Presentation 2003/3/7
Video Text Recognition Based on Category-Dependent Feature Extraction Using Feature Compensation
Minoru MORI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When recognizing multiple fonts, geometric features, such as the directional information of strokes, are generally robust against deformation but are weak against degradation. This paper describes a category-dependent feature extraction method that uses a feature compensation technique to overcome this weakness. Our proposed method estimates the degree of degradation of an input pattern by comparing the input pattern and the template of each category. This estimation enables us to compensate the degradation in feature values. We apply the proposed method to the recognition of video text suffering from degradation and deformation. Recognition experiments using characters extracted from videos show that the proposed method is superior to the conventional alternatives in resisting degradation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) OCR / feature extraction / category-dependent / compensation / degradation / deformation
Paper # PRMU2002-246
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/3/7(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) Video Text Recognition Based on Category-Dependent Feature Extraction Using Feature Compensation
Sub Title (in English)
Keyword(1) OCR
Keyword(2) feature extraction
Keyword(3) category-dependent
Keyword(4) compensation
Keyword(5) degradation
Keyword(6) deformation
1st Author's Name Minoru MORI
1st Author's Affiliation NTT Communication Science Laboratories, NTT Corporation()
Date 2003/3/7
Paper # PRMU2002-246
Volume (vol) vol.102
Number (no) 708
Page pp.pp.-
#Pages 6
Date of Issue