Title: A holistic word recognition technique for handwritten Bangla words

Authors: Showmik Bhowmik; Sanjib Polley; Md. Galib Roushan; Samir Malakar; Ram Sarkar; Mita Nasipuri

Addresses: Computer Science and Engineering Department, Jadavpur University, Kolkata-700032, India ' Computer Science and Engineering Department, MCKV Institute of Engineering, Howrah, India ' Computer Science and Engineering Department, Jadavpur University, Kolkata-700032, India ' Master of Computer Application Department, MCKV Institute of Engineering, Howrah, India ' Computer Science and Engineering Department, Jadavpur University, Kolkata-700032, India ' Computer Science and Engineering Department, Jadavpur University, Kolkata-700032, India

Abstract: Holistic word recognition is the current trend for handwritten word recognition. The holistic paradigm in handwritten word recognition considers a word as a single, indivisible entity and attempts to recognise words from their overall shape unlike recognising the individual characters comprising the word. In the present work, concentric rectangles and convex hull-based features are designed in order to classify word images belonging to different classes. For the evaluation of the current technique, 2,754 handwritten Bangla word samples are collected from different sources. A neural network-based classifier is chosen on the basis of the performances of different classifiers and some statistical tests. The recognition performance of the technique is evaluated using a three-fold cross-validation method. From the experimental results, it is observed that the proposed technique correctly recognises 84.74% word images in best case.

Keywords: holistic word recognition; handwritten document images; Bangla script; convex hull; concentric rectangles; neural networks; word images.

DOI: 10.1504/IJAPR.2015.069539

International Journal of Applied Pattern Recognition, 2015 Vol.2 No.2, pp.142 - 159

Received: 26 Feb 2014
Accepted: 03 Jun 2014
Published online: 22 May 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article