Jamal Ahmad Dargham

Iris recognition using self-organizing neural network

Among biometric systems for user verification, iris recognition systems represent a relatively new technology. Our system consists of two main parts: a localizing iris and iris pattern recognition. The raw image is captured using a digital camera. The iris is then extracted from the background after enhancement and noise elimination. Due to noise and the high degree of freedom in the iris pattern, only parts of the iris structure are selected for recognition. The selected iris structure is then reconstructed into a rectangle format. Using a trained self-organizing map neural network, iris patterns are recognized. The overall accuracy of our network is found to be about 83%.

Lip detection by the use of neural networks

Lip detection is used in many applications such as face detection and lip reading. In this article, a method for lip detection in color images in a normalized RGB color scheme is presented. In this method, MLP neural networks are used to perform lip detection on segmented skin regions. Several combinations of chrominance components of the normalized RGB color space were used as the input to the neural networks. Two methods were used for obtaining the normalized RGB components from the RGB color scheme. These are called the maximum and intensity normalization methods, respectively. The method was tested on two Asian databases. The number of neurons in the hidden layer was determined by using a modified network-growing algorithm. It was found that the pixel intensity normalization method gave lower lip detection error than the maximum intensity normalization method regardless of the database used, and for most of the combinations of chrominance components. In addition, the combination of the g and r/g chrominance components gave the lowest lip detection error when the pixel intensity normalization method was used for both databases. The effects of the scale and facial expression on lip detection was also studied. It was found that the lip detection error decreased as the scale factor increased. As for facial expression, a laughing facial expression gave the highest lip detection error, followed by smiling and neutral expressions.

Fingerprint identification and recognition using backpropagation neural network

Biometrics is a technology which identifies a person based on his physiology or behavioral characteristics. Fingerprint identification and recognition is a biometrics method that has been widely used in various applications because of its reliability and accuracy in the process of recognizing and verifying a persons identity. The main purpose of this paper is to develop a fingerprint identification and recognition system. The system consists of three main parts, image acquisition, processing and identification and recognition. Fingerprint images are acquired and stored in the database in the image acquisition stage. These images are then enhanced in the image processing stage by performing gray level enhancement, spatial filtering, image sharpening, edge detection, segmentation, and thinning processes. After the image has been processed, it is fed into the backpropagation neural network as input in order to train the network. After training, the neural network is ready to perform the identification and recognition operations (matching process). A neural network has been successfully developed to identify and recognize the core part of fingerprint images.

Data fusion for skin detection

Two methods of data fusion to improve the performance of skin detection were tested. The first method fuses two chrominance components from the same color space, while the second method fuses the outputs of two skin detection methods each based on a different color space. The color spaces used are the normalized red, green, blue (RGB) color space, referred to here as pixel intensity normalization, and a new method of obtaining the R, G, and B components of the normalized RGB color space called maximum intensity normalization. The multilayer perceptron (MLP) neural network and histogram thresholding were used for skin detection. It was found that fusion of two chrominance components gives a lower skin detection error than a single chrominance component regardless of the database or the color space for both skin detection methods. In addition, the fusion of the outputs of two skin detection methods further reduces the skin detection error.

A direct assessment method of the achievement of the program outcomes from the courses outcomes

The achievement of the program outcomes (POs) is very important for engineering institutions who have adopted Outcome Based Education (OBE). Generally, program outcomes assessment methods can be divided into direct and indirect methods. Direct methods are generally based on grades obtained from examination or project works while indirect methods are based on perception obtained from surveys, questionnaires and observations. In this paper, a direct assessment method is proposed whereby the assessment of the achievement of the program outcomes is based on the marks obtained by students in the final exam. There are three main advantages of the system. First, the relationship between the program outcomes and courses outcomes is based on Set Theory and therefore the use of the weight matrix, used in most assessment systems, is not necessary. Second, the system can deal with courses outcomes of all learning domains by converting marks into rubric scale. Thirdly, the system can assess the performance of the cohort as well as the individual graduates.

Radon transform for face recognition

Face recognition is an important biometric because of its potential applications in many fields such as access control, surveillance, and human-computer interactions. In this article, an investigation of the effect of the step size for both the angle and the vector of the Radon transform on the performance of a face recognition system based on principal component analysis (PCA) and Euclidean distance is carried out. It was found that changing the vector or the angle step size affects the performance of the system. However, the best equal error rate is achieved when the step size for both angle and vector is set to 1.

Analysis of Surface Electromyography for On-Off Control

Myogram on-and-off controller is important for improving or assisting the elderly people. One of the most important aspects of the controller development is to determine the on and off time with respect to the body movement. In this project, high accuracy signal filtering, high gain amplifier, signal converter, microcontroller and electrodes are used for circuit simulation and development to obtain muscle signal (Electromyogram). Precision rectifier is used to solve the ordinary semiconductor problem to avoid signal block. To ensurethe user-friendliness in the development of this device, non-invasive electrodes are used in this project instead of invasive electrodes.

Hybrid Component-Based Face Recognition System

Face recognition system is a fast growing research field because of its potential as an eminent tool for security surveillance, human-computer interaction, identification declaration and other applications. Face recognition techniques can be categorized into 3 categories namely holistic approach, feature-based approach, and hybrid approach. In this paper, a hybrid component-based system is proposed. Linear discriminant analysis (LDA) is used to extract the feature from each component. The outputs from the individual components are then combined to give the final recognition output. Two methods are used to obtain the components, namely the facial landmarks and the sub-images. It was found out that the fusion of the components does improve the recognition rate compared to individual results of each component. From the sub-image method, it can be seen that as the size of the components get smaller, the recognition rate tends increase but not always.

Fusing Facial Features for Face Recognition

Face recognition is an important biometric method because of its potential applications in many fields, such as access control, surveillance, and human-computer interaction. In this paper, a face recognition system that fuses the outputs of three face recognition systems based on Gabor jets is presented. The first system uses the magnitude of the, the second uses the phase, and the third uses the magnitude with phase of the jets. The jets are generated from facial landmarks selected using three selection methods. It was found out that fusing the facial features gives better recognition rate than either facial feature used individually regardless of the landmark selection method.

Linking program outcomes to the courses outcomes: A top-down approach

In outcome-based education (OBE), the achievement of the program outcomes is very important as it is the yardstick by which the program achievement is measured. However, the program outcomes can only be achieved if they are properly linked to the courses outcomes. In this paper, a top-down approach that links the program outcomes to the courses outcomes is presented. The approach is based on analysis of set theory between the program and the courses outcomes sets. It also examines the level of details that can be used when linking the program and the courses outcomes. The main features of this approach are: Each program outcome is analyzed to determine the components that make that outcome. Each course or course outcome can only contribute to one program outcome thus, eliminating the need for the weights matrix. In addition, this approach ensures that all the program outcomes can be measured by appropriately linking them or embedding them in the appropriate courses or courses outcomes. This method has an added advantage whereby the outcomes for a given course can be evaluated in terms of their contribution to the program outcome.