Feature map sharing hypercolumn model for shift invariant face recognition

Saleh Aly, Naoyuki Tsuruta, Rin-Ichiro Taniguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a shift invariant pattern recognition mechanism using feature sharing Hypercolumn model (FSHCM). To improve the recognition rate of Hypercolumn model (HCM) a shared map among a set of locally neighborhood maps is constructed in the feature extraction and feature integration layers. The shared maps help the network to increase its ability to deal with wide translation and distortion variations. The proposed framework uses FSHCM neural network to perform feature extraction step, and linear support vector machine for recognition task. The effectiveness of proposed approach is verified by using the misaligned ORL face database.

Original languageEnglish
Title of host publicationProceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09
Pages190-193
Number of pages4
Publication statusPublished - Dec 1 2009
Event14th International Symposium on Artificial Life and Robotics, AROB 14th'09 - Oita, Japan
Duration: Feb 5 2008Feb 7 2009

Publication series

NameProceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09

Other

Other14th International Symposium on Artificial Life and Robotics, AROB 14th'09
CountryJapan
CityOita
Period2/5/082/7/09

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Feature map sharing hypercolumn model for shift invariant face recognition'. Together they form a unique fingerprint.

  • Cite this

    Aly, S., Tsuruta, N., & Taniguchi, R-I. (2009). Feature map sharing hypercolumn model for shift invariant face recognition. In Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09 (pp. 190-193). (Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09).