Contextual Text Block Detection towards Scene Text Understanding

TL;DR

This paper introduces a new method for detecting contextual text blocks in scene images, which improves scene text understanding by capturing complete text messages through a dual detection and clustering approach.

Contribution

It proposes a novel setup for detecting contextual text blocks, introduces a dual detection and clustering technique, and provides new datasets and metrics for evaluating contextual text detection.

Findings

Accurately detects contextual text blocks in scene images.

Facilitates downstream tasks like text classification and translation.

Provides new datasets and evaluation metrics for the task.

Abstract

Most existing scene text detectors focus on detecting characters or words that only capture partial text messages due to missing contextual information. For a better understanding of text in scenes, it is more desired to detect contextual text blocks (CTBs) which consist of one or multiple integral text units (e.g., characters, words, or phrases) in natural reading order and transmit certain complete text messages. This paper presents contextual text detection, a new setup that detects CTBs for better understanding of texts in scenes. We formulate the new setup by a dual detection task which first detects integral text units and then groups them into a CTB. To this end, we design a novel scene text clustering technique that treats integral text units as tokens and groups them (belonging to the same CTB) into an ordered token sequence. In addition, we create two datasets SCUT-CTW-Context and ReCTS-Context to facilitate future research, where each CTB is well annotated by an ordered sequence of integral text units. Further, we introduce three metrics that measure contextual text detection in local accuracy, continuity, and global accuracy. Extensive experiments show that our method accurately detects CTBs which effectively facilitates downstream tasks such as text classification and translation. The project is available at https://sg-vilab.github.io/publication/xue2022contextual/.