TY - GEN
T1 - BIP-NET
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
AU - Yang, Chuang
AU - Chen, Mulin
AU - Yuan, Yuan
AU - Wang, Qi
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - 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 Bidirectional Perspective strategy based Network (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.
AB - 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 Bidirectional Perspective strategy based Network (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.
KW - Arbitrary-shaped text detection
KW - computer vision
KW - real-time text detector
KW - scene text detection
UR - https://www.scopus.com/pages/publications/85131267094
U2 - 10.1109/ICASSP43922.2022.9747331
DO - 10.1109/ICASSP43922.2022.9747331
M3 - 会议稿件
AN - SCOPUS:85131267094
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2255
EP - 2259
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 May 2022 through 27 May 2022
ER -