A Survey of Image Classification Algorithms based on Convolution Neural Network

Ruofan Mo

doi:10.54097/hset.v15i.2222

Authors

Ruofan Mo

DOI:

https://doi.org/10.54097/hset.v15i.2222

Keywords:

Deep Learning; Convolutional Neural Network; Image Classification; Feature Extraction.

Abstract

With the deep learning (DL) sweeping the world. Traditional image classification methods are difficult to process huge image data and cannot meet people's requirements for image classification accuracy and speed. The image classification method based on convolutional neural network (CNN) breaks through the bottle neck of traditional image classification methods and becomes the mainstream algorithm of image classification at present, how to effectively use convolutional neural network to classify images has become a hot research topic in the field of computer vision at home and abroad. Convolutional neural network (CNN) has performed well in image classification and segmentation, target detection and other applications, and its powerful feature learning and feature expression capabilities are increasingly respected by researchers. However, CNN still has a few problems, such as incomplete feature extraction and overfitting of sample training. In view of these problems, after in-depth research on the application of convolutional neural network in image processing, this paper gives the mainstream structure model, advantages and disadvantages, time/space complexity, problems that may be encountered in the model training process and corresponding solutions used in image classification based on convolutional neural network. Through the overview of the research status of CNN model in image classification, it provides suggestions for the further development and research direction of CNN.

Downloads

Download data is not yet available.

References

HUANG B, HE B Y, WU L N, et al. A deep learning approach to detecting ships from high-resolution aerial remote sensing images[J]. Journal of Coastal Research,2020,111(SI):16-20.

FU K S, ROSENFELD. Pattern recognition and image processing[J]. IEEE Transactions on Computers, 1976, C-25(12):1336-1346.

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.

HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37

HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE,2016:770-778.

HOWARD A G, ZHU M L, CHEN B, et al. Mobile Nets: efficient convolutional neural networks for mobile vision applications [EB/OL]. (2017-04-17) [2021-06-20]. https://arxiv. org/pdf/1704. 04861. pdf.

ZHANG L, WANG X S, YANG D, et al. Generalizing deep learning for medical image segmentation to unseen domains via deep stacked transformation[J]. IEEE Transactions on Medical Imaging, 2020,39(7):2531-2540.

Kong Lingjun, Wang Qiwen, Bao Yunchao, etc. A review of medical image segmentation based on in-depth learning [J]. Radio Communications Technology,2021,47(2):121-130. (KONG L J, WANG Q W, BAO Y C, et al. A survey on medical image segmentation based on deep learning[J]. Radio Communications Technology,2021,47(2):121-130.)

Tian Jin, Yuan Jiazhen, Liu Hongzhe. Lane line detection and adaptive fitting algorithm based on instance segmentation [J]. Computer application, 2020,40(7):1932-1937(TIAN J, YUAN J Z, LIU H Z. Instance segmentation-based lane line detection and adaptive fitting algorithm[J]. Journal of Computer Applications, 2020,40(7):1932-1937)

Fan Wei, Liu Ting, Huang Rui, etc. Image Instance Segmentation Method Assisted by Low Level Features of Convolution Neural Network [J]. Computer Science,2020,47(11):186-191(FAN W, LIU T, HUANG R, et al. Low-level CNN feature aided image instance segmentation[J]. Computer Science, 2020,47 (11): 186-191.

VASWANI A, SHAZEER N, PARMAR N, 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. 2017:6000-6010.

DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale [EB/OL]. (2021-06-03) [2021-06-20]. https://arxiv. org/pdf/ 2010. 11929. pdf.

TOUVRON H, CORD M, DOUZE M, et al. Training dataefficient image transformers & distillation through attention[C]// Proceedings of the 38th International Conference on Machine Learning. New York: JMLR. org,2021:10347-10357.

XU B, WANG N Y, CHEN T Q, et al. Empirical evaluation of rectified activations in convolutional network [EB/OL]. (2015-11- 27) [2021-06-20]. https://arxiv. org/pdf/1505. 00853. pdf.

CLEVERT D A, UNTERTHINER T, HOCHREITER S. Fast and accurate deep network learning by Exponential Linear Units (ELUs)[EB/OL]. (2016-02-22) [2021-06-20]. https://arxiv. org/ pdf/1511. 07289. pdf.

MAAS A L, HANNUN A Y, NG A Y. Rectifier nonlinearities improve neural network acoustic models [C/OL]// Proceedings of the 30th International Conference on Machine Learning. [2021-06- 20. https://ai. stanford. edu/~amaas/papers/relu_hybrid_icml201 3_final. pdf.