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

Cui, Chenwei; Lu, Liangfu; Tan, Zhiyuan; Hussain, Amir

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; and (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, demonstrating remarkable consistency and stability.

• Journal Article Type: Article
• Acceptance Date: Aug 9, 2021
• Online Publication Date: Aug 11, 2021
• Publication Date: 2021-11
• Deposit Date: Aug 9, 2021
• Publicly Available Date: Aug 12, 2022
• Print ISSN: 0925-2312
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 464
• Pages: 252-264
• DOI: https://doi.org/10.1016/j.neucom.2021.08.026
• Keywords: Scene text detection, Arbitrary-shaped text detection, Neural networks, Semantic segmentation
• Public URL: http://researchrepository.napier.ac.uk/Output/2792548