Ultrasonography is widely used in medical diagnosis with the advantages of being low cost, non-invasive and capable of real time imaging. When interpreting ultrasonographic images of mammalian ovaries, the structures of interest are follicles, corpora lutea (CL) and stroma. This thesis presents an approach to perform CL texture analysis, including detection and segmentation, based on the classiers trained by genetic programming (GP). The objective of CL detection is to determine whether there is a CL in the ovarian images, while the goal of segmentation is to localize the CL within the image. Genetic programming (GP) oers a solution through the evolution of computer programs by methods inspired by the mechanisms of natural selection. Herein, we use rotationally invariant local binary patterns (LBP) to encode the local texture features. These are used by the programs which are manipulated by GP to obtain highly t CL classiers. Grayscale standardization was performed on all images in our data set based on the reference grayscale in each image. CL classication programs were evolved by genetic programming and tested on ultrasonographic images of ovaries. On the bovine dataset, our CL detection algorithm is reliable and robust. The detection algorithm correctly determined the presence or absence of a CL in 93.3% of 60 test images. The segmentation algorithm achieved a mean ( standard deviation) sensitivity and specicity of 0.87 (0.14) and 0.91 (0.05), respectively, over the 30 CL images. Our CL segmentation algorithm is an improvement over the only previously published algorithm, since our method is fully automatic and does not require the placement of an initial contour. The success of these algorithms demonstrates that similar algorithms designed for analysis of in vivo human ovaries are likely viable.

Ultrasonography is widely used in medical diagnosis with the advantages of being low cost, non-invasive and capable of real time imaging. When interpreting ultrasonographic images of mammalian ovaries, the structures of interest are follicles, corpora lutea (CL) and stroma. This thesis presents an approach to perform CL texture analysis, including detection and segmentation, based on the classiers trained by genetic programming (GP). The objective of CL detection is to determine whether there is a CL in the ovarian images, while the goal of segmentation is to localize the CL within the image. Genetic programming (GP) oers a solution through the evolution of computer programs by methods inspired by the mechanisms of natural selection. Herein, we use rotationally invariant local binary patterns (LBP) to encode the local texture features. These are used by the programs which are manipulated by GP to obtain highly t CL classiers. Grayscale standardization was performed on all images in our data set based on the reference grayscale in each image. CL classication programs were evolved by genetic programming and tested on ultrasonographic images of ovaries. On the bovine dataset, our CL detection algorithm is reliable and robust. The detection algorithm correctly determined the presence or absence of a CL in 93.3% of 60 test images. The segmentation algorithm achieved a mean ( standard deviation) sensitivity and specicity of 0.87 (0.14) and 0.91 (0.05), respectively, over the 30 CL images. Our CL segmentation algorithm is an improvement over the only previously published algorithm, since our method is fully automatic and does not require the placement of an initial contour. The success of these algorithms demonstrates that similar algorithms designed for analysis of in vivo human ovaries are likely viable.

Magister Scientiae - MSc (Computer Science) / A machine translation system that can convert South African Sign Language (SASL) video to audio or text and vice versa would be bene cial to people who use SASL to communicate. Five fundamental parameters are associated with sign language gestures, these are: hand location; hand orientation; hand shape; hand movement and facial expressions. The aim of this research is to recognise facial expressions and to compare both feature descriptors and machine learning techniques. This research used the Design Science Research (DSR) methodology. A DSR artefact was built which consisted of two phases. The rst phase compared local binary patterns (LBP), compound local binary patterns (CLBP) and histogram of oriented gradients (HOG) using support vector machines (SVM). The second phase compared the SVM to arti cial neural networks (ANN) and random forests (RF) using the most promising feature descriptor|HOG|from the rst phase. The performance was evaluated in terms of accuracy, robustness to classes, robustness to subjects and ability to generalise on both the Binghamton University 3D facial expression (BU-3DFE) and Cohn Kanade (CK) datasets. The evaluation rst phase showed HOG to be the best feature descriptor followed by CLBP and LBP. The second showed ANN to be the best choice of machine learning technique closely followed by the SVM and RF.

Various hand-crafted features have been explored for medical image classification, which include SIFT and Local Binary Patterns (LBP). However, hand-crafted features may not be optimally discriminative for classifying images from particular domains (e.g. colonoscopy), as not necessarily tuned to the domain’s characteristics. In this work, I give emphasis on learning highly discriminative local features and image representations to achieve the best possible classification performance for medical images, particularly for colonoscopy and histology (cell) images. I propose approaches to learn local features using unsupervised and weakly-supervised methods, and an approach to improve the feature encoding methods such as bag-of-words. Unlike the existing work, the proposed weakly-supervised approach uses image-level labels to learn the local features. Requiring image-labels instead of region-level labels makes annotations less expensive, and closer to the data normally available from normal clinical practice, hence more feasible in practice. In this thesis, first, I propose a generalised version of the LBP descriptor called the Generalised Local Ternary Patterns (gLTP), which is inspired by the success of LBP and its variants for colonoscopy image classification. gLTP is robust to both noise and illumination changes, and I demonstrate its competitive performance compared to the best performing LBP-based descriptors on two different datasets (colonoscopy and histology). However LBP-based descriptors (including gLTP) lose information due to the binarisation step involved in their construction. Therefore, I then propose a descriptor called the Extended Multi-Resolution Local Patterns (xMRLP), which is real-valued and reduces information loss. I propose unsupervised and weakly-supervised learning approaches to learn the set of parameters in xMRLP. I show that the learned descriptors give competitive or better performance compared to other descriptors such as root-SIFT and Random Projections. Finally, I propose an approach to improve feature encoding methods. The approach captures inter-cluster features, providing context information in the feature as well as in the image spaces, in addition to the intra-cluster features often captured by conventional feature encoding approaches. The proposed approaches have been evaluated on three datasets, 2-class colonoscopy (2, 100 images), 3-class colonoscopy (2, 800 images) and histology (public dataset, containing 13, 596 images). Some experiments on radiology images (IRMA dataset, public) also were given. I show state-of-the-art or superior classification performance on colonoscopy and histology datasets.

Shape description is an important problem in computer vision because most vision tasks that require comparing or matching visual entities rely on shape descriptors. In this thesis, two novel shape descriptors are proposed, namely Intersection Consistency Histogram (ICH) and Global Binary Patterns (GBP). The former is based on a local regularity measure called Intersection Consistency (IC), which determines whether edge pixels in an image patch point towards the center or not. The second method, called Global Binary Patterns, represents the shape in binary along horizontal, vertical, diagonal or principal directions. These two methods are extensively analyzed on several databases, and retrieval and running time performances are presented. Moreover, these methods are compared with methods such as Shape Context, Histograms of Oriented Gradients, Local Binary Patterns and Fourier Descriptors. We report that our descriptors perform comparable to these methods.

Automated facial expression analysis for Emotion Recognition (ER) is an active research area towards creating socially intelligent systems. The eye region, often considered integral for ER by psychologists and neuroscientists, has received very little attention in engineering and computer sciences. Using eye region as an input signal presents several bene ts for low-cost, non-intrusive ER applications. This work proposes two frameworks towards ER from eye region images. The first framework uses Local Binary Patterns (LBP) as the feature extractor on grayscale eye region images. The results validate the eye region as a signi cant contributor towards communicating the emotion in the face by achieving high person-dependent accuracy. The system is also able to generalize well across di erent environment conditions. In the second proposed framework, a color-based approach to ER from the eye region is explored using Local Color Vector Binary Patterns (LCVBP). LCVBP extend the traditional LBP by incorporating color information extracting a rich and a highly discriminative feature set, thereby providing promising results.

Automated facial expression analysis for Emotion Recognition (ER) is an active research area towards creating socially intelligent systems. The eye region, often considered integral for ER by psychologists and neuroscientists, has received very little attention in engineering and computer sciences. Using eye region as an input signal presents several bene ts for low-cost, non-intrusive ER applications. This work proposes two frameworks towards ER from eye region images. The first framework uses Local Binary Patterns (LBP) as the feature extractor on grayscale eye region images. The results validate the eye region as a signi cant contributor towards communicating the emotion in the face by achieving high person-dependent accuracy. The system is also able to generalize well across di erent environment conditions. In the second proposed framework, a color-based approach to ER from the eye region is explored using Local Color Vector Binary Patterns (LCVBP). LCVBP extend the traditional LBP by incorporating color information extracting a rich and a highly discriminative feature set, thereby providing promising results.

Face detection in video sequence is becoming popular in surveillance applications. The trade-off between obtaining discriminative features to achieve accurate detection versus computational overhead of extracting these features, which affects the classification speed, is a persistent problem. Two ideas are introduced to increase the features’ discriminative power. These ideas are used to implement two frontal face detectors examined on a 2D low-resolution surveillance sequence. First contribution is the parallel classifier. High discriminative power features are achieved by fusing the decision from two different features trained classifiers where each type of the features targets different image structure. Accurate and fast to train classifier is achieved. Co-occurrence of Local Binary Patterns (CoLBP) features is proposed, the pixels of the image are targeted. CoLBP features find the joint probability of multiple LBP features. These features have computationally efficient feature extraction and provide high discriminative features; hence, accurate detection is achieved.

Face detection in video sequence is becoming popular in surveillance applications. The trade-off between obtaining discriminative features to achieve accurate detection versus computational overhead of extracting these features, which affects the classification speed, is a persistent problem. Two ideas are introduced to increase the features’ discriminative power. These ideas are used to implement two frontal face detectors examined on a 2D low-resolution surveillance sequence. First contribution is the parallel classifier. High discriminative power features are achieved by fusing the decision from two different features trained classifiers where each type of the features targets different image structure. Accurate and fast to train classifier is achieved. Co-occurrence of Local Binary Patterns (CoLBP) features is proposed, the pixels of the image are targeted. CoLBP features find the joint probability of multiple LBP features. These features have computationally efficient feature extraction and provide high discriminative features; hence, accurate detection is achieved.

Recently, automatic demographic classification has found its way into embedded applications such as targeted advertising in mobile devices, and in-car warning systems for elderly drivers. In this thesis, we present a complete framework for video-based gender classification and age estimation which can perform accurately on embedded systems in real-time and under unconstrained conditions. We propose a segmental dimensionality reduction technique utilizing Enhanced Discriminant Analysis (EDA) to minimize the memory and computational requirements, and enable the implementation of these classifiers for resource-limited embedded systems which otherwise is not achievable using existing resource-intensive approaches. On a multi-resolution feature vector we have achieved up to 99.5% compression ratio for training data storage, and a maximum performance of 20 frames per second on an embedded Android platform. Also, we introduce several novel improvements such as face alignment using the nose, and an illumination normalization method for unconstrained environments using bilateral filtering. These improvements could help to suppress the textural noise, normalize the skin color, and rectify the face localization errors. A non-linear Support Vector Machine (SVM) classifier along with a discriminative demography-based classification strategy is exploited to improve both accuracy and performance of classification. We have performed several cross-database evaluations on different controlled and uncontrolled databases to assess the generalization capability of the classifiers. Our experiments demonstrated competitive accuracies compared to the resource-demanding state-of-the-art approaches.