A Difference Perceptual Hashing Algorithm for Medical Volume Data Against Local Nonlinear Geometric Attacks

Abstract

Traditional image hashing methods can often only resist traditional global geometric attacks and cannot resist local nonlinear geometric attacks. This has a huge impact on the protection, identification and authentication of three-dimensional medical volume data. In response to these problems, a new difference perceptual hashing algorithm for medical volume data is proposed in this paper. It uses the difference between adjacent elements in each column of the volume data feature matrix to generate a hashing sequence. Experiments show that it has a good ability to resist local nonlinear geometric attacks.