Omnidirectional Scene Text Detection with Sequential-free Box Discretization
This addresses a critical problem in computer vision for detecting text in natural scenes, offering a novel solution with broad applicability, though it is incremental in improving existing detection frameworks.
The paper tackles the label confusion issue in scene text detection caused by quadrilateral bounding boxes by proposing Sequential-free Box Discretization (SBD), which discretizes boxes into key edges to improve performance, achieving state-of-the-art results on benchmarks like ICDAR 2015 and HRSC2016.
Scene text in the wild is commonly presented with high variant characteristics. Using quadrilateral bounding box to localize the text instance is nearly indispensable for detection methods. However, recent researches reveal that introducing quadrilateral bounding box for scene text detection will bring a label confusion issue which is easily overlooked, and this issue may significantly undermine the detection performance. To address this issue, in this paper, we propose a novel method called Sequential-free Box Discretization (SBD) by discretizing the bounding box into key edges (KE) which can further derive more effective methods to improve detection performance. Experiments showed that the proposed method can outperform state-of-the-art methods in many popular scene text benchmarks, including ICDAR 2015, MLT, and MSRA-TD500. Ablation study also showed that simply integrating the SBD into Mask R-CNN framework, the detection performance can be substantially improved. Furthermore, an experiment on the general object dataset HRSC2016 (multi-oriented ships) showed that our method can outperform recent state-of-the-art methods by a large margin, demonstrating its powerful generalization ability. Source code: https://github.com/Yuliang-Liu/Box_Discretization_Network.