Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation

Automatic image annotation is an active field of research in which a set of annotations are automatically assigned to images based on their content. In literature, some works opted for handcrafted features and manual approaches of linking concepts to images, whereas some others involved convolutiona...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ramla Bensaci, Belal Khaldi, Oussama Aiadi, Ayoub Benchabana
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	automatic image annotation image segmentation region annotation image content understanding Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/77652e2b4eb5473cae5966e5af81d21a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:77652e2b4eb5473cae5966e5af81d21a
record_format	dspace
spelling	oai:doaj.org-article:77652e2b4eb5473cae5966e5af81d21a2021-11-11T15:14:01ZDeep Convolutional Neural Network with KNN Regression for Automatic Image Annotation10.3390/app1121101762076-3417https://doaj.org/article/77652e2b4eb5473cae5966e5af81d21a2021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10176https://doaj.org/toc/2076-3417Automatic image annotation is an active field of research in which a set of annotations are automatically assigned to images based on their content. In literature, some works opted for handcrafted features and manual approaches of linking concepts to images, whereas some others involved convolutional neural networks (CNNs) as black boxes to solve the problem without external interference. In this work, we introduce a hybrid approach that combines the advantages of both CNN and the conventional concept-to-image assignment approaches. J-image segmentation (JSEG) is firstly used to segment the image into a set of homogeneous regions, then a CNN is employed to produce a rich feature descriptor per area, and then, vector of locally aggregated descriptors (VLAD) is applied to the extracted features to generate compact and unified descriptors. Thereafter, the not too deep clustering (N2D clustering) algorithm is performed to define local manifolds constituting the feature space, and finally, the semantic relatedness is calculated for both image–concept and concept–concept using KNN regression to better grasp the meaning of concepts and how they relate. Through a comprehensive experimental evaluation, our method has indicated a superiority over a wide range of recent related works by yielding F1 scores of 58.89% and 80.24% with the datasets Corel 5k and MSRC v2, respectively. Additionally, it demonstrated a relatively high capacity of learning more concepts with higher accuracy, which results in N+ of 212 and 22 with the datasets Corel 5k and MSRC v2, respectively.Ramla BensaciBelal KhaldiOussama AiadiAyoub BenchabanaMDPI AGarticleautomatic image annotationimage segmentationregion annotationimage content understandingTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10176, p 10176 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	automatic image annotation image segmentation region annotation image content understanding Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	automatic image annotation image segmentation region annotation image content understanding Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Ramla Bensaci Belal Khaldi Oussama Aiadi Ayoub Benchabana Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
description	Automatic image annotation is an active field of research in which a set of annotations are automatically assigned to images based on their content. In literature, some works opted for handcrafted features and manual approaches of linking concepts to images, whereas some others involved convolutional neural networks (CNNs) as black boxes to solve the problem without external interference. In this work, we introduce a hybrid approach that combines the advantages of both CNN and the conventional concept-to-image assignment approaches. J-image segmentation (JSEG) is firstly used to segment the image into a set of homogeneous regions, then a CNN is employed to produce a rich feature descriptor per area, and then, vector of locally aggregated descriptors (VLAD) is applied to the extracted features to generate compact and unified descriptors. Thereafter, the not too deep clustering (N2D clustering) algorithm is performed to define local manifolds constituting the feature space, and finally, the semantic relatedness is calculated for both image–concept and concept–concept using KNN regression to better grasp the meaning of concepts and how they relate. Through a comprehensive experimental evaluation, our method has indicated a superiority over a wide range of recent related works by yielding F1 scores of 58.89% and 80.24% with the datasets Corel 5k and MSRC v2, respectively. Additionally, it demonstrated a relatively high capacity of learning more concepts with higher accuracy, which results in N+ of 212 and 22 with the datasets Corel 5k and MSRC v2, respectively.
format	article
author	Ramla Bensaci Belal Khaldi Oussama Aiadi Ayoub Benchabana
author_facet	Ramla Bensaci Belal Khaldi Oussama Aiadi Ayoub Benchabana
author_sort	Ramla Bensaci
title	Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
title_short	Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
title_full	Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
title_fullStr	Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
title_full_unstemmed	Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation
title_sort	deep convolutional neural network with knn regression for automatic image annotation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/77652e2b4eb5473cae5966e5af81d21a
work_keys_str_mv	AT ramlabensaci deepconvolutionalneuralnetworkwithknnregressionforautomaticimageannotation AT belalkhaldi deepconvolutionalneuralnetworkwithknnregressionforautomaticimageannotation AT oussamaaiadi deepconvolutionalneuralnetworkwithknnregressionforautomaticimageannotation AT ayoubbenchabana deepconvolutionalneuralnetworkwithknnregressionforautomaticimageannotation
_version_	1718436381948116992

Deep Convolutional Neural Network with KNN Regression for Automatic Image Annotation

Ejemplares similares