Pyrboxes: An efficient multi-scale scene text detector with feature pyramids | |
Sheng, Fenfen1,2; Chen, Zhineng1; Zhang, Wei3; Xu, Bo1 | |
刊名 | PATTERN RECOGNITION LETTERS |
2019-07-01 | |
卷号 | 125页码:228-234 |
关键词 | Scene text detection Multi-scale text detection Grouped pyramid module Efficient and effective |
ISSN号 | 0167-8655 |
DOI | 10.1016/j.patrec.2019.04.022 |
通讯作者 | Chen, Zhineng(zhineng.chen@ia.ac.cn) |
英文摘要 | Scene text detection has attracted many researches due to its importance to various applications. However, current approaches could not keep a good balance between accuracy and speed, i.e., a high-performance accuracy but with a low processing speed, or vice-versa. In this paper, we propose a novel model, named PyrBoxes, for efficient and effective multi-scale scene text detection. PyrBoxes consists of an SSD-based backbone that utilizes deep layers with strong semantics to detect texts in various sizes, and a proposed grouped pyramid module that leverages basic layers to append detailed locations into detection. Most existing detectors discard features from the basic layers due to the efficiency issue. We argue these layers contain fine-grained information, which is complementary to high-level semantics. Based on this, the grouped pyramid module combines the basic layers recursively into a detection layer via a top-down partition and a bottom-up group. Extensive experiments on both horizontal and oriented benchmarks, including ICDAR2013 Focused Scene Text, ICDAR2015 Incidental Text and COCO-Text, demonstrate that PyrBoxes achieves state-of-the-art or highly competitive performance compared with baselines, while runs significantly faster at inference. Furthermore, by experimenting on another ChiTVText dataset, PyrBoxes shows great generality to Chinese and long text lines. By visualizing some qualitative results, as expected, PyrBoxes provides more accurate locations and reduces the rate of missed detections, especially for small-sized texts. (C) 2019 Elsevier B.V. All rights reserved. |
资助项目 | National Natural Science Foundation of China[61772526] ; Beijing Science and Technology Program[Z171100002217015] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:000482374500032 |
资助机构 | National Natural Science Foundation of China ; Beijing Science and Technology Program |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/27329] |
专题 | 中国科学院自动化研究所 |
通讯作者 | Chen, Zhineng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.JD AI Res, Beijing 100101, Peoples R China |
推荐引用方式 GB/T 7714 | Sheng, Fenfen,Chen, Zhineng,Zhang, Wei,et al. Pyrboxes: An efficient multi-scale scene text detector with feature pyramids[J]. PATTERN RECOGNITION LETTERS,2019,125:228-234. |
APA | Sheng, Fenfen,Chen, Zhineng,Zhang, Wei,&Xu, Bo.(2019).Pyrboxes: An efficient multi-scale scene text detector with feature pyramids.PATTERN RECOGNITION LETTERS,125,228-234. |
MLA | Sheng, Fenfen,et al."Pyrboxes: An efficient multi-scale scene text detector with feature pyramids".PATTERN RECOGNITION LETTERS 125(2019):228-234. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论