Image compression based on the neural network art |
| |
| Authors: | O. G. Rudenko M. S. Snytkin |
| |
| Affiliation: | (1) Kharkov National University of Radio Electronics, Kharkov, Ukraine |
| |
| Abstract: | JPEG-similar algorithms are proposed for compressing video information. These algorithms are based on the ART neural network that realizes the vector quantization operation. The results of modelling the proposed algorithms in the Matlab environment testify to the possibility of using them for image compression. These algorithms are shown to be good enough for images with recurrent segments. Translated from Kibernetika i Sistemnyi Analiz, No. 6, pp. 10–16, November–December 2008. |
| |
| Keywords: | ART neural network compression algorithm vector quantization discrete cosine transform training |
| 本文献已被 SpringerLink 等数据库收录！ |
