Comparison between JPEG and a New Neural Compression Method for Digitized Mammograms
暂无分享,去创建一个
This paper presents the development and evaluation of a new lossy neural-based compression algorithm for digitized mammograms. The influence of the neural compression method on the mammographic image is not perceptible to a mammogram reader up to a high compression rate. Compared with JPEG the achieved image quality based on the proposed method is much better.
[1] Thomas Martinetz,et al. 'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.
[2] William A. Pearlman,et al. A new, fast, and efficient image codec based on set partitioning in hierarchical trees , 1996, IEEE Trans. Circuits Syst. Video Technol..
[3] Erkki Oja,et al. Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..