Business Commons^™

Visual Pattern Recognition Using Neural Networks, Jenlong Moh

Dissertations

Neural networks have been widely studied in a number of fields, such as neural architectures, neurobiology, statistics of neural network and pattern classification. In the field of pattern classification, neural network models are applied on numerous applications, for instance, character recognition, speech recognition, and object recognition. Among these, character recognition is commonly used to illustrate the feature and classification characteristics of neural networks.

In this dissertation, the theoretical foundations of artificial neural networks are first reviewed and existing neural models are studied. The Adaptive Resonance Theory (ART) model is improved to achieve more reasonable classification results. Experiments in applying the …

Design And Implementation Of Two Text Recognition Algorithms, Madhumathi Yendamuri

Theses

This report presents two algorithms for text recognition. One is a neural-based orthogonal vector with pseudo-inverse approach for pattern recognition. A method to generate N orthogonal vectors for an N-neuron network is also presented. This approach converges the input to the corresponding orthogonal vector representing the prototype vector. This approach can restore an image to the original image and thus has error recovery capacility. Also, the concept of sub-networking is applied to this approach to enhance the memory capacity of the neural network. This concept drastically increases the memory capacity of the network and also causes a reduction of the …

Searching For Orthogonal States Of Neural Networks, Heng Wang

Theses

Two approaches to find orthogonal states of neural network are presented in the paper. The first approach is a recursive one, it builds N orthogonal vectors based on N /2 orthogonal vectors. The second approach is a formula approach, in which orthogonal vectors can be obtained using a formula. Using these approaches, orthogonal states of neural network are found. Some properties of the neural network built on these orthogonal vectors are presented in Appendix A and some examples are given in Appendix B.

The Performance Of Training Pattern Sets In A New Art-Based Neural Architecture For Image Enhancement, Fu-Chun Chang

Theses

Neural network can be applied on the image enhancement after adding another two layers into the Adaptive Resonance Theory architectures (ART 1). The analysis for selecting a nice training pattern set associate the appropriate vigilance values is the main concerns in this thesis. For a single training pattern ,the network can act as a mathematical morphology operators such as erosion , dilation, opening and closing. With more than one training patterns in the network, 16 experiments are tested and are compared to each other in order to find the best selection for doing the image enhancement work. With both the …