Abstract
The performance of text detection is crucial for the subsequent recognition task. Currently, the accuracy of the text detector still needs further improvement, particularly those with irregular shapes in a complex environment. We propose a pixel-wise method based on instance segmentation for scene text detection. Specifically, a text instance is split into five components: a Text Skeleton and four Directional Pixel Regions, then restoring itself based on these elements and receiving supplementary information from other areas when one fails. Besides, a Confidence Scoring Mechanism is designed to filter characters similar to text instances. Experiments on several challenging benchmarks demonstrate that our method achieves state-of-the-art results in scene text detection with an F-measure of 84.6% on Total-Text and 86.3% on CTW1500.
Highlights
Detecting text in the real world is a fundamental computer vision task that directly determines the subsequent recognition results
Five feature maps containing a Text Skeleton (TS) and four Directional Pixel Regions (DPRs) are generated after up-sampling. e TS features are evaluated by a Confidence Scoring Mechanism (CSM), and obtaining the predicted text regions incorporated with the DPRs regions
We propose a novel text detector, which achieves upto 86.3% F-measure among common text benchmarks, including text instance with irregular shapes
Summary
Detecting text in the real world is a fundamental computer vision task that directly determines the subsequent recognition results. Many applications in the real world depend on accurate text detection, such as photo translation [1] and autonomous driving [2]. Precisely locating text instances is still a challenge because of arbitrary angles, shapes, and complex backgrounds. E first challenge involves text instances with irregular shapes. The shaped instance often cannot be accurately described by a horizontal box or an oriented quadrilateral.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
