Pyrboxes: An efficient multi-scale scene text detector with feature pyramids | |
Sheng, Fenfen1,2; Chen, Zhineng1; Zhang, Wei3; Xu, Bo1 | |
发表期刊 | PATTERN RECOGNITION LETTERS |
ISSN | 0167-8655 |
2019-07-01 | |
卷号 | 125期号:2019页码:228-234 |
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. |
关键词 | Scene text detection Multi-scale text detection Grouped pyramid module Efficient and effective |
DOI | 10.1016/j.patrec.2019.04.022 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Beijing Science and Technology Program[Z171100002217015] ; National Natural Science Foundation of China[61772526] ; National Natural Science Foundation of China[61772526] ; Beijing Science and Technology Program[Z171100002217015] |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000482374500032 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/27330 |
专题 | 数字内容技术与服务研究中心_远程智能医疗 数字内容技术与服务研究中心 |
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 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
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(2019):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(2019),228-234. |
MLA | Sheng, Fenfen,et al."Pyrboxes: An efficient multi-scale scene text detector with feature pyramids".PATTERN RECOGNITION LETTERS 125.2019(2019):228-234. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
代表性论文1-盛芬芬-PyrBoxes_(1558KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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