Meaningful Visual Secret Sharing by Genetic Algorithm

in visual secret sharing, the secret image is transformed into several share images and distributed among different people. The share images do not contain any information about the original image, and these images are similar to the noise image. When needed, the original image can be retrieved in the presence of all stakeholders and by stacking the share images. In this regard, the appearance of noisy images may attract the attention of the attackers. To solve this problem, meaningful visual secret sharing was presented. In this article, a method for sharing the image with meaningful shares is introduced. There are a number of hyper parameters in the proposed algorithm. To improve performance, an attempt has been made to determine these hyper parameters using a genetic algorithm. The cost function of the genetic algorithm is the difference between the two values of the correct number of bits of the recovered image and the original image and the correct number of integer bits between the cover image and the shares. The proposed method was evaluated using PSNR, MSE, BCR criteria and presented good results on different images with different number of shares.