Development of convolutional neural network and its application in image classification: a survey

Wei Wang; Yujing Yang; Xin Wang; Weizheng Wang; Ji Li

doi:10.1117/1.OE.58.4.040901

11 April 2019 Development of convolutional neural network and its application in image classification: a survey

Wei Wang, Yujing Yang, Xin Wang, Weizheng Wang, Ji Li

Author Affiliations +

Optical Engineering, Vol. 58, Issue 4, 040901 (April 2019). https://doi.org/10.1117/1.OE.58.4.040901

Abstract

In recent years, convolutional neural networks (CNNs) have been widely used in various computer visual recognition tasks and have achieved good results compared with traditional methods. Image classification is one of the basic and important tasks of visual recognition, 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. We first summarize the development history of CNNs and then analyze the architecture of various deep CNNs in image classification. Furthermore, not only the innovation of the network architecture is beneficial to the results of image classification, but also the improvement of the network optimization method or training method has improved the result of image classification. We also analyze each of these methods’ effect. The experimental results of various methods are compared. Finally, the development of future CNNs is prospected.

Citation Download Citation

Wei Wang, Yujing Yang, Xin Wang, Weizheng Wang, and Ji Li "Development of convolutional neural network and its application in image classification: a survey," Optical Engineering 58(4), 040901 (11 April 2019). https://doi.org/10.1117/1.OE.58.4.040901

Received: 3 November 2018; Accepted: 12 March 2019; Published: 11 April 2019

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
19 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

CITATIONS

Cited by 141 scholarly publications.

Explore citations on Lens.org

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Image classification

Convolutional neural networks

Neural networks

Visualization

Data modeling

Network architectures

Show All Keywords

RELATED CONTENT

Attention based two stream high resolution networks for building damage...
Proceedings of SPIE (May 27 2022)

Detection method of a goat in a natural scene based...
Proceedings of SPIE (October 09 2022)

Research on side channel attack based on bagging ensemble strategy
Proceedings of SPIE (September 07 2022)

The influence of different parameters on classical neural network fitting
Proceedings of SPIE (January 12 2023)

A comparison study between MLP and convolutional neural network models...
Proceedings of SPIE (May 01 2017)

Refined image colorization using capsule generative adversarial networks
Proceedings of SPIE (January 31 2020)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years