Recognition of handwritten Amazigh characters based on zoning methods and MLP

摘要

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.