Automated Text Detection and Character Recognition in Natural Scenes Based on Local Image Features and Contour Processing Techniques

被引：22

作者：

Baran, Remigiusz ^{[1
]}

Partila, Pavol ^{[2
]}

Wilk, Rafal ^{[3
]}

机构：

[1] Kielce Univ Technol, Dept Comp Sci Elect & Elect Engn, Kielce, Poland

[2] VSB Tech Univ Ostrava, Dept Telecommun, Ostrava, Czech Republic

[3] Univ Comp Engn & Telecommun, Dept Teleinformat, Kielce, Poland

来源：

INTELLIGENT HUMAN SYSTEMS INTEGRATION, IHSI 2018 | 2018年 / 722卷

关键词：

Natural scene images; Text detection and recognition; Connected component-based methods; MSER; Contour oriented filters; IMCOP system;

D O I：

10.1007/978-3-319-73888-8_8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A novel effective scheme for automated text detection and character recognition in natural scene images is presented in the paper. The proposed text detection approach belongs to the category of connected component-based methods utilizing Maximally Stable Extremal Regions (MSER) feature detector. Various literature based geometrical and contour oriented filters, used to distinguish between text and non-text MSER regions as well as to group remaining text regions into words and phrases, are applied first. Novel filters, designed to reject remaining non-text regions and words (phrases) that are not in line with assumed properties, are utilized next. Final words and phrases are recognized using an OCR system. Finally, an application of the presented approach within the IMCOP content discovery and delivery platform is briefly described.

引用

页码：42 / 48

页数：7

共 14 条

[1] A capable multimedia content discovery platform based on visual content analysis and intelligent data enrichment
Baran, Remigiusz
Dziech, Andrzej
Zeja, Andrzej
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2018, 77 (11) : 14077 - 14091
[2] Baran R, 2016, 2016 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE & COMPUTATIONAL INTELLIGENCE (CSCI), P1333, DOI [10.1109/CSCI.2016.0249, 10.1109/CSCI.2016.248]
[3] Chen H., 2011, 2011 18th IEEE International Conference on Image Processing (ICIP 2011), P2609, DOI 10.1109/ICIP.2011.6116200
[4] Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning
Coates, Adam
Carpenter, Blake
Case, Carl
Satheesh, Sanjeev
Suresh, Bipin
Wang, Tao
Wu, David J.
Ng, Andrew Y.
[J]. 11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011), 2011, : 440 - 445
[5] Signal compression based on zonal selection methods
Dziech, W
Baran, R
Wiraszka, D
[J]. MMET 2000: INTERNATIONAL CONFERENCE ON MATHEMATICAL METHODS IN ELECTROMAGNETIC THEORY, VOLS 1 AND 2, CONFERENCE PROCEEDINGS, 2000, : 224 - 226
[6] Enhanced Method of Near Duplicate Detection for Red Carpet Photographs
Grega, Michal
[J]. MULTIMEDIA COMMUNICATIONS, SERVICES AND SECURITY, MCSS 2015, 2015, 566 : 132 - 140
[7] Jain A. K., 1992, Machine Vision and Applications, V5, P169, DOI 10.1007/BF02626996
[8] Lucas SM, 2003, PROC INT CONF DOC, P682
[9] Robust wide-baseline stereo from maximally stable extremal regions
Matas, J
Chum, O
Urban, M
Pajdla, T
[J]. IMAGE AND VISION COMPUTING, 2004, 22 (10) : 761 - 767
[10] Merino-Gracia K., 2011, P 4 INT WORKSH CAM B, P29, DOI DOI 10.1007/978-3-642-29364-1_3

← 1 2 →