Images compression for medical diagnosis using neural networks
- 1 archivo (603,2 KB)
Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
Images compression is a widely studied topic. Conventional situations offer variable compression ratios depending on the image in question and, in general, do not yield good results for images that are rich in tones. This work is an application o f i mages compression o f patient's computed tomographies using neural networks, which allows to carry out both compression and decompression of the images with a fixed ratio of 8:1 and a loss of 2%.
DIF-M6848
INTELIGENCIA ARTIFICIAL REDES NEURONALES SISTEMAS DE PROCESAMIENTO DE IMÁGENES CIENCIAS MÉDICAS Y DE LA VIDA