Review of Image Classification Algorithms Based on Convolutional Neural Networks

Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN architecture...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Leiyu Chen, Shaobo Li, Qiang Bai, Jing Yang, Sanlong Jiang, Yanming Miao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	image classification convolutional neural networks deep learning Science Q
Acceso en línea:	https://doaj.org/article/d6e42026eaa94282b4031eb188df3fb5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d6e42026eaa94282b4031eb188df3fb5
record_format	dspace
spelling	oai:doaj.org-article:d6e42026eaa94282b4031eb188df3fb52021-11-25T18:55:40ZReview of Image Classification Algorithms Based on Convolutional Neural Networks10.3390/rs132247122072-4292https://doaj.org/article/d6e42026eaa94282b4031eb188df3fb52021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4712https://doaj.org/toc/2072-4292Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. In the wake of these successes, CNN-based methods have emerged in remote sensing image scene classification and achieved advanced classification accuracy. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art (SOAT) network architectures. Along the way, we analyze (1) the basic structure of artificial neural networks (ANNs) and the basic network layers of CNNs, (2) the classic predecessor network models, (3) the recent SOAT network algorithms, (4) comprehensive comparison of various image classification methods mentioned in this article. Finally, we have also summarized the main analysis and discussion in this article, as well as introduce some of the current trends.Leiyu ChenShaobo LiQiang BaiJing YangSanlong JiangYanming MiaoMDPI AGarticleimage classificationconvolutional neural networksdeep learningScienceQENRemote Sensing, Vol 13, Iss 4712, p 4712 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	image classification convolutional neural networks deep learning Science Q
spellingShingle	image classification convolutional neural networks deep learning Science Q Leiyu Chen Shaobo Li Qiang Bai Jing Yang Sanlong Jiang Yanming Miao Review of Image Classification Algorithms Based on Convolutional Neural Networks
description	Image classification has always been a hot research direction in the world, and the emergence of deep learning has promoted the development of this field. Convolutional neural networks (CNNs) have gradually become the mainstream algorithm for image classification since 2012, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. In the wake of these successes, CNN-based methods have emerged in remote sensing image scene classification and achieved advanced classification accuracy. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art (SOAT) network architectures. Along the way, we analyze (1) the basic structure of artificial neural networks (ANNs) and the basic network layers of CNNs, (2) the classic predecessor network models, (3) the recent SOAT network algorithms, (4) comprehensive comparison of various image classification methods mentioned in this article. Finally, we have also summarized the main analysis and discussion in this article, as well as introduce some of the current trends.
format	article
author	Leiyu Chen Shaobo Li Qiang Bai Jing Yang Sanlong Jiang Yanming Miao
author_facet	Leiyu Chen Shaobo Li Qiang Bai Jing Yang Sanlong Jiang Yanming Miao
author_sort	Leiyu Chen
title	Review of Image Classification Algorithms Based on Convolutional Neural Networks
title_short	Review of Image Classification Algorithms Based on Convolutional Neural Networks
title_full	Review of Image Classification Algorithms Based on Convolutional Neural Networks
title_fullStr	Review of Image Classification Algorithms Based on Convolutional Neural Networks
title_full_unstemmed	Review of Image Classification Algorithms Based on Convolutional Neural Networks
title_sort	review of image classification algorithms based on convolutional neural networks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d6e42026eaa94282b4031eb188df3fb5
work_keys_str_mv	AT leiyuchen reviewofimageclassificationalgorithmsbasedonconvolutionalneuralnetworks AT shaoboli reviewofimageclassificationalgorithmsbasedonconvolutionalneuralnetworks AT qiangbai reviewofimageclassificationalgorithmsbasedonconvolutionalneuralnetworks AT jingyang reviewofimageclassificationalgorithmsbasedonconvolutionalneuralnetworks AT sanlongjiang reviewofimageclassificationalgorithmsbasedonconvolutionalneuralnetworks AT yanmingmiao reviewofimageclassificationalgorithmsbasedonconvolutionalneuralnetworks
_version_	1718410555988901888

Review of Image Classification Algorithms Based on Convolutional Neural Networks

Ejemplares similares