Enhanced Characterness for Text Detection in the Wild

TL;DR

This paper introduces a language-agnostic text detection method in natural scenes that leverages edge-enhanced extremal regions and characterness measures to improve text region identification and rejection of non-text areas.

Contribution

The paper proposes a novel, language-agnostic text detection approach using edge-enhanced extremal regions and characterness cues, enhancing generalization over traditional methods.

Findings

Provides better generalization performance compared to traditional methods.

Effective in rejecting non-text regions through characterness measures.

Achieves comparable or superior accuracy in text detection in natural scenes.

Abstract

Text spotting is an interesting research problem as text may appear at any random place and may occur in various forms. Moreover, ability to detect text opens the horizons for improving many advanced computer vision problems. In this paper, we propose a novel language agnostic text detection method utilizing edge enhanced Maximally Stable Extremal Regions in natural scenes by defining strong characterness measures. We show that a simple combination of characterness cues help in rejecting the non text regions. These regions are further fine-tuned for rejecting the non-textual neighbor regions. Comprehensive evaluation of the proposed scheme shows that it provides comparative to better generalization performance to the traditional methods for this task.