Cargando…

Deep convolutional neural networks for regular texture recognition

Regular textures are frequently found in man-made environments and some biological and physical images. There are a wide range of applications for recognizing and locating regular textures. In this work, we used deep convolutional neural networks (CNNs) as a general method for modelling and classify...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Ni, Rogers, Mitchell, Cui, Hua, Liu, Weiyu, Li, Xizhi, Delmas, Patrice
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044313/
https://www.ncbi.nlm.nih.gov/pubmed/35494803
http://dx.doi.org/10.7717/peerj-cs.869
_version_ 1784695079299973120
author Liu, Ni
Rogers, Mitchell
Cui, Hua
Liu, Weiyu
Li, Xizhi
Delmas, Patrice
author_facet Liu, Ni
Rogers, Mitchell
Cui, Hua
Liu, Weiyu
Li, Xizhi
Delmas, Patrice
author_sort Liu, Ni
collection PubMed
description Regular textures are frequently found in man-made environments and some biological and physical images. There are a wide range of applications for recognizing and locating regular textures. In this work, we used deep convolutional neural networks (CNNs) as a general method for modelling and classifying regular and irregular textures. We created a new regular texture database and investigated two sets of deep CNNs-based methods for regular and irregular texture classification. First, the classic CNN models (e.g. inception, residual network, etc.) were used in a standard way. These two-class CNN classifiers were trained by fine-tuning networks using our new regular texture database. Next, we transformed the trained filter features of the last convolutional layer into a vector representation using Fisher Vector pooling (FV). Such representations can be efficiently used for a wide range of machine learning tasks such as classification or clustering, thus more transferable from one domain to another. Our experiments show that the standard CNNs attained sufficient accuracy for regular texture recognition tasks. The Fisher representations combined with support vector machine (SVM) also showed high performance for regular and irregular texture classification. We also find CNNs performs sub-optimally for long-range patterns, despite the fact that their fully-connected layers pool local features into a global image representation.
format Online
Article
Text
id pubmed-9044313
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-90443132022-04-28 Deep convolutional neural networks for regular texture recognition Liu, Ni Rogers, Mitchell Cui, Hua Liu, Weiyu Li, Xizhi Delmas, Patrice PeerJ Comput Sci Artificial Intelligence Regular textures are frequently found in man-made environments and some biological and physical images. There are a wide range of applications for recognizing and locating regular textures. In this work, we used deep convolutional neural networks (CNNs) as a general method for modelling and classifying regular and irregular textures. We created a new regular texture database and investigated two sets of deep CNNs-based methods for regular and irregular texture classification. First, the classic CNN models (e.g. inception, residual network, etc.) were used in a standard way. These two-class CNN classifiers were trained by fine-tuning networks using our new regular texture database. Next, we transformed the trained filter features of the last convolutional layer into a vector representation using Fisher Vector pooling (FV). Such representations can be efficiently used for a wide range of machine learning tasks such as classification or clustering, thus more transferable from one domain to another. Our experiments show that the standard CNNs attained sufficient accuracy for regular texture recognition tasks. The Fisher representations combined with support vector machine (SVM) also showed high performance for regular and irregular texture classification. We also find CNNs performs sub-optimally for long-range patterns, despite the fact that their fully-connected layers pool local features into a global image representation. PeerJ Inc. 2022-02-09 /pmc/articles/PMC9044313/ /pubmed/35494803 http://dx.doi.org/10.7717/peerj-cs.869 Text en © 2022 Liu et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Liu, Ni
Rogers, Mitchell
Cui, Hua
Liu, Weiyu
Li, Xizhi
Delmas, Patrice
Deep convolutional neural networks for regular texture recognition
title Deep convolutional neural networks for regular texture recognition
title_full Deep convolutional neural networks for regular texture recognition
title_fullStr Deep convolutional neural networks for regular texture recognition
title_full_unstemmed Deep convolutional neural networks for regular texture recognition
title_short Deep convolutional neural networks for regular texture recognition
title_sort deep convolutional neural networks for regular texture recognition
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9044313/
https://www.ncbi.nlm.nih.gov/pubmed/35494803
http://dx.doi.org/10.7717/peerj-cs.869
work_keys_str_mv AT liuni deepconvolutionalneuralnetworksforregulartexturerecognition
AT rogersmitchell deepconvolutionalneuralnetworksforregulartexturerecognition
AT cuihua deepconvolutionalneuralnetworksforregulartexturerecognition
AT liuweiyu deepconvolutionalneuralnetworksforregulartexturerecognition
AT lixizhi deepconvolutionalneuralnetworksforregulartexturerecognition
AT delmaspatrice deepconvolutionalneuralnetworksforregulartexturerecognition