Scale (ratio)

Boundary (topology)

Statistics

Cartography

Astrophysics

Computer science

Variation (astronomy)

Image segmentation

Thermodynamics

Line segment

Physics

Finite element method

Regression

Segmentation

Quadrilateral

Pattern recognition (psychology)

Mathematics

Geography

Mathematical analysis

Artificial intelligence

Geometry

Line (geometry)

Computer vision

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.

MSR: Multi-Scale Shape Regression for Scene Text Detection