Presentation	2013-03-14 Learning-based Text Image Detection Naoki CHIBA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	A method for detecting images that contain text regions is proposed. Although methods for text region detection in an image have been proposed, those of text image detection have not been extensively investigated. This is because such text image detection depends on applications. An efficient and general method that can detect text images by using a learning framework is proposed. It requires only manually classifying images into two groups: text and non-text. It can be used for various applications without font information such as type, style, size, color, or language. It builds an image classifier from these two image groups. Experiments showed that this method is more effective than conventional ones.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Text detection / clustering / learning
Paper #	PRMU2012-181
Date of Issue

Conference Information
Committee	PRMU
Conference Date	2013/3/7(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Pattern Recognition and Media Understanding (PRMU)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Learning-based Text Image Detection
Sub Title (in English)
Keyword(1)	Text detection
Keyword(2)	clustering
Keyword(3)	learning
1st Author's Name	Naoki CHIBA
1st Author's Affiliation	Rakuten Institute of Technology, Rakuten, Inc.()
Date	2013-03-14
Paper #	PRMU2012-181
Volume (vol)	vol.112
Number (no)	495
Page	pp.pp.-
#Pages	6
Date of Issue