%0 Journal Article %1 noauthororeditor %A VenkateswaraRao, %D 2011 %J International Journal of Computer Science, Engineering and Applications (IJCSEA) %K algorithms networks %N 05 %P 47-56 %R 10.5121/ijcsea.2011.1505 %T AN EFFICIENT FEATURE EXTRACTION AND CLASSIFICATION OF HANDWRITTEN DIGITS USING NEURAL NETWORKS %U http://airccse.org/journal/ijcsea/papers/1011ijcsea05.pdf %V 01 %X The wide range of shape variations for handwritten digits requires an adequate representation of thediscriminating features for classification. For the recognition of characters or numerals requires pixel valuesof a normalized raster image and proper features to reach very good classification rate. This paper primarily concerns the problem of isolated handwritten numeral recognition of English scripts.Multilayer Perceptron(MLP) classifier is used for classification. The principalcontributions presented here are preprocessing, feature extraction and multilayer perceptron (MLP) classifiers.The strength of our approach is efficient feature extraction and the comprehensive classification scheme due to which, we have been able to achieve a recognition rate of 95.6, better than the previous approaches.

@article{noauthororeditor, abstract = {The wide range of shape variations for handwritten digits requires an adequate representation of thediscriminating features for classification. For the recognition of characters or numerals requires pixel valuesof a normalized raster image and proper features to reach very good classification rate. This paper primarily concerns the problem of isolated handwritten numeral recognition of English scripts.Multilayer Perceptron(MLP) classifier is used for classification. The principalcontributions presented here are preprocessing, feature extraction and multilayer perceptron (MLP) classifiers.The strength of our approach is efficient feature extraction and the comprehensive classification scheme due to which, we have been able to achieve a recognition rate of 95.6, better than the previous approaches.}, added-at = {2018-05-21T09:33:23.000+0200}, author = {VenkateswaraRao}, biburl = {https://www.bibsonomy.org/bibtex/25661c2b3bbe6d2b1f2a357ec87ade9c8/ijcsea}, doi = {10.5121/ijcsea.2011.1505}, interhash = {981295add5bfed527a3d71f96a34f8a0}, intrahash = {5661c2b3bbe6d2b1f2a357ec87ade9c8}, issn = {2230-9616}, journal = {International Journal of Computer Science, Engineering and Applications (IJCSEA)}, keywords = {algorithms networks}, month = {October}, number = 05, pages = {47-56}, timestamp = {2018-05-21T09:33:23.000+0200}, title = {AN EFFICIENT FEATURE EXTRACTION AND CLASSIFICATION OF HANDWRITTEN DIGITS USING NEURAL NETWORKS}, url = {http://airccse.org/journal/ijcsea/papers/1011ijcsea05.pdf}, volume = 01, year = 2011 }