AdaBoost for Text Detection in Natural Scene

被引：134

作者：

Lee, Jung-Jin ^{[1
]}

Lee, Pyoung-Hean ^{[1
]}

Lee, Seong-Whan ^{[1
]}

Yuille, Alan ^{[1
]}

Koch, Christof ^{[1
]}

机构：

[1] Korea Univ, Dept Brain & Cognit Engn, Seoul 136713, South Korea

来源：

11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011) | 2011年

关键词：

text detection; text location; AdaBoost;

D O I：

10.1109/ICDAR.2011.93

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：429 / 434

页数：6

共 19 条

[1]

[Anonymous], MSU GRAPHICS AND MED

[2]

Breiman L., 1984, CLASSIFICATION AND R

[3] Text analysis using local energy [J].

Chan, W ;

Coghill, G .

PATTERN RECOGNITION, 2001, 34 (12) :2523-2532

[4] Text detection and recognition in images and video frames [J].

Chen, DT ;

Odobez, JM ;

Bourlard, H .

PATTERN RECOGNITION, 2004, 37 (03) :595-608

[5]

Chen X., 2004, COMPUTER VISION AND, V2

[6] A NOTE ON THE GRADIENT OF A MULTIIMAGE [J].

DIZENZO, S .

COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1986, 33 (01) :116-125

[7]

Epshtein B, 2010, PROC CVPR IEEE, P2963, DOI 10.1109/CVPR.2010.5540041

[8] Text detection from natural scene images: Towards a system for visually impaired persons [J].

Ezaki, N ;

Bulacu, M ;

Schomaker, L .

PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, 2004, :683-686

[9]

Freund Y., 1996, Machine Learning. Proceedings of the Thirteenth International Conference (ICML '96), P148

[10] Additive logistic regression: A statistical view of boosting - Rejoinder [J].

Friedman, J ;

Hastie, T ;

Tibshirani, R .

ANNALS OF STATISTICS, 2000, 28 (02) :400-407

← 1 2 →