A high quality image steganography scheme based on Fuzzy Inference System
Sara Sajasi, Amir Masoud Eftekhari Moghadam · 2013
This paper presents a novel image steganography approach for hiding a secret image in the cover image. It benefits from the fact that the occurrence of some local features in the image demonstrates remarkable patterns for determining the payload of the cover image sub-regions based on Human Visual System (HVS). However, the goal of this paper is to propose a system deals with improving the visual quality of the stego-image, while still providing a large embedding capacity. To achieve this goal, a Fuzzy Inference System (FIS) is designed as a classifier which adopts the local features of the cover image sub-regions as its crisp input values and produces semantic concepts corresponding to the payload of image sub-regions. This ensures to decrease the rate of changes in the stego-image, even after embedding a large amount of secret bits. The experimental results demonstrate the effectiveness of the proposed approach.