WordSup: Exploiting Word Annotations for Character based Text Detection

TL;DR

This paper introduces a weakly supervised learning framework that leverages word-level annotations to train character detectors, significantly improving scene text detection performance across multiple benchmarks.

Contribution

It presents a novel method to train character detectors using only word-level annotations, reducing the need for costly character-level labeling.

Findings

Achieves state-of-the-art results on scene text detection benchmarks

Demonstrates effectiveness in deformed text detection and math expression recognition

Utilizes large-scale datasets with only word annotations for training

Abstract

Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks. Among these elements, character is the most basic one for various languages such as Western, Chinese, Japanese, mathematical expression and etc. It is natural and convenient to construct a common text detection engine based on character detectors. However, training character detectors requires a vast of location annotated characters, which are expensive to obtain. Actually, the existing real text datasets are mostly annotated in word or line level. To remedy this dilemma, we propose a weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character detector training. When applied in scene text detection, we are thus able to train a robust character detector by exploiting word annotations in the rich large-scale real scene text datasets, e.g. ICDAR15 and COCO-text. The character detector acts as a key role in the pipeline of our text detection engine. It achieves the state-of-the-art performance on several challenging scene text detection benchmarks. We also demonstrate the flexibility of our pipeline by various scenarios, including deformed text detection and math expression recognition.