A Survey on Feature Extraction Methods for Handwritten Digits Recognition

ABSTRACT Hand written digit recognition is highly nonlinear problem. Recognition of handwritten numerals plays an active role in day to day life now days. Office automation, e-governors and many other areas, reading printed or handwritten documents and convert them to digital media is very crucial and time consuming task. So the system should be designed in such a way that it should be capable of reading handwritten numerals and provide appropriate response as humans do. However, handwritten digits are varying from person to person because each one has their own style of writing, means the same digit or character/word written by different writer will be different even in different languages. This paper presents survey on handwritten digit recognition systems with recent techniques, with three well known classifiers namely MLP, SVM and kNN used for classification. This paper presents comparative analysis that describes recent methods and helps to find future scope.

[1]  S. Himavathi,et al.  Diagonal Based Feature Extraction for Handwritten Alphabets Recognition System using Neural Network , 2011, ArXiv.

[2]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[3]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[4]  Edgar N. Sanchez,et al.  Advances in Computational Intelligence , 2009 .

[5]  Deepika Ahuja,et al.  A Novel Approach to Recognize the off-line Handwritten Numerals using MLP and SVM Classifiers , 2013 .

[6]  Renu Dhir,et al.  Comparative Recognition of Handwritten Gurmukhi Numerals Using Different Feature Sets and Classifiers , 2012 .

[7]  Lambert Schomaker,et al.  Handwritten Character Classification using the Hotspot Feature Extraction Technique , 2012, ICPRAM.

[8]  Lambert Schomaker,et al.  A Comparison of Feature and Pixel-Based Methods for Recognizing Handwritten Bangla Digits , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[9]  Nicole Vincent,et al.  A Set of Chain Code Based Features for Writer Recognition , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[10]  Abdel Belaïd,et al.  Water reservoir based approach for touching numeral segmentation , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[11]  U. Ravi Babu,et al.  Handwritten Digit Recognition Using K-Nearest Neighbour Classifier , 2014, 2014 World Congress on Computing and Communication Technologies.

[12]  David R. Musicant,et al.  Lagrangian Support Vector Machines , 2001, J. Mach. Learn. Res..