MSR: Multi-Scale Shape Regression for Scene Text Detection
This addresses localization errors in scene text detection for applications like image analysis, though it is incremental as it builds on existing regression and multi-scale techniques.
The paper tackles the problem of inaccurate quadrilateral box predictions for scene text detection by introducing a multi-scale shape regression network (MSR) that predicts dense boundary points, achieving superior performance on public datasets for curved and straight text lines.
State-of-the-art scene text detection techniques predict quadrilateral boxes that are prone to localization errors while dealing with straight or curved text lines of different orientations and lengths in scenes. This paper presents a novel multi-scale shape regression network (MSR) that is capable of locating text lines of different lengths, shapes and curvatures in scenes. The proposed MSR detects scene texts by predicting dense text boundary points that inherently capture the location and shape of text lines accurately and are also more tolerant to the variation of text line length as compared with the state of the arts using proposals or segmentation. Additionally, the multi-scale network extracts and fuses features at different scales which demonstrates superb tolerance to the text scale variation. Extensive experiments over several public datasets show that the proposed MSR obtains superior detection performance for both curved and straight text lines of different lengths and orientations.