Image Encryption Using Genetic Algorithm

This paper presents a new method for imageencryption using Genetic algorithm (GA). First, rows andcolumns of the input image are dislocated randomly. Then, theobtained image is divided into four equal sized sub-images. Afterselecting one of these sub-images accidentally, two pixels arechosen from it as GA initial population. Cross-over andmutation operations are applied on the binary values of theselected pixels. Then the image is reconstructed in the reversemanner. If entropy of the result image increases, the current subimageis utilized for the next step. Otherwise, another sub-imagesis chosen randomly and the same process is applied. Randomnessof the encrypted image is measured by entropy, correlationcoefficients and histogram analysis. Experimental results showthat the proposed method can be used effectively for imageencryption.

کلیدواژه ها:

image encryption ، genetic algorithm ، image entropy ، correlation coefficients ، histogram analysis