Visual feature extraction using variable map-dimension hypercolumn model

Saleh Aly, Naoyuki Tsuruta, Rin Ichiro Taniguchi, Atsushi Shimada

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

6 Citations (Scopus)

Abstract

Hypercolumn model (HCM) is a neural network model previously proposed to solve image recognition problem. In this paper, we propose an improved version of HCM network and demonstrate its ability to solve face recognition problem. HCM network is a hierarchical model based on self-organizing map (SOM) that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation. This invariance achieved by alternating between feature extraction and feature integration operation. To improve the recognition rate of HCM, we propose a variable dimension for each map in the feature extraction layer. The number of neurons in each map-side is decided automatically from training data. We demonstrate the performance of the approach using ORL face database.

Original languageEnglish
Title of host publication2008 International Joint Conference on Neural Networks, IJCNN 2008
Pages845-851
Number of pages7
DOIs
Publication statusPublished - 2008
Event2008 International Joint Conference on Neural Networks, IJCNN 2008 - Hong Kong, China
Duration: Jun 1 2008Jun 8 2008

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Other

Other2008 International Joint Conference on Neural Networks, IJCNN 2008
Country/TerritoryChina
CityHong Kong
Period6/1/086/8/08

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Visual feature extraction using variable map-dimension hypercolumn model'. Together they form a unique fingerprint.

Cite this