Light Weight Structure Texture Feature Analysis for Character Recognition Using Progressive Stochastic Learning Algorithm
S. Rubin Bose, Raj Kumar Singh, Yashodaye Joshi, Ayush Marar, R. Regin, S. Suman Rajest
Abstract
Handwritten character recognition is a challenging task in the field of image processing and pattern recognition. The success of character recognition systems depends heavily on the feature extraction methods used to represent the character images. In this chapter, the authors propose a novel feature extraction method called progressive stochastic learning (PSL) algorithm. The proposed work is based on the texture and structural features of the character image and is designed to extract discriminative features that capture the essential information of the characters. The PSL algorithm is used to classify the extracted features into their respective character classes. Experimental results demonstrate that the proposed method achieves a recognition accuracy of 92.6% for correct characters predicted and 91.3% for correct words predicted. Moreover, the proposed method outperforms several state-of-the-art methods in terms of recognition accuracy, computation time, and memory requirements.