Pyrboxes: An efficient multi-scale scene text detector with feature pyramids

doi:10.1016/j.patrec.2019.04.022

	Pyrboxes: An efficient multi-scale scene text detector with feature pyramids
	Sheng, Fenfen1,2 ; Chen, Zhineng1 ; Zhang, Wei 3; Xu, Bo 1
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.