Conceptual Text Region Network: Cognition-Inspired Accurate Scene Text Detection

TL;DR

This paper introduces CTRNet, a cognition-inspired scene text detection framework that improves label design and eliminates the need for text kernel segmentation, resulting in more accurate and interpretable detection.

Contribution

The paper proposes Conceptual Text Regions (CTRs) for better label design and an inference pipeline that removes reliance on text kernel segmentation, enhancing accuracy and interpretability.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Higher stability and consistency across datasets.

F-measures exceeding 85% on all tested benchmarks.

Abstract

Segmentation-based methods are widely used for scene text detection due to their superiority in describing arbitrary-shaped text instances. However, two major problems still exist: 1) current label generation techniques are mostly empirical and lack theoretical support, discouraging elaborate label design; 2) as a result, most methods rely heavily on text kernel segmentation which is unstable and requires deliberate tuning. To address these challenges, we propose a human cognition-inspired framework, termed, Conceptual Text Region Network (CTRNet). The framework utilizes Conceptual Text Regions (CTRs), which is a class of cognition-based tools inheriting good mathematical properties, allowing for sophisticated label design. Another component of CTRNet is an inference pipeline that, with the help of CTRs, completely omits the need for text kernel segmentation. Compared with previous segmentation-based methods, our approach is not only more interpretable but also more accurate. Experimental results show that CTRNet achieves state-of-the-art performance on benchmark CTW1500, Total-Text, MSRA-TD500, and ICDAR 2015 datasets, yielding performance gains of up to 2.0%. Notably, to the best of our knowledge, CTRNet is among the first detection models to achieve F-measures higher than 85.0% on all four of the benchmarks, with remarkable consistency and stability.