A robust classifier combined with an auto-associative network for completing partly occluded images

Authors:
Takashi Takahashi;Takio Kurita
Affiliations:
Department of Applied Mathematics and Informatics, Ryukoku University, Ootsu, Shiga 520-2194, Japan;National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki 305-8568, Japan
Venue:
Neural Networks
Year:
2005

Citing 6
Cited 1

Neural networks and principal component analysis: learning from examples without local minima

Neural Networks
Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Robust De-noising by Kernel PCA

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Robust principal component analysis by self-organizing rules based on statistical physics approach

IEEE Transactions on Neural Networks

Fast and robust face recognition via coding residual map learning based adaptive masking

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes an approach for constructing a classifier which is unaffected by occlusions in images. We propose a method for integrating an auto-associative network into a simple classifier. As the auto-associative network can recall the original image from a partly occluded input image, we can employ it to detect occluded regions and complete the input image by replacing those regions with recalled pixels. By iterating this reconstruction process, the integrated network is able to classify target objects with occlusions robustly. To confirm the effectiveness of this method, we performed experiments involving face image classification. It is shown that the classification performance is not decreased, even if about 30% of the face image is occluded.