Feed Forward Networks in Color Extended Visual Cryptography to Generate Meaningful Shares

Abstract

Conventional visual secret sharing schemes generate noise-like random pixels on shares to hide secret images. It suffers a management problem, because of which dealers cannot visually identify each share. This problem is solved by the Extended Visual Cryptography Scheme (EVCS), which adds a meaningful cover image in each share. However, the previous approaches involving the EVCS for color images suffer from a pixel expansion problem. In this paper, we propose a general approach to solve the abovementioned problem; the approach can be used for color images in non computer-aided decryption environments. The proposed approach uses Feed Forward Network to construct the shares. The experimental results indicate that a solution to the pixel expansion problem of the EVCS is achieved. Moreover, the display quality of the recovered image is better than that obtained using other VC schemes.