TY - GEN

T1 - Detecting oriented text in natural images by linking segments

AU - Shi, Baoguang

AU - Bai, Xiang

AU - Belongie, Serge

N1 - Funding Information: This work was supported in part by National Natural Science Foundation of China (61222308 and 61573160), a Google Focused Research Award, AWS Cloud Credits for Research, a Microsoft Research Award and a Facebook equipment donation. The authors also thank China Scholarship Council (CSC) for supporting this work Publisher Copyright: © 2017 IEEE.

PY - 2017/11/6

Y1 - 2017/11/6

N2 - Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or text line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are produced by combining segments connected by links. Compared with previous methods, SegLink improves along the dimensions of accuracy, speed, and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512×512 images. Moreover, without modification, SegLink is able to detect long lines of non-Latin text, such as Chinese.

AB - Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or text line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are produced by combining segments connected by links. Compared with previous methods, SegLink improves along the dimensions of accuracy, speed, and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512×512 images. Moreover, without modification, SegLink is able to detect long lines of non-Latin text, such as Chinese.

UR - http://www.scopus.com/inward/record.url?scp=85040234078&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2017.371

DO - 10.1109/CVPR.2017.371

M3 - Conference article

AN - SCOPUS:85040234078

SP - 3482

EP - 3490

JO - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

JF - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

Y2 - 21 July 2017 through 26 July 2017

ER -