Cross-language Framework for Word Recognition and Spotting of Indic Scripts

TL;DR

This paper introduces a cross-language framework for handwritten word recognition and spotting in low-resource Indic scripts, leveraging a large dataset from a source script and applying zone-wise character mapping to recognize and spot text in target scripts with limited data.

Contribution

The novel framework enables recognition of low-resource Indic scripts by transferring knowledge from a resource-rich source script using zone-wise character mapping and script similarity scoring.

Findings

Effective recognition across Bangla, Devanagari, and Gurumukhi scripts.

Zone-wise character mapping improves recognition accuracy.

Script similarity score guides cross-language transcription feasibility.

Abstract

Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform for handwritten word recognition and spotting for such low-resource scripts where training is performed with a sufficiently large dataset of an available script (considered as source script) and testing is done on other scripts (considered as target script). Training with one source script and testing with another script to have a reasonable result is not easy in handwriting domain due to the complex nature of handwriting variability among scripts. Also it is difficult in mapping between source and target characters when they appear in cursive word images. The proposed Indic cross language framework exploits a large resource of dataset for training and uses it for recognizing and spotting text of other target scripts where sufficient amount of training data is not available. Since, Indic scripts are mostly written in 3 zones, namely, upper, middle and lower, we employ zone-wise character (or component) mapping for efficient learning purpose. The performance of our cross-language framework depends on the extent of similarity between the source and target scripts. Hence, we devise an entropy based script similarity score using source to target character mapping that will provide a feasibility of cross language transcription. We have tested our approach in three Indic scripts, namely, Bangla, Devanagari and Gurumukhi, and the corresponding results are reported.