A Textual Information Detection and Elimination System
for Secure Medical Image Distribution

James Ze Wang, Michel Bilello, Gio Wiederhold
Stanford University, Stanford, CA 94305

Before medical images can be distributed online, it is necessary for confidentiality reasons to eliminate text that appears in the image. This paper describes TIDE (Textual Information Detection and Elimination) system for secure medical image distribution. The algorithm uses Daubechies' wavelets to detect and eliminate areas of textual information within digital medical images. The system is practical for real-world applications, processing each 512x512 image in about 10 seconds. Besides its exceptional speed, the algorithm has demonstrated a remarkable accuracy when tested on various types of medical images, including X-ray and CT scans.

Full Paper in Color
(PostScript)    (PDF)

Color Figures

Copyright 1997 AMIA. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the AMIA.

Last Modified: 11-Mar-97 23:09:15 PST
1997, James Z. Wang