A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering

Addressing the limitations of existing deep clustering methods, which struggle with variations in image size and quality and are vulnerable to data noise and model deviations, we propose a deeply-learned clustering paradigm in an unsupervised context. This framework utilizes a multi-layer deep archi...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhongzhe Chen, Xing Gao
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10767584/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128565911814144
author Zhongzhe Chen
Xing Gao
author_facet Zhongzhe Chen
Xing Gao
author_sort Zhongzhe Chen
collection DOAJ
description Addressing the limitations of existing deep clustering methods, which struggle with variations in image size and quality and are vulnerable to data noise and model deviations, we propose a deeply-learned clustering paradigm in an unsupervised context. This framework utilizes a multi-layer deep architecture, in which the standard fully-linked layers are replaced by the deep convolutional ones in order to intelligently calculate semantic visual representations. Furthermore, we integrate a contraction regularizer derived by the contracted autoencoders to the optimization task of our designed clustering, so as to enhance the clustering structure’s quality. This model’s simplified structure allows for more efficient end-to-end training and shows enhanced stability and resilience against variations in initial network parameter settings. Experimental evaluations on the MNIST (Modified National Institute of Standards and Technology database) and STL-10 (Self-Taught Learning 10) indicate that our model surpasses other leading clustering architectures in terms of clustering efficacy. Besides, furthermore, the learned deep features can facilitate generic visual recognition substantially, as demonstrated by our empirical comparison with plenty of successful visual recognition models.
format Article
id doaj-art-c441749e22ac444a911d85c568d83b0a
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-c441749e22ac444a911d85c568d83b0a2024-12-11T00:04:57ZengIEEEIEEE Access2169-35362024-01-011217798617799510.1109/ACCESS.2024.350674210767584A Novel Deeply-Learned Image Quality Analysis Algorithm for ClusteringZhongzhe Chen0Xing Gao1https://orcid.org/0009-0004-1040-4188Intelligent Manufacturing College, Jinhua University of Vocational Technology, Jinhua, ChinaCollege of AI, Anhui University, Hefei, ChinaAddressing the limitations of existing deep clustering methods, which struggle with variations in image size and quality and are vulnerable to data noise and model deviations, we propose a deeply-learned clustering paradigm in an unsupervised context. This framework utilizes a multi-layer deep architecture, in which the standard fully-linked layers are replaced by the deep convolutional ones in order to intelligently calculate semantic visual representations. Furthermore, we integrate a contraction regularizer derived by the contracted autoencoders to the optimization task of our designed clustering, so as to enhance the clustering structure’s quality. This model’s simplified structure allows for more efficient end-to-end training and shows enhanced stability and resilience against variations in initial network parameter settings. Experimental evaluations on the MNIST (Modified National Institute of Standards and Technology database) and STL-10 (Self-Taught Learning 10) indicate that our model surpasses other leading clustering architectures in terms of clustering efficacy. Besides, furthermore, the learned deep features can facilitate generic visual recognition substantially, as demonstrated by our empirical comparison with plenty of successful visual recognition models.https://ieeexplore.ieee.org/document/10767584/CNNvisual qualityend-to-endnoisesvisual classification
spellingShingle Zhongzhe Chen
Xing Gao
A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering
IEEE Access
CNN
visual quality
end-to-end
noises
visual classification
title A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering
title_full A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering
title_fullStr A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering
title_full_unstemmed A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering
title_short A Novel Deeply-Learned Image Quality Analysis Algorithm for Clustering
title_sort novel deeply learned image quality analysis algorithm for clustering
topic CNN
visual quality
end-to-end
noises
visual classification
url https://ieeexplore.ieee.org/document/10767584/
work_keys_str_mv AT zhongzhechen anoveldeeplylearnedimagequalityanalysisalgorithmforclustering
AT xinggao anoveldeeplylearnedimagequalityanalysisalgorithmforclustering
AT zhongzhechen noveldeeplylearnedimagequalityanalysisalgorithmforclustering
AT xinggao noveldeeplylearnedimagequalityanalysisalgorithmforclustering