Cargando…

An Efficient Supervised Deep Hashing Method for Image Retrieval

In recent years, searching and retrieving relevant images from large databases has become an emerging challenge for the researcher. Hashing methods that mapped raw data into a short binary code have attracted increasing attention from the researcher. Most existing hashing approaches map samples to a...

Descripción completa

Detalles Bibliográficos
Autores principales: Hussain, Abid, Li, Heng-Chao, Ali, Muqadar, Wali, Samad, Hussain, Mehboob, Rehman, Amir
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9601888/
https://www.ncbi.nlm.nih.gov/pubmed/37420445
http://dx.doi.org/10.3390/e24101425
_version_ 1784817175550230528
author Hussain, Abid
Li, Heng-Chao
Ali, Muqadar
Wali, Samad
Hussain, Mehboob
Rehman, Amir
author_facet Hussain, Abid
Li, Heng-Chao
Ali, Muqadar
Wali, Samad
Hussain, Mehboob
Rehman, Amir
author_sort Hussain, Abid
collection PubMed
description In recent years, searching and retrieving relevant images from large databases has become an emerging challenge for the researcher. Hashing methods that mapped raw data into a short binary code have attracted increasing attention from the researcher. Most existing hashing approaches map samples to a binary vector via a single linear projection, which restricts the flexibility of those methods and leads to optimization problems. We introduce a CNN-based hashing method that uses multiple nonlinear projections to produce additional short-bit binary code to tackle this issue. Further, an end-to-end hashing system is accomplished using a convolutional neural network. Also, we design a loss function that aims to maintain the similarity between images and minimize the quantization error by providing a uniform distribution of the hash bits to illustrate the proposed technique’s effectiveness and significance. Extensive experiments conducted on various datasets demonstrate the superiority of the proposed method in comparison with state-of-the-art deep hashing methods.
format Online
Article
Text
id pubmed-9601888
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96018882022-10-27 An Efficient Supervised Deep Hashing Method for Image Retrieval Hussain, Abid Li, Heng-Chao Ali, Muqadar Wali, Samad Hussain, Mehboob Rehman, Amir Entropy (Basel) Article In recent years, searching and retrieving relevant images from large databases has become an emerging challenge for the researcher. Hashing methods that mapped raw data into a short binary code have attracted increasing attention from the researcher. Most existing hashing approaches map samples to a binary vector via a single linear projection, which restricts the flexibility of those methods and leads to optimization problems. We introduce a CNN-based hashing method that uses multiple nonlinear projections to produce additional short-bit binary code to tackle this issue. Further, an end-to-end hashing system is accomplished using a convolutional neural network. Also, we design a loss function that aims to maintain the similarity between images and minimize the quantization error by providing a uniform distribution of the hash bits to illustrate the proposed technique’s effectiveness and significance. Extensive experiments conducted on various datasets demonstrate the superiority of the proposed method in comparison with state-of-the-art deep hashing methods. MDPI 2022-10-07 /pmc/articles/PMC9601888/ /pubmed/37420445 http://dx.doi.org/10.3390/e24101425 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hussain, Abid
Li, Heng-Chao
Ali, Muqadar
Wali, Samad
Hussain, Mehboob
Rehman, Amir
An Efficient Supervised Deep Hashing Method for Image Retrieval
title An Efficient Supervised Deep Hashing Method for Image Retrieval
title_full An Efficient Supervised Deep Hashing Method for Image Retrieval
title_fullStr An Efficient Supervised Deep Hashing Method for Image Retrieval
title_full_unstemmed An Efficient Supervised Deep Hashing Method for Image Retrieval
title_short An Efficient Supervised Deep Hashing Method for Image Retrieval
title_sort efficient supervised deep hashing method for image retrieval
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9601888/
https://www.ncbi.nlm.nih.gov/pubmed/37420445
http://dx.doi.org/10.3390/e24101425
work_keys_str_mv AT hussainabid anefficientsuperviseddeephashingmethodforimageretrieval
AT lihengchao anefficientsuperviseddeephashingmethodforimageretrieval
AT alimuqadar anefficientsuperviseddeephashingmethodforimageretrieval
AT walisamad anefficientsuperviseddeephashingmethodforimageretrieval
AT hussainmehboob anefficientsuperviseddeephashingmethodforimageretrieval
AT rehmanamir anefficientsuperviseddeephashingmethodforimageretrieval
AT hussainabid efficientsuperviseddeephashingmethodforimageretrieval
AT lihengchao efficientsuperviseddeephashingmethodforimageretrieval
AT alimuqadar efficientsuperviseddeephashingmethodforimageretrieval
AT walisamad efficientsuperviseddeephashingmethodforimageretrieval
AT hussainmehboob efficientsuperviseddeephashingmethodforimageretrieval
AT rehmanamir efficientsuperviseddeephashingmethodforimageretrieval