Zone-based Keyword Spotting in Bangla and Devanagari Documents

TL;DR

This paper introduces a zone-based keyword spotting system for Bangla and Devanagari scripts that leverages HMM-based zone segmentation and a novel foreground-background feature to improve recognition accuracy.

Contribution

It proposes a new zone segmentation method using HMMs and a combined foreground-background feature for better keyword spotting in Indic scripts.

Findings

Significant performance improvement over traditional methods

HMM-based zone segmentation effectively isolates script zones

Combined foreground-background features outperform individual features

Abstract

In this paper we present a word spotting system in text lines for offline Indic scripts such as Bangla (Bengali) and Devanagari. Recently, it was shown that zone-wise recognition method improves the word recognition performance than conventional full word recognition system in Indic scripts. Inspired with this idea we consider the zone segmentation approach and use middle zone information to improve the traditional word spotting performance. To avoid the problem of zone segmentation using heuristic approach, we propose here an HMM based approach to segment the upper and lower zone components from the text line images. The candidate keywords are searched from a line without segmenting characters or words. Also, we propose a novel feature combining foreground and background information of text line images for keyword-spotting by character filler models. A significant improvement in performance is noted by using both foreground and background information than their individual one. Pyramid Histogram of Oriented Gradient (PHOG) feature has been used in our word spotting framework. From the experiment, it has been noted that the proposed zone-segmentation based system outperforms traditional approaches of word spotting.