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

Fingerprint

Face recognition
Feature extraction
Pattern recognition
Support vector machines
Neural networks

All Science Journal Classification (ASJC) codes

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

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).

Feature map sharing hypercolumn model for shift invariant face recognition. / Aly, Saleh; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09. 2009. p. 190-193 (Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09).

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

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. Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09, pp. 190-193, 14th International Symposium on Artificial Life and Robotics, AROB 14th'09, Oita, Japan, 2/5/08.
Aly S, Tsuruta N, Taniguchi R-I. 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. 2009. p. 190-193. (Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09).
Aly, Saleh ; Tsuruta, Naoyuki ; Taniguchi, Rin-Ichiro. / Feature map sharing hypercolumn model for shift invariant face recognition. Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09. 2009. pp. 190-193 (Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09).
@inproceedings{6f44c42e3db046ae864f5cd389b3550e,
title = "Feature map sharing hypercolumn model for shift invariant face recognition",
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.",
author = "Saleh Aly and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9784990288037",
series = "Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09",
pages = "190--193",
booktitle = "Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09",

}

TY - GEN

T1 - Feature map sharing hypercolumn model for shift invariant face recognition

AU - Aly, Saleh

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2009/12/1

Y1 - 2009/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=78149339367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149339367&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78149339367

SN - 9784990288037

T3 - Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09

SP - 190

EP - 193

BT - Proceedings of the 14th International Symposium on Artificial Life and Robotics, AROB 14th'09

ER -