Presentation 2007-10-25
Combining Three Different Types of Local Features for Generic Object Recognition(International Session 1)
Yasunori KAMIYA, Yoshikazu YANO, Shigeru OKUMA, Tomokazu TAKAHASHI, Ichiro IDE, Hiroshi MURASE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Many types of local features have been proposed in various researches. The local features are grouped by : (1) distinguishing texture pattern ; (2) area uniform in color ; (3) and boundary between different colors or textures. However in generic object recogntion, previous reseaches use mainly only type (1). For improving recognition performance, we propose recognition method combining all types local feature with considering the effectivity of each type for the object. In the experiment, we show the method's effectiveness using all types of local features and compare its performance with previous works by Caltech database and Graz-02 dataset.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) generic object recognition / object category recognition / different types of local feature
Paper # PRMU2007-94
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/10/18(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Combining Three Different Types of Local Features for Generic Object Recognition(International Session 1)
Sub Title (in English)
Keyword(1) generic object recognition
Keyword(2) object category recognition
Keyword(3) different types of local feature
1st Author's Name Yasunori KAMIYA
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Yoshikazu YANO
2nd Author's Affiliation Electronics Course, Aichi Institute of Technology
3rd Author's Name Shigeru OKUMA
3rd Author's Affiliation Graduate School of Engineering, Nagoya University
4th Author's Name Tomokazu TAKAHASHI
4th Author's Affiliation Graduate School of Information Science, Nagoya University
5th Author's Name Ichiro IDE
5th Author's Affiliation Graduate School of Information Science, Nagoya University
6th Author's Name Hiroshi MURASE
6th Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2007-10-25
Paper # PRMU2007-94
Volume (vol) vol.107
Number (no) 281
Page pp.pp.-
#Pages 6
Date of Issue