DocumentCode :
3580488
Title :
A Texture Based Approach to Word-Level Script Identification from Multi-script Handwritten Documents
Author :
Singh, Pawan Kumar ; Khan, Aparajita ; Sarkar, Ram ; Nasipuri, Mita
Author_Institution :
Dept. of Comput. Sci. & Eng., Jadavpur Univ., Kolkata, India
fYear :
2014
Firstpage :
228
Lastpage :
232
Abstract :
Script identification from handwritten document images is an open document analysis problem especially for multilingual environment like India. To design the Optical Character Recognition (OCR) system for multi-script document pages, it is essential to recognize different scripts prior to employing an OCR engine of a particular script. The present work describes a texture based approach to word-level script identification from five handwritten scripts namely, Malayalam, Oriya, Tamil, Telugu and Roman. A 92-element feature vector has been designed in which 80 features consists of selected coefficients of Discrete Cosine Transform (DCT) and the remaining 12 features have been taken from the Moment invariants. Experimentations are conducted on a database consisting of 1000 word images of each script which are evaluated using multiple classifiers. The Multi Layer Perceptron (MLP) classifier is found to be a best choice for the said purpose which is then applied comprehensively using different cross validation folds and different epoch sizes. The average success rate for the present technique of word-level handwritten script identification is found to be 93.56% for 5-fold cross validation with epoch size 1000, which is quite encouraging.
Keywords :
discrete cosine transforms; document image processing; handwritten character recognition; image classification; image texture; multilayer perceptrons; optical character recognition; vectors; 92-element feature vector; DCT; India; MLP classifier; Malayalam handwritten script; Moment invariants; OCR system; Oriya handwritten script; Roman handwritten script; Tamil handwritten script; Telugu handwritten script; discrete cosine transform; multilayer perceptron classifier; multiscript handwritten document images; open document analysis problem; optical character recognition system; texture based approach; word-level handwritten script identification; Accuracy; Arrays; Character recognition; Discrete cosine transforms; Feature extraction; Optical character recognition software; Discrete Cosine Transform; Handwritten Documents; Moment invariant; Multiple classifiers; Script Identification;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Communication Networks (CICN), 2014 International Conference on
Print_ISBN :
978-1-4799-6928-9
Type :
conf
DOI :
10.1109/CICN.2014.60
Filename :
7065479
Link To Document :
بازگشت