ROBUST TEXT DETECTION IN NATURAL IMAGES WITH EDGE-ENHANCED MAXIMALLY STABLE EXTREMAL REGIONS

被引：0

作者：

Chen, Huizhong ^{[1
]}

Tsai, Sam S. ^{[1
]}

Schroth, Georg ^{[2
]}

Chen, David M. ^{[1
]}

Grzeszczuk, Radek ^{[3
]}

Girod, Bernd ^{[1
]}

机构：

[1] Stanford Univ, Dept Elect Engn, Stanford, CA 94305 USA

[2] Tech Univ Munich, Inst Med Technol, Munich, Germany

[3] Nokia Res Ctr, Palo Alto, CA 94304 USA

来源：

2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2011年

关键词：

Text detection; maximally stable extremal regions; connected component analysis; VIDEO;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Detecting text in natural images is an important prerequisite. In this paper, we propose a novel text detection algorithm, which employs edge-enhanced Maximally Stable Extremal Regions as basic letter candidates. These candidates are then filtered using geometric and stroke width information to exclude non-text objects. Letters are paired to identify text lines, which are subsequently separated into words. We evaluate our system using the ICDAR competition dataset and our mobile document database. The experimental results demonstrate the excellent performance of the proposed method.

引用

页数：4

共 50 条

[1] Edge-enhanced maximally stable color regions
Pan, Neng-Jie
Yu, Hui-Min
[J]. Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2014, 48 (07): : 1241 - 1247
[2] Text Recognition Using Poisson Filtering and Edge Enhanced Maximally Stable Extremal Regions
Mol, Jiji
Mohammed, Anisha
Mahesh, B. S.
[J]. 2017 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING, INSTRUMENTATION AND CONTROL TECHNOLOGIES (ICICICT), 2017, : 302 - 306
[3] Multi-Sensor Image Registration Using Edge-Enhanced Maximally Stable Extremal Region
Liu, Li
Tuo, Hongya
Xu, Tao
Jing, Zhongliang
[J]. 2012 5TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), 2012, : 901 - 905
[4] Scene text detection method research based on maximally stable extremal regions
Xu, Lei
Liu, Yi
Mou, Lianming
[J]. INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS, 2022, 15 (02) : 142 - 154
[5] Entropy-Based Maximally Stable Extremal Regions for Robust Feature Detection
Cai, Huiwen
Wang, Xiaoyan
Xia, Ming
Wang, Yangsheng
[J]. MATHEMATICAL PROBLEMS IN ENGINEERING, 2012, 2012
[6] Road Sign Text Detection Using Contrast Intensify Maximally Stable Extremal Regions
Hossain, Md Shamim
Alwan, Ahmad Fouad
Pervin, Mahfuza
[J]. 2018 IEEE SYMPOSIUM ON COMPUTER APPLICATIONS & INDUSTRIAL ELECTRONICS (ISCAIE 2018), 2018, : 321 - 325
[7] Pedestrian detection based on maximally stable extremal regions
Frolov, Vadim
Leon, Fernando Puente
[J]. 2010 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV), 2010, : 910 - 914
[8] Scene text detection using graph model built upon maximally stable extremal regions
Shi, Cunzhao
Wang, Chunheng
Xiao, Baihua
Zhang, Yang
Gao, Song
[J]. PATTERN RECOGNITION LETTERS, 2013, 34 (02) : 107 - 116
[9] Scene Text Segmentation with Multi-level Maximally Stable Extremal Regions
Tian, Shangxuan
Lu, Shijian
Su, Bolan
Tan, Chew Lim
[J]. 2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 2703 - 2708
[10] Vehicle detection in Satellite Imagery using Maximally Stable Extremal Regions
Karim, Shahid
Halepoto, Imtiaz Ali
Manzoor, Adnan
Phulpoto, Nazar Hussain
Laghari, Asif Ali
[J]. INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2018, 18 (04): : 75 - 78

← 1 2 3 4 5 →