Presentation	2011-01-20 Scene Text Detection and Tracking for Wearable Camera System ,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	One of the most anticipated hardware for visually impaired people is probably the device capable of capturing and translating text messages in natural scene images into an alternative representation such as speech or braille. This paper presents a wearable camera system that is capable of detecting text regions in natural scene images, tracking text regions and selecting text images suitable for character recognition. A particle filter-based tracking is employed to reduce multiple and redundant text images. Moreover, the most appropriate text images are selected from text regions chains created by the text tracking. Experimental results demonstrate that 35% improvement has been achieved.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Particle Filter / Bhattacharyya Coefficient / Edge Orientation Histogram
Paper #	PRMU2010-156,MVE2010-81
Date of Issue

Conference Information
Committee	MVE
Conference Date	2011/1/13(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	Media Experience and Virtual Environment (MVE)
Language	ENG
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Scene Text Detection and Tracking for Wearable Camera System
Sub Title (in English)
Keyword(1)	Particle Filter
Keyword(2)	Bhattacharyya Coefficient
Keyword(3)	Edge Orientation Histogram
1st Author's Name
1st Author's Affiliation	()
Date	2011-01-20
Paper #	PRMU2010-156,MVE2010-81
Volume (vol)	vol.110
Number (no)	382
Page	pp.pp.-
#Pages	6
Date of Issue