Design of Four Image Recognition Algorithms based on Convolutional Neural Network

Guangcai Zhang

《International Core Journal of Engineering》 8卷8期 (2022/08) Pp. 856-860

https://doi.org/10.6919/ICJE.202208_8(8).0116

摘要

This paper describes the basic process of digital recognition system in terms of data extraction and pre-processing, feature extraction and selection, and classifier design. Several main classification algorithms such as minimum distance method, nearest neighbor method, K-nearest neighbor method and BP neural network are focused on, and the recognition rates of different algorithms are analyzed by MATLAB simulation experiments.

關鍵字

Minimum Distance Method ； Nearest Neighbor Method ； K-nearest Neighbor Method ； BP Neural Network

參考文獻

Mcculloch W S , Pitts W . A Logical Calculus of the Ideas Immanent in Nervous Activity[J]. Bulletin of Mathematical Biology, 1943, 52(1–2):99-115.

Rumelhart D E , Hinton G E , Williams R J . Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.

Huang H K, Chiu C F, Kuo C H, et al. Mixture of deep CNN-based ensemble model for image retrieval [C]// 2016.

Tara N. Sainath, Oriol Vinyals, Andrew Senior, et al. Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks[C]// 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2015.

N.B. Karayiannis. Gradient descent learning of radial basis neural networks[C]// Neural Networks,1997. International Conference on. IEEE, 1997.