Normalization schemes in a neural network image compression algorithm

✍ Scribed by Doron Kornreich; Yaniv Benbenisti; H.B. Mitchell; Paul Schaefer

• Publisher: Elsevier Science
• Year: 1997
• Tongue: English
• Weight: 822 KB
• Volume: 10
• Category: Article
• ISSN: 0923-5965
• DOI: 10.1016/s0923-5965(96)00024-0

✦ Synopsis

Recently multilayer neural networks have been used for still picture compression. In these networks it is necessary to normalize the gray levels in the input picture before they are fed into the neural network. In this paper we investigate six different normalization functions, of which four are new and appear for the first time in this paper. We show that the compression efficiency of a neural network depends on the normalization function used and that the new normalization functions consistently outperform the traditional normalization functions. 0 1997 Elsevier Science B.V.