Statistical Region Merging deals with secure way of image hiding through segmented images. In the existing system, a new type of computer art called Line Based Cubism-Like Image is used. Here prominent lines in the cover image are extracted to form an art image and Image is hidden into the art image. The main drawback is that, Line Based Cubism technique can be applied only on certain images. It works effectively only on specific images which are of cubism flavour. Moreover only text hiding is achieved successfully by this technique. Image hiding is not done efficiently. Hence Image Segmentation using Statistical Region Merging is proposed. In this technique, cover image is converted into segmented image and secret image is hidden into the segmented image. This segmented image is used to distract hackers’ attention. Also the main advantage of the proposed system is that, it is generalized for all type of images. Statistical region merging is a fast and robust algorithm to segment an image into regions and it evaluates the values within a regional span and grouped together based on the merging criteria. This algorithm exhibits efficient performance in solving significant noise corruption. Also lossless image embedding is achieved successfully by using optimal embedding technique. As the variation between the original pixel value and the embedded pixel is small, the image quality is often high even after the hiding process is completed. The optimal embedding technique typically provides high quality images.
Volume 11 | 09-Special Issue
Pages: 1010-1015
DOI: 10.5373/JARDCS/V11/20192665