Farsi digit recognition via features extraction

International Journal of Physical Sciences

Mehdi Alirezanejad¹ 

关键词: Features extraction;    recognition of Persian numbers;    perceptron neural network;    standard deviance;    average angle.;   

DOI  :  10.5897/IJPS11.298

学科分类：物理（综合）

来源: Academic Journals

【 摘 要 】

In this paper, a new method is proposed to extract the features of a one-numberPersian image in which for the final verification of the extracted features, a three-layer neural network (mesh) of Perceptron has been utilized. The method is capable of extracting some ideal features from a one-number image that are stable against rotation, movement, size change and noise. The method is examined on a database of 60000 discredited numbers, from which 40000 numbers were used in the training stage and 20000 ones were used for the experiment. The recognition percentage of 92.7% shows the great efficiency of the proposed method.

【 授权许可】

CC BY