Encrypted Image Feature Extraction by Privacy-Preserving MFS
Guoming Chen, Qiang Chen, Xiongyong Zhu, Yiqun Chen · 2018
Privacy preserve machine learning is a hot topic in multimedia domain. In this paper, we propose a secure multifractal feature extraction and representation method in the encrypted domain. We first use chaotic sequence to scramble the image in a block wise way, then according to the characteristic of chaotic sequence which preserves locally the randomness and maintain special periodicity we propose a multifractal feature extraction method in the encrypted domain. Experimental results showed that multifractal feature has a good distinguish ability in the encrypted domain.