TY - GEN
T1 - Learning shape-aware embedding for scene text detection
AU - Tian, Zhuotao
AU - Shu, Michelle
AU - Lyu, Pengyuan
AU - Li, Ruiyu
AU - Zhou, Chao
AU - Shen, Xiaoyong
AU - Jia, Jiaya
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - We address the problem of detecting scene text in arbitrary shapes, which is a challenging task due to the high variety and complexity of the scene. Specifically, we treat text detection as instance segmentation and propose a segmentation-based framework, which extracts each text instance as an independent connected component. To distinguish different text instances, our method maps pixels onto an embedding space where pixels belonging to the same text are encouraged to appear closer to each other and vise versa. In addition, we introduce a Shape-Aware Loss to make training adaptively accommodate various aspect ratios of text instances and the tiny gaps among them, and a new post-processing pipeline to yield precise bounding box predictions. Experimental results on three challenging datasets (ICDAR15, MSRA-TD500 and CTW1500) demonstrate the effectiveness of our work.
AB - We address the problem of detecting scene text in arbitrary shapes, which is a challenging task due to the high variety and complexity of the scene. Specifically, we treat text detection as instance segmentation and propose a segmentation-based framework, which extracts each text instance as an independent connected component. To distinguish different text instances, our method maps pixels onto an embedding space where pixels belonging to the same text are encouraged to appear closer to each other and vise versa. In addition, we introduce a Shape-Aware Loss to make training adaptively accommodate various aspect ratios of text instances and the tiny gaps among them, and a new post-processing pipeline to yield precise bounding box predictions. Experimental results on three challenging datasets (ICDAR15, MSRA-TD500 and CTW1500) demonstrate the effectiveness of our work.
KW - Categorization
KW - Recognition: Detection
KW - Retrieval
KW - Vision Applications and Systems
UR - https://www.scopus.com/pages/publications/85077229268
U2 - 10.1109/CVPR.2019.00436
DO - 10.1109/CVPR.2019.00436
M3 - 会议稿件
AN - SCOPUS:85077229268
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 4229
EP - 4238
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -