الفهرس | Only 14 pages are availabe for public view |
Abstract This thesis introduces two techniques for recognizing offline signatures. The first one presents an implementation for offline signature recognition using rough neural network. Rough neural network tries to find better recognition performance to classify the input offline signature images. Rough sets have provided an array of tools which turned out to be especially adequate for conceptualization, organization, classification and analysis of various types of data, when dealing with inexact, uncertain, or vague knowledge. Also, rough sets discover hidden pattern and regularities in application. The second technique presents a new combination between grid features as a good technique to correctly discriminate one class from the other and Rough Neural Network as a powerful classifier because of its Low classification error rate will overcome these weaknesses and solve the problem of recognizing a handwritten signature . The new combination determines the most core part in the signature images using small representative set of features. |