The Development of Image Classification Algorithms Based on CNNs

Qichang Liu

doi:10.54097/hset.v34i.5484

Authors

Qichang Liu

DOI:

https://doi.org/10.54097/hset.v34i.5484

Keywords:

Image classification, CNN, Deep Learning

Abstract

Image classification is a method to process the given images by picking up the distinct features of different kinds of images to distinguish different targets in the image. The classification of images analyzes the given images quantitatively by using computers and divides the image or areas contained in the image into several categories instead of explaining them by human’s visualization. Image classification is an important research direction in computer vision technology and the basis for other applications such as image detection, behavior analysis, and object tracking. With the arrival of big data and the improvement of computer power, Deep Learning (DL) has swept the world, and the Convolutional Neural Network (CNN) image classification method has broken down the limitations of traditional image classification methods and has become a currently mainstream image classification algorithm. Thereinto, some typical architectures e.g., MobileNet, ResNet and VGG are attracted a lot of attention. This paper will review the development of the image classification and introduce some typical CNNs.

Downloads

Download data is not yet available.

References

Yang Z et al. Review of Image Classification Algorithms Based on Convolutional Neural Networks [J]. JOURNAL OF SIGNAL PROCESSING, 2018,34(12):1475-1489.

Hu M et al. Image Classification Method based on Modified Convolutional Neural Network [J]. Communications Technology,2018,51(11):2594-2600.

Han B Zero-based entry deep learning (4) - convolutional neural network [Z]. (2014). https://www.zybuluo.com/hanbingtao/note/485480

Ji C et al. Review of image classification algorithms based on convolutional neural network [J]. Journal of Computer Applications, 2022, 42(4): 1044-1049.

Alex K et al. ImageNet Classification with Deep Convolutional Neural Networks [J]. Communications of the ACM, 2017, 60(6): 84-90.

Szegedy C et al. Going Deeper with Convolutions [R]. arXiv, (2014).

He K et al. Deep Residual Learning for Image Recognition [R]. arXiv. 2015.

Howard A G et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [R]. 2017

Vaswani A et al. Attention is all you need [C], Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc., 2017.

Dosovitskiy, A et al. An image is worth 16x16 words: Transformers for image recognition at scale [R]. arXiv preprint arXiv:2010.11929, 2020.