Presentation 2014-03-14
Object Recognition Featuring Decision-Value Based True/False Classification and Two-Stage Learning
Toshihiko YAMASAKI, Takaki MAEDA, Kiyoharu AIZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a two-stage classification framework for image recognition. In the first stage, input images are classified using a bag-of-features (BoF) based method with a multi-class classifier. The results are categorized into two groups by our confidence analysis: highly confident and less confident. The images with less confidence are re-classified in the second stage using our proposed algorithm. The validity of the proposed algorithm was confirmed by some experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Object recognition / image recognition / confidence / true/false classification / two-stage learning
Paper # PRMU2013-197
Date of Issue

Conference Information
Committee PRMU
Conference Date 2014/3/6(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) Object Recognition Featuring Decision-Value Based True/False Classification and Two-Stage Learning
Sub Title (in English)
Keyword(1) Object recognition
Keyword(2) image recognition
Keyword(3) confidence
Keyword(4) true/false classification
Keyword(5) two-stage learning
1st Author's Name Toshihiko YAMASAKI
1st Author's Affiliation Department of Information and Communication Engineering, The University of Tokyo()
2nd Author's Name Takaki MAEDA
2nd Author's Affiliation Department of Information and Communication Engineering, The University of Tokyo
3rd Author's Name Kiyoharu AIZAWA
3rd Author's Affiliation Department of Information and Communication Engineering, The University of Tokyo
Date 2014-03-14
Paper # PRMU2013-197
Volume (vol) vol.113
Number (no) 493
Page pp.pp.-
#Pages 6
Date of Issue