteristics structure unbroken and the quality of image is not too poor. On the other hand, we also proposed a new technique on refining the fingerprint pattern after thinning it and the generation of ridge directional map, which can work effectively.
19
Wang, Yao-I., and 王耀億. "An AFIS Using Fingerprint Classification." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/63412069894813032772.
Full textAbstract:
碩士國立清華大學
資訊工程學系
89
In this thesis, we are devoted to the implementation of an automatic fingerprint identification system (AFIS). Fingerprint is considered to be a popular characteristic for personal identification which is necessary for access control, criminal identification and credit card usage. An AFIS can reduce time and laborious effort taken by manual identification effectively. Our AFIS is a minutiae-based matching system. Each fingerprint is recorded with its minutiae and is also classified into one of loop, whorl and arch types. The data set is acquired by FPS 110 Silicon Fingerprint Sensor manufactured by Veridicom. We will describe the whole procedures and show the experimental results.
20
Cavallaro, Anneliese. "Perceptual Expertise in Fingerprint Classification." Thesis, 2019. http://hdl.handle.net/2440/129100.
Full textAbstract:
This item is only available electronically.Fingerprint examiners classify crime scene prints as belonging a left or right hand and to a finger-type – thumb index, middle, ring or little – to help narrow their search for known candidate prints. While fingerprint examiners have been found to have impressive perceptual expertise little in known about their perceptual abilities in this aspect of the fingerprint examination process. The present study served as a first test of fingerprint classification expertise, probing experienced (n = 30) and novice (n = 30) examiners in their ability to classify a controlled, fully rolled, set of prints by hand-type and finger-type in a 10-alternative forced-choice task. Using a yoked novice-expert design performance was measured at two levels of specificity: a coarse-grained level accounting for hand-type classifications (i.e. “left” versus “right”), and a fine-grained level accounting for finger-type classifications (i.e., “thumb”, “index’, “middle”, “ring”, “little”). The results revealed experienced fingerprint examiners were indeed sensitive to the type of hand a fingerprint originated from and were significantly better than novices at these classifications. The experts were also able to classify fingerprints by finger-type, performing significantly above chance. Novices, on the other hand, did not differ from chance at classifying fingerprints by finger-type. These expert-novice differences remained large, even when accounting for response times when classifying prints by hand and finger-type. These data suggest that fingerprint experts are able to generalise their highly specific perceptual expertise with fingerprint to coarser grained levels of analysis: moving from identity to hand and finger classification.
Thesis (B.PsychSc(Hons)) -- University of Adelaide, School of Psychology, 2019
21
Chiou, Tzone-Kaie, and 邱宗楷. "Using Fuzzy Feature Extraction Fingerprint Classification." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/92760623300716087147.
Full textAbstract:
碩士元智大學
資訊工程學系
89
Fingerprint classification is a useful task for a large database of fingerprint recognition system. Accurate classification can speed up the process of fingerprint recognition. The fingerprint classification method proposed in this paper is based on human thinking and uses fuzzy theory. The key point of human thinking to classify fingerprint is attempting to find out fingerprint ridge, singular points (cores or deltas), direction of ridge, wrinkles or scars as global features. Firstly, in order to determine the fingerprint ridge direction, we need to transform the fingerprint image into 50x50 direction pattern. Then we use a set of pre-defined fuzzy mask to find out the singular points. Finally we use relationship between the singular points to classify the fingerprint. The experimental results of our method exhibit the best performance, a very low sensitivity and good classification accuracy.
22
Chou, Wen-Chi, and 周文祺. "A Study on Fingerprint Classification Systems." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/89324443782441152146.
Full textAbstract:
碩士國立中央大學
資訊工程研究所
90
Fingerprints are one of the most popular biometrics techniques in both of verification and identification mode because the fingerprints of an individual are unique. To facilitate the management of large fingerprint database and to speedup the process of fingerprint identification, we will first classify fingerprints into several categories such as arch, tented arch, left loop, right loop, and whorl. Several different approaches have been proposed for fingerprint classification. Each has its own advantages and limitations. In this thesis, a new fingerprint classification system is introduced. The proposed system tries to use feature as fewer as possible, while to achieve correct recognition as high as possible. In this system, we first propose an efficient method to transform fingerprint image into block directional image. Then a registration point detection method is applied to locate the center of each block directional image. In the following, several feature are extracted from a window whose center is located at the detected registration point. Finally, a class of Hyper Rectangular Composite Neural Networks (HRCNNs) is trained for fingerprint classification. The system was tested on 4000 images in the NIST-4 database.
23
Lu, Zhuang-Yuan, and 呂壯元. "Design of the Fingerprint Classification System." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/87539053350097829226.
Full textAbstract:
碩士淡江大學
電機工程學系
88
Preprocessing is a important step of the image processing. For each pixel’s neighborhoods be a unit of fingerprint image , we use sort method and K-mean algorithm to find out the cluster center and threshold value of two objects---ridge and valley respectively. Then for each unit is smoothed and shaped by filter with smooth parameter S and sharp parameter K. After had preprocessing , the original irregular histogram became bimodal histogram , and helpful to binarzation. It might cause classification fail by extracting singular points and correlate locations if fingerprint image is broken and obscure. Therefore we issue a new feature─directional and minute feature, due to it can show the crude and minute textures of the fingerprint image, on the other way it can solve that if image is broken or obscure and get well classification result. For extracting directional and minute features, we must build feature -directional- matrix first. The procedures of building feature-directional —matrix are binarzation image, thinning , calculating ridges slope, smoothing and quantification. Feature-directional-matrix discuss in chapter 2 of this paper respectively. Chapter 4 shows the framework of fingerprint classification system. Chapter 5 presents the experiment result, we can class more kinds of fingerprints and get well classification rate by we issuing the features(direction and minute feature) and classification framework(Neural-Backproprgation-Networks). Final is conclusion and future work.
24
Wu, Ming Yo, and 吳明祐. "A New Approach for Fingerprint Classification." Thesis, 1996. http://ndltd.ncl.edu.tw/handle/89542190642664821939.
Full textAbstract:
碩士國立交通大學
資訊科學學系
84
A new fingerprint classification method is proposed in this thesis. We classify fingerprints based on the global ridge shapes. The fingerprint image is first locally thresholded and the background is removed. After thresholding, we use the line following technique to obtain a thinned image. Then we establish a 6*5 directional matrix, which represents the global ridge shapes of the fingerprint. In order to establish the directional matrix, we insert five vertical lines into the thinned image and for each intersection point between one of the vertical lines and the thinned fingerprint, we calculate its ridge slope. Then we quantize these slopes into four directions using nonuniform quantization. After all directions of the intersection points are found, the intersection points in each line are divided into six parts. In each part, we calculate the number of each appearing direction and find the direction with maximum number. Then a directional matrix of 6*5 is generated, and some features are extracted from the directional matrix to represent the global ridge shapes. We finally classify fingerprints based on the combinations of these features. Experimental results are given to show that the system has a high classification rate.
25
Rong, Shys Shyu, and 徐世榮. "Design of a Fingerprint Classification System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/11305942329801154902.
Full textAbstract:
碩士淡江大學
電機工程學系
92
In the biometrics, using fingerprints is one of the most popular biometrics techniques in both verification and identification systems because the fingerprints of an individual are unique. To facilitate the management of large fingerprint database and to speed up the process of fingerprint identification, fingerprints will be first classified into several categories. Several different effective approaches have been proposed for fingerprint classification. Each has its own advantages and limitations. In this thesis, a new fingerprint classification system is introduced. The proposed system directly extracts the directional information from the thinned image of the fingerprint. The proposed octagon mask is used to find the center point of the interesting region. Then, the direction information of the interesting region is used to be the feature vectors for classifying. In the system, not only is the amount of computation reduced but also can the extracted information be used for identification on AFIS. The system is tested on 2000 images in the NIST-4 database.
26
Chen, Yu-yi, and 陳育誼. "Fingerprint Image Classification Based on Singular Points." Thesis, 2002. http://ndltd.ncl.edu.tw/handle/74077019496841793955.
Full textAbstract:
碩士國立清華大學
資訊工程學系
90
An automatic fingerprint identification system (AFIS) is one of the most important biometric technologies. How to reduce the time of computing in an AFIS with a huge database is an important and necessary issue. Fingerprint classification provides a practical method. In this thesis, we present a fingerprint classification algorithm based on singular points with novel criteria of a classification scheme. A fingerprint is classified into one of the four classes: arch, right loop, left loop, and whorl. The fingerprint classification was tested on 27,000 images in the Nist14 database as well as on 28 images in a live-scan database. The recognition rate of 83.13% for the Nist14 database and 96.4% for the live-scan database have been achieved.
27
Hsaio, Fu-Chung, and 蕭輔中. "Fast Fingerprint Classification Based on Normalized Histogram Statistic." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/ghucju.
Full textAbstract:
碩士國立東華大學
資訊工程學系
95
The fingerprint classification is essential for the fingerprint matching. It provides an important classified index for each fingerprint to enhance the efficiency of fingerprint matching in a large fingerprint database. Recently, some fingerprint classification methods were proposed. The Qi et al’s method provides a high classification speed but the lower accuracy. Nevertheless, Shah et al’s method provides the high accuracy but low efficiency. Therefore, our proposed classification method gains the high accuracy and needs simple computation by using the normalized histogram statistic. In this thesis, we proposed three fingerprint classification methods based on statistical analysis. Before classification, we have to preprocess the fingerprint images for enhancing the resolution and locating the core of fingerprint. The first is a pixel-histogram based method but it will be interfered by noise. The second is a line-segment-histogram based classification which reduces the interference but has the problem for classifying the whorl fingerprint. Therefore, a hybrid method combining the “pixel” and the “line-segment” is proposed. Our method can classify the fingerprints into four types: arch, whorl, left-loop and right-loop, and meantime need only simple operations and statistics. We test our methods with the NIST-4 fingerprint database. Experimental results show that our hybrid method is fast and effective for the fingerprint classification.
28
Hsu, Ching-Fu, and 許景復. "Fingerprint recognition based on classification and orientation field coding." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/64272392529698100972.
Full textAbstract:
碩士國立高雄應用科技大學
光電與通訊研究所
96
In this paper we present an innovative fingerprint classification scheme based on hierarchical singular point detection and traced orientation flow. Contrary to conventional methods, fingerprint is classified into seven categories: right loop, left loop, plain arch, tented arch, plain whorl, S-type (twin loop), and eddy. A novel technique for histogram specification is devised to enhance the separation between ridge and valley for the captured fingerprint. Then we transform the enhanced gray level image into an energy image and segment the impression region for orientation field estimation by projection on eight specified angles to locate the boundary. Hierarchical singular points detection through Poincare index method is used for the preliminary filtering of fingerprint class. Finally, the class label is assigned per the traced orientation flow and related threshold setting. The performance of the proposed method has been validated through experiments on the NIST4 database. For the 2133 images in the tests set, the classification accuracy reaches 87.36% with rejection rate 1.5% in average. In terms of speed, our system is faster, operating at an average processing time 0.9 sec per fingerprint on an AMD64 Athlon CPU 3.0 GHz PC.
29
Chang, Jeng-Horng, and 張正弘. "Fingerprint CLassification by Ridge DIstribution Sequences and Ridge Distribution Model." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/78873947177873333329.
Full textAbstract:
博士國立中央大學
資訊工程研究所
89
Ridges and ravines are the main components constituting a fingerprint. Traditional Automatic Fingerprint Identification Systems (AFIS) are mainly based on minutiae matching techniques. The minutiae for fingerprint identification are defined by ridge terminations and ridge bifurcations. Most AFIS perform ridge line following process to automatically detect minutiae based on binary or skeleton fingerprint images. For low-quality fingerprint images, the preprocessing stage of an AFIS produces redundant minutiae or even destroys real minutiae. The minutiae detection algorithms in direct gray-scale domain have been developed to overcome these problems. The first step of gray-scale minutiae detection algorithm is to determine ridge locations and then perform gray-scale ridge line following algorithm to extract minutiae. However, the existing gray-scale minutiae detection techniques can only work on partial fingerprint images due to the ignorance of image background. Moreover, the gray value variation inside a ridge also generates redundant ridge points. In this dissertation, we propose a novel method, based on gray-level histogram decomposition, to locate the ridge points in complete fingerprint images. By decomposing the gray-level histogram, redundant ridge points can be eliminated according to some statistical parameters. Experimental results demonstrate that the correct rate can be over 96% even applied to poor-quality fingerprint images. For automatic fingerprint classification problem, a novel method is introduced which is a combination of structural and syntactic approaches. The goal of the proposed Ridge Distribution (R-D) Model is to present the idea of the possibility for classifying a fingerprint into the complete seven classes in the Henry''s classification. From our observation, there exist only ten basic ridge patterns which construct fingerprints. Fingerprint classes can be interpreted as a combination of these ten ridge patterns with different ridge distribution sequences. In this thesis, the classification task is performed depending on the global distribution of the ten basic ridge patterns by analyzing the ridge shapes and the sequence of ridges distribution. The regular expression for each class is formulated and a NFA model is constructed accordingly. An explicit rejection criterion is also defined in this thesis. For the seven-class fingerprint classification problem, our method can achieve the classification accuracy of 93.4% with 5.1% rejection rate. For the five-class problem, the accuracy rate of 94.8% is achieved. Experimental results reveal the feasibility and validity of the proposed approach in fingerprint classification.
30
Yi, Hung Ming, and 洪銘曎. "Blur detection for fingerprint classification based on gradient and SVD." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/39075506475585587790.
Full textAbstract:
碩士國立高雄應用科技大學
光電與通訊研究所
99
Automatic fingerprint classification is nowadays one of the most important and reliable biometric technologies. This is because of the fingerprint distinctiveness, persistence, ease of acquisition, and high matching accuracy rates. However, the performance of classification relies heavily on the quality of the input fingerprint images. Due to various factors such as skin conditions, e.g. dry, wet, cuts, scars, and bruises, non-uniform finger pressure, noise introduced by sensor and inherently poor-quality fingers, e.g. manual workers and elders, a significant percentage of fingerprint images is of poor quality. In fact, a single fingerprint may contain regions with quality of good, medium, and blur. Thus an enhanced method which can mend the ridge structure of a blur region is necessary. In this thesis, we propose an effective algorithm for fingerprint image patch, which can much improve the clarity and continuity of ridge structures based on the novel mutual-lighting SVD compensation with blur region detection. The algorithm consists of two stages. The first stage extracts the blur region using wavelet entropy filtering with region growing. The second stage yields the patched image by doing lighting compensation mutually for the dark and light regions based on the image mean. Experimental results for NIST-4 and FVC databases show that the patched image quality is much better than the other existing methods for improving singular point detection and fingerprint classification.
31
Wu, Cheng-Jung, and 吳振榮. "Dry and Wet Fingerprint Classification Using Ridge Features for Multiple Resolutions." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/csv265.
Full text
32
Le, Ngoc Tuyen, and 黎玉線. "Image Enhancement Using Adaptive Singular Value Decomposition for Face Recognition and Fingerprint Classification." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/88627310951461650212.
Full textAbstract:
博士國立高雄應用科技大學
電子工程系碩士班
103
The development of face recognition and fingerprint classification systems in real world still remains a major challenge for the scientific researchers. One of the most crucial reasons affecting the efficiency of these systems is the quality of the input image. To improve the quality of images in pre-processing step, this dissertation applies the useful properties of the singular value decomposition in image processing to improve quality of the color face and fingerprint images. For face recognition, this study proposes three methods to enhance color face images. First, we propose the innovative illumination compensation algorithm, two separated singular value decomposition, in the spatial domain. Second, we introduce an efficient brightness detector for lighting detection and an illumination compensation method, adaptive singular value decomposition in the two-dimensional discrete Fourier domain. Third, we propose a novel illumination compensation method called adaptive singular value decomposition in the 2D discrete wavelet domain. These methods can resolve the illumination variation problem on color face images when there is insufficient light and, at the same time, improve the effective of recognition system. Fingerprint image enhancement is one of the most major steps in an automated fingerprint identification system. In this study, an effective algorithm for fingerprint image quality improvement is proposed. The algorithm consists of two stages. The first stage is decomposing the input fingerprint image into four subbands by applying two-dimensional discrete wavelet transform. At the second stage, the compensated image is produced by adaptively obtaining the compensation coefficient for each subband based on the image content and the referred Gaussian template. The experimental results indicated the efficiency of the proposed method.
33
Mieloch, Krzysztof. "Hierarchically linked extended features for fingerprint processing." Doctoral thesis, 2008. http://hdl.handle.net/11858/00-1735-0000-0006-B3BC-A.
Full text