DocumentCode
2950781
Title
Handwritten Character Recognition Using Gray-scale Based State-Space Parameters and Class Modular NN
Author
Lajish, V.L.
Author_Institution
Tata Consultancy Services Ltd., Mumbai
fYear
2008
fDate
4-6 Jan. 2008
Firstpage
374
Lastpage
379
Abstract
We present a novel feature extraction method for offline recognition of segmented Malayalam handwritten characters from their gray-scale images without the usual step of binarization. We investigate a new approach to model handwritten characters using state-space map (SSM) and state-space point distribution (SSPD) parameters. In the recognition stage we used class modular neural network with the proposed SSPD features and this method is found to be promising.
Keywords
feature extraction; handwritten character recognition; image segmentation; natural language processing; neural nets; Malayalam handwritten character segmentation; class modular neural network; feature extraction; gray-scale image; handwritten character recognition; offline recognition; state-space map; state-space point distribution; Character recognition; Delay; Feature extraction; Gray-scale; Handwriting recognition; Humans; Image reconstruction; Natural languages; Neural networks; Signal processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing, Communications and Networking, 2008. ICSCN '08. International Conference on
Conference_Location
Chennai
Print_ISBN
978-1-4244-1924-1
Electronic_ISBN
978-1-4244-1924-1
Type
conf
DOI
10.1109/ICSCN.2008.4447222
Filename
4447222
Link To Document