Learning Deep Latent Representation of Color Images Using Autoencoders for Efficient Image Retrieval

The content-based image retrieval (CBIR) systems exploit the visual information present in the images to find a suitable match similar to the human visual saliency mechanism. The rise of deep learning methods accomplished notable results in learning efficient image descriptors over traditional featu...

Full description

Saved in:
Bibliographic Details
Published in:Annual IEEE India Conference pp. 1 - 6
Main Authors: Kale, Mandar, Mukhopadhyay, Sudipta
Format: Conference Proceeding
Language:English
Published: IEEE 19.12.2024
Subjects:
ISSN:2325-9418
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The content-based image retrieval (CBIR) systems exploit the visual information present in the images to find a suitable match similar to the human visual saliency mechanism. The rise of deep learning methods accomplished notable results in learning efficient image descriptors over traditional features. These methods automatically extract the salient features and reduce the dimension to get the useful representation of raw image data. In this light, the article proposes a feature learning framework using a deep stacked sparse autoencoder (SAE) and convolutional autoencoder (CAE) models. The autoencoder learns the meaningful approximation of the raw image data following unsupervised training. The study shows the impact of unsupervised training of autoencoder networks on the efficacy of the learned latent features using large-size CIFAR-10 and CIFAR-100 databases. Different model architectures are evaluated to find a suitable architecture for efficient feature extraction of natural color images. The proposed autoencoder networks achieve a nearly 90% reduction in size while maintaining accuracy with a simple distance-based approach. Further, the efficacy of the learned features is tested with two classifier-based retrieval methods using a trained softmax classifier. The experimental evaluation shows that the proposed method SAE and CAE model achieves promising improvements and highly competitive retrieval performance with a large-size CIFAR-10 database.
AbstractList The content-based image retrieval (CBIR) systems exploit the visual information present in the images to find a suitable match similar to the human visual saliency mechanism. The rise of deep learning methods accomplished notable results in learning efficient image descriptors over traditional features. These methods automatically extract the salient features and reduce the dimension to get the useful representation of raw image data. In this light, the article proposes a feature learning framework using a deep stacked sparse autoencoder (SAE) and convolutional autoencoder (CAE) models. The autoencoder learns the meaningful approximation of the raw image data following unsupervised training. The study shows the impact of unsupervised training of autoencoder networks on the efficacy of the learned latent features using large-size CIFAR-10 and CIFAR-100 databases. Different model architectures are evaluated to find a suitable architecture for efficient feature extraction of natural color images. The proposed autoencoder networks achieve a nearly 90% reduction in size while maintaining accuracy with a simple distance-based approach. Further, the efficacy of the learned features is tested with two classifier-based retrieval methods using a trained softmax classifier. The experimental evaluation shows that the proposed method SAE and CAE model achieves promising improvements and highly competitive retrieval performance with a large-size CIFAR-10 database.
Author Mukhopadhyay, Sudipta
Kale, Mandar
Author_xml – sequence: 1
  givenname: Mandar
  surname: Kale
  fullname: Kale, Mandar
  email: mandar9975@gmail.com
  organization: Indian Institute of Technology Kharagpur,Electronics & Electrical Communication Engineering,Kharagpur,India
– sequence: 2
  givenname: Sudipta
  surname: Mukhopadhyay
  fullname: Mukhopadhyay, Sudipta
  email: smukho@ece.iitkgp.ac.in
  organization: Indian Institute of Technology Kharagpur,Electronics & Electrical Communication Engineering,Kharagpur,India
BookMark eNo1UEtLAzEYjKJgrf0HHoL3rXlsNsmxbKsuLC1IPZfs5kuJtElJVsF_79bHaYZ5HeYWXYUYAKEHSuaUEv3YrJdNvVlXXGoyZ4SV81EVigl-gWZaasUF4ZoyxS7RhHEmCl1SdYNmOb8TQhghlIpygmwLJgUf9ngJcMKtGSAM-BVOCfLIzOBjwNHhOh5iws3R7CHjt3wuLD6GCKGPFlLGbnRXzvnen_s_uXFlSB4-zeEOXTtzyDD7wynaPq229UvRbp6betEWXvOhYEyDsswyBrIStuythLJzqued4cr0BDhILWmlCOmkZc4A8E52lRKVsWNsiu5_Zz0A7E7JH0362v3_wr8BbYVbuw
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/INDICON63790.2024.10958253
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350391282
EISSN 2325-9418
EndPage 6
ExternalDocumentID 10958253
Genre orig-research
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i93t-229e8d2d22e765d4cd7e4bf8c3ba38ac0e3e79716800b7d2faee3b7b6856ad8c3
IEDL.DBID RIE
IngestDate Wed Apr 30 05:50:36 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-229e8d2d22e765d4cd7e4bf8c3ba38ac0e3e79716800b7d2faee3b7b6856ad8c3
PageCount 6
ParticipantIDs ieee_primary_10958253
PublicationCentury 2000
PublicationDate 2024-Dec.-19
PublicationDateYYYYMMDD 2024-12-19
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-Dec.-19
  day: 19
PublicationDecade 2020
PublicationTitle Annual IEEE India Conference
PublicationTitleAbbrev INDICON
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002001154
Score 1.8927283
Snippet The content-based image retrieval (CBIR) systems exploit the visual information present in the images to find a suitable match similar to the human visual...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Autoencoders
CIFAR-10
CIFAR-100
Color
Deep Autoencoder
Deep learning
Feature extraction
Fuzzy Class membership
Image retrieval
Performance analysis
Representation learning
Retrieval
Training
Visualization
Title Learning Deep Latent Representation of Color Images Using Autoencoders for Efficient Image Retrieval
URI https://ieeexplore.ieee.org/document/10958253
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVoxQALX0V8ywNrSmo7sT2ifohKKFSoQ7cqti-oAwlqU34_ZzctMDCwRdHFiuzYfue8946Qe4cQPBc9iCQ3JhLWsigXTkYy1spAzI0AEYpNyCxTs5meNGL1oIUBgEA-g66_DP_yXWXX_qgMZ7hOMKPhLdKSMt2ItXYHKmxjLdMYi2LowzgbjPsvWcqljjETZKK7beBXKZWwk4yO_vkOx6Tzrcmjk91uc0L2oDwlhz_sBM-Ia8xS3-gA4IM-I4wsa_oauK6NxKikVUH7uOAt6fgdl5IVDZwB-riuK29p6WnNFHEsHQZrCf98iMNWfOUt_Cw7ZDoaTvtPUVNFIVpoXkeMaVCOOcZApokT1kkQplCWm5yr3MbAQXofKUSORjpW5ADcSJOqJM0dhp2TdlmVcEGo4A4nbC9RDnGMdlph8iMsIjKXK1ZofUk6vr_mHxufjPm2q67-uH9NDvyoeHJIT9-Qdr1cwy3Zt5_1YrW8C6P7BXKYpkY
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4UTdSLvzD-tgevw9F2tD0ahLCIkxgO3Mi6vhkODgLDv9_XMlAPHrwty1uztGv7ve77vkfIvUUInoomBJIbE4gsY0EqrAxkqJWBkBsBwhebkEmiRiM9qMTqXgsDAJ58Bg136f_l22m2dEdlOMN1hBkN3yY7kRAsXMm1NkcqbGUuU1mLYvBDnDzF7dekxaUOMRdkorFu4lcxFb-XdA__-RZHpP6tyqODzX5zTLagOCEHPwwFT4mt7FLf6RPAjPYRSBYlffNs10pkVNBpTtu45M1p_IGLyYJ61gB9XJZTZ2rpiM0UkSzteHMJ97yPw1Zc7S38MOtk2O0M272gqqMQTDQvA8Y0KMssYyBbkRWZlSBMrjJuUq7SLAQO0jlJIXY00rI8BeBGmpaKWqnFsDNSK6YFnBMquMUp24yURSSjrVaY_ogMMZlNFcu1viB111_j2copY7zuqss_7t-Rvd7wpT_ux8nzFdl3I-SoIk19TWrlfAk3ZDf7LCeL-a0f6S9GmamN
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Annual+IEEE+India+Conference&rft.atitle=Learning+Deep+Latent+Representation+of+Color+Images+Using+Autoencoders+for+Efficient+Image+Retrieval&rft.au=Kale%2C+Mandar&rft.au=Mukhopadhyay%2C+Sudipta&rft.date=2024-12-19&rft.pub=IEEE&rft.eissn=2325-9418&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FINDICON63790.2024.10958253&rft.externalDocID=10958253