WSEAS Transactions on Systems and Control
Print ISSN: 1991-8763, E-ISSN: 2224-2856
Volume 10, 2015
Recognition System of Handwriten Craft Motive Using Based Feature Extraction and Neural Network
Authors: Khalid Fardousse, Hassan Qjidaa
Abstract: In this paper, a diagonal feature extraction scheme for the recognizing an off-line handwritten motive is presented. In the feature extraction process, resized individual images motives of our base of the models “handwritten motives of crafts” of size 100x60 pixels is further divided into 60 equal zones, each of size 10x10 pixels. The features are extracted from the pixels of each zone by moving along their diagonals. This procedure is repeated for all the zones leading to extraction of 60 features for each basic image motives. These extracted features are used to train a feed forward back propagation neural network employed for performing classification and recognition tasks. Extensive simulation studies show that the recognition system using diagonal features provides good recognition accuracy while requiring less time for training.
Search Articles
Keywords: Feature extraction, recognition, neural networks, Image processing, handwritten Craft motives
Pages: 415-420
WSEAS Transactions on Systems and Control, ISSN / E-ISSN: 1991-8763 / 2224-2856, Volume 10, 2015, Art. #44