Research on the Application of RBF Neural Network in Image Compression
Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China
Proceedings: ICMLCA 2021
Pages: 5Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Liu, Fang; Wang, Tianyun; Cheng, Mowen (School of Information Science and Engineering, Shenyang Ligong University, Shenyang, China)
Feng, Yongxin (Graduate School, Shenyang Ligong University, Shenyang, China)
Abstract:
In contemporary life, a large number of images need to be stored and transmitted. In order to save transmission resources and improve transmission speed, image compression is particularly important, and the application of intelligent algorithms such as neural networks provides new ideas and methods for image compression. Considering the serious block effect of traditional BP neural network in image compression and the poor performance of compression rate, RBF radial basis neural network quantization image compression method (RQIC) is proposed. After testing, RQIC has the ability to quickly locate the optimal number of nodes in the hidden layer relative to the traditional BP neural network compression algorithm and can reduce the block effect and improve the compression rate by about 0.05 under the premise of similar PSNR.