Handwritten Bangla Word Recognition Using HOG Descriptor

Author

Bhowmik, Showmik ; Roushan, Md Galib ; Sarkar, Ram ; Nasipuri, Mita ; Polley, Sanjib ; Malakar, Samir

Author_Institution

Dept. of Comput. Sc. & Eng., Jadavpur Univ., Kolkata, India

fYear

2014

Firstpage

193

Lastpage

197

Abstract

The holistic approaches for handwritten word recognition treat the words as single, indivisible entity and attempt to recognize words from their overall shape. In the present work, a novel technique to recognize handwritten Bangla word is proposed. Histograms of Oriented Gradients (HOG) are used as the feature set to represent each word sample at the feature space and a neural network based classifier is applied to classify the word images. On the basis of the HOG feature set, the performance achieved by the technique on a small dataset is quite satisfactory.

Keywords

document image processing; handwritten character recognition; image classification; natural languages; neural nets; word processing; HOG descriptor; HOG feature set; classifier; handwritten Bangla word recognition; histograms of oriented gradients; neural network; word image classification; Character recognition; Feature extraction; Handwriting recognition; Hidden Markov models; Histograms; Optical character recognition software; Bangla script; Histograms of oriented gradients; Holistic word recognition; handwritten words;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Applications of Information Technology (EAIT), 2014 Fourth International Conference of

Type

conf

DOI

10.1109/EAIT.2014.43

Filename

7052044