الفهرس | Only 14 pages are availabe for public view |
Abstract Artificial Neural Networks have broad applications to the real world business problems. They have already been successfully applied in many industries. Since neural networks are best at identifying patterns or trends in data, they are well suited for prediction or forecasting. These include Sales forecasting, Industrial process control, Customer research, Data validation, Risk management, Target marketing. The thesis studies the use of Artificial Neural Network in the field of Image Processing. One of the applications studied is the edge detection process. Edge detection of an image significantly reduces the amount of data and filters out useless information, while preserving the important structural properties in an image. Edges detection of digital images is used in a various fields of applications ranging from real-time video surveillance and traffic management to medical imaging applications. Thesis demonstrates both entropy and Neural Network based edge detection methods, where Renyi’s Entropy and Convolutional Neural Network based edge detection is proposed and their results are compared. Thesis presents another application of Artificial Neural Network, An identification system using eye detection based on Wavelets and Neural Networks, for recognizing humans using their eyes as a biometric identity. The system is first trained to learn how to identify each eye and generate a unique identity for each eye, and then the person is recognized when his eye identity matches the previously defined one. The identification system proposed is efficient and robust against different image conditions. Thesis consists mainly of six chapters as follows: Chapter one presents the motivation behind this thesis, and defined the fundamental problem considered with real applications. It also summarized the contributions made toward this problem. Chapter two contains general concepts about Artificial Neural Network and its history, architecture and applications. Chapter three discusses a new proposed Renyi’s entropy algorithm for edge detection in level images and presenting the algorithm and simulation results Chapter four presents a new technique including the Implementation of Convolutional Neural Network, applying it for edge detection, experiment discussion, simulation results and a full comparison between Renyi’s Entropy edge detection and Convolutional Neural Network based edge detection. Chapter five studies Biometric Technology, Introduces eye as a perfect ID, how to use discrete Wavelet transform and Artificial Neural Network to eye extraction and recognition then discusses proposed identification system, finally the experiment discussion, performance and simulation results. In chapter six we present the summary, conclusion of our thesis and future work. |