Invariant moments based convolutional neural networks for image analysis
The paper proposes a method using convolutional neural network to effectively evaluate the discrimination between face and non face patterns, gender classification using facial images and facial expression recognition. The novelty of the method lies in the utilization of the initial trainable convol...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Atlantis Press
2017-01-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://www.atlantis-press.com/article/25875161/view |
id |
doaj-842c48e679ea4b828fea6fee4ea25e3e |
---|---|
record_format |
Article |
spelling |
doaj-842c48e679ea4b828fea6fee4ea25e3e2020-11-25T02:39:22ZengAtlantis PressInternational Journal of Computational Intelligence Systems 1875-68832017-01-0110110.2991/ijcis.2017.10.1.62Invariant moments based convolutional neural networks for image analysisVijayalakshmi G.V. MaheshAlex Noel Joseph RajZhun FanThe paper proposes a method using convolutional neural network to effectively evaluate the discrimination between face and non face patterns, gender classification using facial images and facial expression recognition. The novelty of the method lies in the utilization of the initial trainable convolution kernels coefficients derived from the zernike moments by varying the moment order. The performance of the proposed method was compared with the convolutional neural network architecture that used random kernels as initial training parameters. The multilevel configuration of zernike moments was significant in extracting the shape information suitable for hierarchical feature learning to carry out image analysis and classification. Furthermore the results showed an outstanding performance of zernike moment based kernels in terms of the computation time and classification accuracy.https://www.atlantis-press.com/article/25875161/viewZernike momentsconvolution kernelinvariant momentspattern recognitionhierarchical feature learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Vijayalakshmi G.V. Mahesh Alex Noel Joseph Raj Zhun Fan |
spellingShingle |
Vijayalakshmi G.V. Mahesh Alex Noel Joseph Raj Zhun Fan Invariant moments based convolutional neural networks for image analysis International Journal of Computational Intelligence Systems Zernike moments convolution kernel invariant moments pattern recognition hierarchical feature learning |
author_facet |
Vijayalakshmi G.V. Mahesh Alex Noel Joseph Raj Zhun Fan |
author_sort |
Vijayalakshmi G.V. Mahesh |
title |
Invariant moments based convolutional neural networks for image analysis |
title_short |
Invariant moments based convolutional neural networks for image analysis |
title_full |
Invariant moments based convolutional neural networks for image analysis |
title_fullStr |
Invariant moments based convolutional neural networks for image analysis |
title_full_unstemmed |
Invariant moments based convolutional neural networks for image analysis |
title_sort |
invariant moments based convolutional neural networks for image analysis |
publisher |
Atlantis Press |
series |
International Journal of Computational Intelligence Systems |
issn |
1875-6883 |
publishDate |
2017-01-01 |
description |
The paper proposes a method using convolutional neural network to effectively evaluate the discrimination between face and non face patterns, gender classification using facial images and facial expression recognition. The novelty of the method lies in the utilization of the initial trainable convolution kernels coefficients derived from the zernike moments by varying the moment order. The performance of the proposed method was compared with the convolutional neural network architecture that used random kernels as initial training parameters. The multilevel configuration of zernike moments was significant in extracting the shape information suitable for hierarchical feature learning to carry out image analysis and classification. Furthermore the results showed an outstanding performance of zernike moment based kernels in terms of the computation time and classification accuracy. |
topic |
Zernike moments convolution kernel invariant moments pattern recognition hierarchical feature learning |
url |
https://www.atlantis-press.com/article/25875161/view |
work_keys_str_mv |
AT vijayalakshmigvmahesh invariantmomentsbasedconvolutionalneuralnetworksforimageanalysis AT alexnoeljosephraj invariantmomentsbasedconvolutionalneuralnetworksforimageanalysis AT zhunfan invariantmomentsbasedconvolutionalneuralnetworksforimageanalysis |
_version_ |
1724786520267685888 |