Paper Details: Downloads: 630
Serial Number: P1150535167
Title: Color Medical Images Watermarking based Neural Network Segmentation
Authors: H. Seddik and E. Ben Braiek
Abstract: Medical images are usually stored for diagnosis, database or long term storage. They enclose information with different levels of importance. The most important information is located in areas we call Regions Of Importance (ROI). In the storing operation, the ROI must not subject any distortion. The watermarking can be a solution to this problem. In this paper, we propose a digital watermarking method which avoids the distortion of the image data in ROI by embedding signature information into other area than ROI. We apply our method to images corresponding to cancerous cases. We use a neural network to discriminate the different zones and we classify the image in two different zones (timorous and healthy). The watermark is then hidden in the healthy zones to avoid any possible change in the medical diagnosis
Keywords: Watermarking, neural network, color image
Journal/Conference: ICGST Conference on Graphics, Vision and Image Processing, GVIP-05
Volume: 5
Issue:
Submission Date: 9/1/2005 12:00:00 AM
Review Date: 10/1/2005 12:00:00 AM
Publishing Date: 12/19/2005 12:00:00 AM
Article Downloads: 630
Download:

Facebook