On the Performance Improvement of Devanagari Handwritten Character Recognition. (22nd February 2015)

• Record Type: Journal Article
• Authors: Singh, Pratibha; Verma, Ajay; Chaudhari, Narendra S.
• Other Names: Hsiao Ying-Tung Academic Editor.
• Is Part Of: Applied computational intelligence and soft computing. Volume 2015(2015)
• Publication Date: 2015-02-22
• Subjects: Computational intelligence -- Periodicals; Soft computing -- Periodicals; 006.305
• DOI: 10.1155/2015/193868
• Languages: English
• ISSNs: 1687-9724

Abstract

Abstract : The paper is about the application of mini minibatch stochastic gradient descent (SGD) based learning applied to Multilayer Perceptron in the domain of isolated Devanagari handwritten character/numeral recognition. This technique reduces the variance in the estimate of the gradient and often makes better use of the hierarchical memory organization in modern computers.L2 -weight decay is added on minibatch SGD to avoid overfitting. The experiments are conducted firstly on the direct pixel intensity values as features. After that, the experiments are performed on the proposed flexible zone based gradient feature extraction algorithm. The results are promising on most of the standard dataset of Devanagari characters/numerals.