Grouping of handwritten Bangla basic characters, numerals and vowel modifiers for multilayer classification
Date
2012Publisher
© 2012 Institute of Electrical and Electronics Engineers Inc.Metadata
Show full item recordCitation
Reza, K. N., & Khan, M. (2012). Grouping of handwritten bangla basic characters, numerals and vowel modifiers for multilayer classification. Paper presented at the Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR, 325-330. doi:10.1109/ICFHR.2012.206Abstract
For better performance in multilayer or hierarchical classification of handwritten text, appropriate grouping of similar symbols is very important. Here we aim to develop a reliable grouping schema for the similar looking basic characters, numerals and vowel modifiers of Bangla language. We experimented with thickened and thinned segmented handwritten text to compare which type of image is better for which group. For classification we chose Support Vector Machine (SVM) as it outperforms other classifiers in this field. We used both "one against one" and "one against all" strategies for multiclass SVM and compared their performance.