Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning

We propose a novel multiple query retrieval approach, named weight-learner, which relies on visual feature discrimination to estimate the distances between the query images and images in the database. For each query image, this discrimination consists of learning, in an unsupervised manner, the opti...

Full description

Bibliographic Details
Main Authors:	Abeer Al-Mohamade, Ouiem Bchir, Mohamed Maher Ben Ismail
Format:	Article
Language:	English
Published:	MDPI AG 2020-01-01
Series:	Journal of Imaging
Subjects:	content-based image retrieval multiple query visual feature weight learning
Online Access:	https://www.mdpi.com/2313-433X/6/1/2

id	doaj-ab78595441434f118b93f99bbd2eba35
record_format	Article
spelling	doaj-ab78595441434f118b93f99bbd2eba352020-11-25T02:20:56ZengMDPI AGJournal of Imaging2313-433X2020-01-0161210.3390/jimaging6010002jimaging6010002Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight LearningAbeer Al-Mohamade0Ouiem Bchir1Mohamed Maher Ben Ismail2Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11362, Saudi ArabiaComputer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11362, Saudi ArabiaComputer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh 11362, Saudi ArabiaWe propose a novel multiple query retrieval approach, named weight-learner, which relies on visual feature discrimination to estimate the distances between the query images and images in the database. For each query image, this discrimination consists of learning, in an unsupervised manner, the optimal relevance weight for each visual feature/descriptor. These feature relevance weights are designed to reduce the semantic gap between the extracted visual features and the user’s high-level semantics. We mathematically formulate the proposed solution through the minimization of some objective functions. This optimization aims to produce optimal feature relevance weights with respect to the user query. The proposed approach is assessed using an image collection from the Corel database.https://www.mdpi.com/2313-433X/6/1/2content-based image retrievalmultiple queryvisual featureweight learning
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Abeer Al-Mohamade Ouiem Bchir Mohamed Maher Ben Ismail
spellingShingle	Abeer Al-Mohamade Ouiem Bchir Mohamed Maher Ben Ismail Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning Journal of Imaging content-based image retrieval multiple query visual feature weight learning
author_facet	Abeer Al-Mohamade Ouiem Bchir Mohamed Maher Ben Ismail
author_sort	Abeer Al-Mohamade
title	Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning
title_short	Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning
title_full	Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning
title_fullStr	Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning
title_full_unstemmed	Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning
title_sort	multiple query content-based image retrieval using relevance feature weight learning
publisher	MDPI AG
series	Journal of Imaging
issn	2313-433X
publishDate	2020-01-01
description	We propose a novel multiple query retrieval approach, named weight-learner, which relies on visual feature discrimination to estimate the distances between the query images and images in the database. For each query image, this discrimination consists of learning, in an unsupervised manner, the optimal relevance weight for each visual feature/descriptor. These feature relevance weights are designed to reduce the semantic gap between the extracted visual features and the user’s high-level semantics. We mathematically formulate the proposed solution through the minimization of some objective functions. This optimization aims to produce optimal feature relevance weights with respect to the user query. The proposed approach is assessed using an image collection from the Corel database.
topic	content-based image retrieval multiple query visual feature weight learning
url	https://www.mdpi.com/2313-433X/6/1/2
work_keys_str_mv	AT abeeralmohamade multiplequerycontentbasedimageretrievalusingrelevancefeatureweightlearning AT ouiembchir multiplequerycontentbasedimageretrievalusingrelevancefeatureweightlearning AT mohamedmaherbenismail multiplequerycontentbasedimageretrievalusingrelevancefeatureweightlearning
_version_	1724868842782457856

Multiple Query Content-Based Image Retrieval Using Relevance Feature Weight Learning

Similar Items