High capacity image steganography on sparse message of scanned document image (SMSDI)

This paper presents a novel algorithm for high capacity image steganography, whose aim is to hide a scanned document as a message into a host image. In this approach, halftoning algorithm is applied to convert the gray-scale scanned document into a binary image, which is a sparse matrix. In the next step, an algorithm is proposed to read the the halftone image, and to convert each bit-stream of the sparse matrix into some meaningful decimal numbers, which are then to be embedded in 3-LSB bits of concealable pixels. Standard deviation is used in order to filter the concealable pixels of stego image and to preserve the quality of stego image. As a result, the smoother area that is sensitive to human visual system will not be chosen for embedding. The experiment results on 20 standard image, indicate that the PSNR measure and the embedding rate are 36.86 dB and 5.25 bpp in average, respectively, which are great progresses in comparison to the state-of-the-art.