OPT OpenIR  > 光学影像学习与分析中心
PixelLink: Detecting scene text via instance segmentation
Deng, Dan1,3,5; Liu, Haifeng1; Li, Xuelong4; Cai, Deng1,2
Conference Name32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Source Publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
Conference Date2018-02-02
Conference PlaceNew Orleans, LA, United states
PublisherAAAI press
Contribution Rank4
AbstractMost state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression. Regression plays a key role in the acquisition of bounding boxes in these methods, but it is not indispensable because text/non-text prediction can also be considered as a kind of semantic segmentation that contains full location information in itself. However, text instances in scene images often lie very close to each other, making them very difficult to separate via semantic segmentation. Therefore, instance segmentation is needed to address this problem. In this paper, PixelLink, a novel scene text detection algorithm based on instance segmentation, is proposed. Text instances are first segmented out by linking pixels within the same instance together. Text bounding boxes are then extracted directly from the segmentation result without location regression. Experiments show that, compared with regression-based methods, PixelLink can achieve better or comparable performance on several benchmarks, while requiring many fewer training iterations and less training data. Copyright © 2018, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Indexed ByEI
EI Accession Number20190506436164
Document Type会议论文
Affiliation1.State Key Lab of CAD and CG, College of Computer Science, Zhejiang University, China;
2.Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China;
3.CVTE Research, China;
4.Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, China;
5.Visual Computing Group, CVTE Research, China
Recommended Citation
GB/T 7714
Deng, Dan,Liu, Haifeng,Li, Xuelong,et al. PixelLink: Detecting scene text via instance segmentation[C]:AAAI press,2018:6773-6780.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Deng, Dan]'s Articles
[Liu, Haifeng]'s Articles
[Li, Xuelong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Deng, Dan]'s Articles
[Liu, Haifeng]'s Articles
[Li, Xuelong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Deng, Dan]'s Articles
[Liu, Haifeng]'s Articles
[Li, Xuelong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.