Image retargeting based on object inpainting and background seam carving

Abstract

Image Retargeting is the most important Image resizing techniques in the digitalized world. In this paper, we find the solution for images retargeting technique using harvest festival images. The proposed technology is called Object-CRIST (Content Retargeting Image Seam Carving Technique). The method is a combination of two resizing Methods Region based object inpainting and resizing background image seam carving. The first method identifies the objects in the image and performs Region based retargeting. Second method works on image background regions. We evaluate Object-CRIST method on harvest festival image dataset. The experiment result of proposed system outperforms rest of all retargeting methodologies. The Result accuracy is calculated based on Resolution and Mean Opinion Score (MOS).