![](/images/graphics-bg.png)
On the Performance Improvement of Devanagari Handwritten Character Recognition
Joint Authors
Singh, Pratibha
Verma, Ajay
Chaudhari, Narendra S.
Source
Applied Computational Intelligence and Soft Computing
Issue
Vol. 2015, Issue 2015 (31 Dec. 2015), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2015-02-22
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Information Technology and Computer Science
Abstract EN
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.
American Psychological Association (APA)
Singh, Pratibha& Verma, Ajay& Chaudhari, Narendra S.. 2015. On the Performance Improvement of Devanagari Handwritten Character Recognition. Applied Computational Intelligence and Soft Computing،Vol. 2015, no. 2015, pp.1-12.
https://search.emarefa.net/detail/BIM-1052212
Modern Language Association (MLA)
Singh, Pratibha…[et al.]. On the Performance Improvement of Devanagari Handwritten Character Recognition. Applied Computational Intelligence and Soft Computing No. 2015 (2015), pp.1-12.
https://search.emarefa.net/detail/BIM-1052212
American Medical Association (AMA)
Singh, Pratibha& Verma, Ajay& Chaudhari, Narendra S.. On the Performance Improvement of Devanagari Handwritten Character Recognition. Applied Computational Intelligence and Soft Computing. 2015. Vol. 2015, no. 2015, pp.1-12.
https://search.emarefa.net/detail/BIM-1052212
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1052212