AdaBoost for Text Detection in Natural Scene

Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions...

Full description

Saved in:
Bibliographic Details
Published in2011 International Conference on Document Analysis and Recognition pp. 429 - 434
Main Authors Jung-Jin Lee, Pyoung-Hean Lee, Seong-Whan Lee, Yuille, A., Koch, C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2011
Subjects
AdaBoost
Algorithm design and analysis
Energy measurement
Feature extraction
Histograms
Image color analysis
Image edge detection
Optimization
text detection
text location
Online AccessGet full text
ISBN1457713500
9781457713507
ISSN1520-5363
DOI10.1109/ICDAR.2011.93

Cover

More Information
Summary:Detecting text regions in natural scenes is an important part of computer vision. We propose a novel text detection algorithm that extracts six different classes features of text, and uses Modest AdaBoost with multi-scale sequential search. Experiments show that our algorithm can detect text regions with a f= 0.70, from the ICDAR 2003 datasets which include images with text of various fonts, sizes, colors, alphabets and scripts.
ISBN:1457713500
9781457713507
ISSN:1520-5363
DOI:10.1109/ICDAR.2011.93