A New Method of Image Encryption/Decryption via Voice Features

Abstract

A new framework of image encryption via voice feature is proposed. Voice data is preprocessed and the MFCC coefficients are firstly calculated on each sub-frame; an iterated vector quantization is then applied on the MFCC data to obtain the key to image encryption and decryption. Image encryption and decryption is done in the frequency domain with a simple XOR operation. Due to the uniqueness and long length of the encryption key, along with the frequency domain encryption, the safeness of the whole system is assured.