BiP-Net: Bidirectional Perspective Strategy based Arbitrary-Shaped Text Detection Network
This addresses the problem of arbitrary-shaped text detection for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the challenge of detecting irregular-shaped text by proposing BiP-Net, which combines top-down and bottom-up strategies to improve accuracy and speed, achieving state-of-the-art results on datasets like MSRA-TD500, CTW1500, and ICDAR2015.
Detecting irregular-shaped text instances is the main challenge for text detection. Existing approaches can be roughly divided into top-down and bottom-up perspective methods. The former encodes text contours into unified units, which always fails to fit highly curved text contours. The latter represents text instances by a number of local units, where the complicated network and post-processing lead to slow detection speed. In this paper, to detect arbitrary-shaped text instances with high detection accuracy and speed simultaneously, we propose a \textbf{Bi}directional \textbf{P}erspective strategy based \textbf{Net}work (BiP-Net). Specifically, a new text representation strategy is proposed to represent text contours from a top-down perspective, which can fit highly curved text contours effectively. Moreover, a contour connecting (CC) algorithm is proposed to avoid the information loss of text contours by rebuilding interval contours from a bottom-up perspective. The experimental results on MSRA-TD500, CTW1500, and ICDAR2015 datasets demonstrate the superiority of BiP-Net against several state-of-the-art methods.