Biometric identification systems have several distinct advantages over other authentication technologies, such as passwords, in reliably recognising individuals. Iris based recognition is one such biometric recognition system. Unlike other biometrics such as fingerprints or face images, the distinct aspect of the iris comes from its randomly distributed features. The patterns of these randomly distributed features on the iris have been proved to be fixed in a person's lifetime, and are stable over time for healthy eyes except for the distortions caused by the constriction and dilation of the pupil. The distortion of the iris pattern caused by pupillary activity, which is mainly due changes in ambient lighting conditions, can be significant. One important question that arises from this is: How closely do two different iris images of the same person, taken at different times using different cameras, in different environments, and under different lighting conditions, agree with each other? It is also problematic for iris recognition systems to correctly identify a person when his/her pupil size is very different from the person's iris images, used at the time of constructing the system's data-base. To date, researchers in the field of iris recognition have made attempts to address this problem, with varying degrees of success. However, there is still a need to conduct in-depth investigations into this matter in order to arrive at more reliable solutions. It is therefore necessary to study the behaviour of iris surface deformation caused by the change of lighting conditions. In this thesis, a study of the physiological behaviour of pupil size variation under different normal indoor lighting conditions (100 lux ~ 1,200 lux) and brightness levels is presented. The thesis also presents the results of applying Elastic Graph Matching (EGM) tracking techniques to study the mechanisms of iris surface deformation. A study of the pupil size variation under different normal indoor lighting conditions was conducted. The study showed that the behaviour of the pupil size can be significantly different from one person to another under the same lighting conditions. There was no evidence from this study to show that the exact pupil sizes of an individual can be determined at a given illumination level. However, the range of pupil sizes can be estimated for a range of specific lighting conditions. The range of average pupil sizes under normal indoor lighting found was between 3 mm and 4 mm. One of the advantages of using EGM for iris surface deformation tracking is that it incorporates the benefit of the use of Gabor wavelets to encode the iris features for tracking. The tracking results showed that the radial stretch of the iris surface is nonlinear. However, the amount of extension of iris surface at any point on the iris during the stretch is approximately linear. The analyses of the tracking results also showed that the behaviour of iris surface deformation is different from one person to another. This implies that a generalised iris surface deformation model cannot be established for personal identification. However, a deformation model can be established for every individual based on their analysis result, which can be useful for personal verification using the iris. Therefore, analysis of the tracking results of each individual was used to model iris surface deformations for that individual. The model was able to estimate the movement of a point on the iris surface at a particular pupil size. This makes it possible to estimate and construct the 2D deformed iris image of a desired pupil size from a given iris image of another different pupil size. The estimated deformed iris images were compared with their actual images for similarity, using an intensitybased (zero mean normalised cross-correlation). The result shows that 86% of the comparisons have over 65% similarity between the estimated and actual iris image. Preliminary tests of the estimated deformed iris images using an open-source iris recognition algorithm have showed an improved personal verification performance. The studies presented in this thesis were conducted using a very small sample of iris images and therefore should not be generalised, before further investigations are conducted.

FundaÃÃo Cearense de Apoio ao Desenvolvimento Cientifico e TecnolÃgico / Esta tese introduz uma nova metodologia para determinar a direÃÃo do vento sobre a superfÃcie dos oceanos utilizando tÃcnicas de processamento das imagens de Radar de Abertura SintÃtica (SAR, do inglÃs Synthetic Aperture Radar). A literatura relacionada demonstra um crescente interesse no processamento dessas imagens para detecÃÃo de alvos, classificaÃÃo de regiÃes, extraÃÃo de campos de ventos, monitoramento de derrames de Ãleo, aplicaÃÃes geofÃsicas e meteorolÃgicas. A extraÃÃo de campos de ventos em imagens SAR à uma tarefa desafiadora devido à contaminaÃÃo das mesmas por um ruÃdo oriundo do sistema de aquisiÃÃo, denominado speckle, que dificulta tarefas de processamento e interpretaÃÃo das mesmas. Portanto, esta tese propÃe metodologias de extraÃÃo da direÃÃo do vento por transformada de Fourier, transformadas wavelets e mÃtodos baseados em textura. As transformadas wavelets utilizadas para esta tarefa sÃo Gabor, ChapÃu Mexicano e o algoritmo à trous. Com relaÃÃo à anÃlise de textura utilizada, esta se baseia na informaÃÃo espacial da matriz de co-ocorrÃncia dos nÃveis de cinza para estimar a direÃÃo de padrÃes lineares em imagens contaminadas com speckle. Os experimentos foram realizados em imagens de textura sintÃticas, imagens do Ãlbum de Brodatz e imagens SAR sintÃticas e reais. Foi observado que os mÃtodos propostos foram capazes de estimar direÃÃes de padrÃes lineares e extrair campos de streaks de vento visÃveis em imagens SAR reais. As principais contribuiÃÃes desta tese sÃo: o mÃtodo proposto para estimaÃÃo de direÃÃo de ventos na superfÃcie do oceano e a extensÃo de tÃcnica jà existente na literatura, possibilitando assim a estimaÃÃo da velocidade dos ventos na faixa de 4 a 10 m/s. Os melhores resultados obtidos nesta tese foram alcanÃados utilizando o mÃtodo proposto que combina transformada wavelet e anÃlise de textura. / This thesis introduces a new methodology to determine the wind direction over the ocean surface using image processing techniques on SAR (Synthetic Aperture Radar) images. Related literature demonstrates a growing interest in processing these images for target detection, region classification, wind field extraction, oil spill monitoring, geophysical and meteorological applications. Wind field extraction in SAR images is a challenging task due to contamination acquisition system by speckle noise, which makes difficult processing and interpretation tasks. Thus, this thesis proposes methods for wind direction estimation by applying image transforms, such as Fourier and wavelets and furthermore texture-based methods. The wavelet transforms used for this task are Gabor, Mexican Hat and the à trous algorithm. Concerning the texture approach, it is based on the co-occurrence matrix to estimate direction of linear patterns in speckled images. The experiments were performed on synthetic texture, Brodatz album, synthetic and real SAR images. It was observed that the proposed methods were able to estimate directions of linear patterns and extract wind fields from visible wind-induced streaks on SAR images. The main contributions of this thesis are: to propose methods for wind direction estimation on the ocean surface and to extend existing techniques in the literature in order to provide wind vector estimation in the range of 4 to 10 m/s. The best results of this tese were achieved with the proposed method that combines wavelet transform and texture analysis.

This thesis states that cracks and scars, referred to as Secondary Creases, in fingerprint images can be used as means for aiding and complementing fingerprint recognition, especially in cases where there is not enough clear data to use traditional methods such as minutiae based or correlation techniques. A Gabor filter bank is used to extract areas with linear patterns, where after the Hough Transform is used to identify secondary creases in a r, theta space. The methods proposed for Secondary Crease extraction works well, and provides information about what areas in an image contains usable linear pattern. Methods for comparison is however not as robust, and generates False Rejection Rate at 30% and False Acceptance Rate at 20% on the proposed dataset that consists of bad quality fingerprints. In short, our methods still makes it possible to make use of fingerprint images earlier considered unusable in fingerprint recognition systems.

Magister Scientiae - MSc / We investigate the use of noise degraded facial images in the application of facial expression recognition. In particular, we trained Gabor+SVMclassifiers to recognize facial expressions images with various types of noise. We applied Gaussian noise, Poisson noise, varying levels of salt and pepper noise, and speckle noise to noiseless facial images. Classifiers were trained with images without noise and then tested on the images with noise. Next, the classifiers were trained using images with noise, and then on tested both images that had noise, and images that were noiseless. Finally, classifiers were tested on images while increasing the levels of salt and pepper in the test set. Our results reflected distinct degradation of recognition accuracy. We also discovered that certain types of noise, particularly Gaussian and Poisson noise, boost recognition rates to levels greater than would be achieved by normal, noiseless images. We attribute this effect to the Gaussian envelope component of Gabor filters being sympathetic to Gaussian-like noise, which is similar in variance to that of the Gabor filters. Finally, using linear regression, we mapped a mathematical model to this degradation and used it to suggest how recognition rates would degrade further should more noise be added to the images. / South Africa

The primary goal of this dissertation is to develop point-based rigid and non-rigid image registration methods that have better accuracy than existing methods. We first present point-based PoIRe, which provides the framework for point-based global rigid registrations. It allows a choice of different search strategies including (a) branch-and-bound, (b) probabilistic hill-climbing, and (c) a novel hybrid method that takes advantage of the best characteristics of the other two methods. We use a robust similarity measure that is insensitive to noise, which is often introduced during feature extraction. We show the robustness of PoIRe using it to register images obtained with an electronic portal imaging device (EPID), which have large amounts of scatter and low contrast. To evaluate PoIRe we used (a) simulated images and (b) images with fiducial markers; PoIRe was extensively tested with 2D EPID images and images generated by 3D Computer Tomography (CT) and Magnetic Resonance (MR) images. PoIRe was also evaluated using benchmark data sets from the blind retrospective evaluation project (RIRE). We show that PoIRe is better than existing methods such as Iterative Closest Point (ICP) and methods based on mutual information. We also present a novel point-based local non-rigid shape registration algorithm. We extend the robust similarity measure used in PoIRe to non-rigid registrations adapting it to a free form deformation (FFD) model and making it robust to local minima, which is a drawback common to existing non-rigid point-based methods. For non-rigid registrations we show that it performs better than existing methods and that is less sensitive to starting conditions. We test our non-rigid registration method using available benchmark data sets for shape registration. Finally, we also explore the extraction of features invariant to changes in perspective and illumination, and explore how they can help improve the accuracy of multi-modal registration. For multimodal registration of EPID-DRR images we present a method based on a local descriptor defined by a vector of complex responses to a circular Gabor filter.

The aim of this master thesis is generating new "atoms'' for purposes of overcomplete signal representation for toolbox Frames in MATLAB. At first is described the principle of overcomplete systems and so-called frames. In the thesis is introduced the basic distribution of frames and conditions of their constructions. There is described the basic principle of finding the sparse solutions in overcomplete systems too. The main part is dealt with construction single functions for generating "atoms'', such as: Gabor function, B-splines, Bézier curves, Daubechies wavelets, etc. At last there is introduced an example of usage these functions for reconstruction signal in comparison with Fourier and wavelet transforms.

Fingerprints are the oldest and most used form of biometric identification. A critical step is reliable extract minutiae from the fingerprint images. However fingerprint images are rarely of perfect quality, they may be degraded and corrupted due to natural variations in skin and sensing conditions. Thus, image enhancement techniques are necessary prior to minutiae extraction. This work includes implementation of three techniques for fingerprint image enhancement, minutiae extraction and consturction of fingerprint reading device. Experiments are realized with two sets of fingerprints to evaluate the performance of implemented techniques.

This diploma thesis deals with the identification of persons by their fingerprints. In the beginning, there is a brief overview of biometric methods. The issue of fingerprints and their automatic processing is very extensive and addresses a large amount of literature. This work describes the various stages processing fingerprints from receiving a fingerprint scan through the methods of enhancing fingerprint, binarization, the detection of minutiae to compare two fingerprints. After a short introduction of biometric techniques is briefly introduced the history of fingerprints as an instrument for identification of persons. Subsequently, there is the description of problems of obtaining fingerprints from older methods that require the transmission medium, to methods of obtaining fingerprints directly into a digital format. There are described basic principles of sensors and the principle of their function. Next part deals with methods of processing digital fingerprint images. These are methods for fingerprint image enhancement, methods for image thresholding, thinning of ridge lines, detection of global and local characteristics of the fingerprint. The next section introduces the basic methods of comparison and classification of fingerprints. The practical part describes the specific implementation of fingerprint processing chain. For each processing stage is implemented one selected method. The result is an application that allows displaying the output of each phase, the comparison of fingerprints 1:1 and also finds a fingerprint in the database, by comparing one fingerprint with many.

Ultrasound imaging is widely used in medical examination. However, the interpretation of images is not trivial and requires much experience. In this thesis, various techniques for enhancement of visual quality of ultrasound images are presented. Several basic and advanced methods that may simplify the visual diagnosis are described. Finally, an interactive application is designed and implemented for simple usage of presented methods.

This paper deals with application of neural networks in image segmentation. First part is an introduction to image processing and neural networks, second part describes an implementation of segmentation system and presents results of experiments. The segmentation system enables to use different types of classifiers, various image features extraction and also to evaluate the success of segmentation. Two classifiers were created - a neural network (self-organizing map) and an algorithm K-means. Colour (RGB and HSV) and texture features and their combinations were used for classification. Texture features were extracted using a set of Gabor filters. Experiments with designed classifiers and feature extractors were carried out and results were compared.