WSEAS Transactions on Computers
Print ISSN: 1109-2750, E-ISSN: 2224-2880
Volume 14, 2015
Recognition of Handwritten Amazigh Characters Based on Zoning Methods and MLP
Authors: , ,
Abstract: The main purpose of this work is to develop an optical character recognition system (OCR) of handwritten Amazigh characters employing a feature set of 79 elements based on statistical methods. The feature set elaborated consists of 37 densities features and 42 shadow features basing on a specific zoning to represent the Amazigh characters; in the recognition phase, we use the multilayer perceptron (MLP) as classifier. The accuracy observed, experimentally, on a database of 24180 characters is 96,47%. The experimental evaluation performed on a large set of handwritten characters not only verifies that the proposed approach provides a very satisfactory recognition rate but also shows a reasonable time during the test phase.
Search Articles
Keywords: OCR, MLP, Handwritten Amazigh charcters, Statistical methods, Features extraction, Neural network
Pages: 178-185
WSEAS Transactions on Computers, ISSN / E-ISSN: 1109-2750 / 2224-2880, Volume 14, 2015, Art. #19