Image Seam-Carving By Controlling Positional Distribution of Seams
Paper ID : 1001-MVIP2020
Mahdi Ahmadi *, Nader Karimi, Shadrokh Samavi
Isfahan University of Technology
Image retargeting is a new image processing task that renders the change of aspect ratio in images. In recent years, researchers have invented many algorithms to solve the image retargeting problem from different points of view. One of the most famous algorithms is seam-carving that is the basis of many other algorithms. Although seam-carving is fast and straightforward, it usually distorts the images. In this paper, we introduce a new seam-carving algorithm that not only has the simplicity of the original seam-carving but also lacks the usual unwanted distortion existed in the original method. To achieve this goal, the positional distribution of seams is controlled by a regular energy pattern. The proposed method does not need the typical time-consuming pre-processes such as saliency detection that are part of modern retargeting algorithms. We show that the proposed method outperforms the original seam-carving in terms of retargeted image quality assessment and seam coagulation measures.
Image Retargeting, Seam-Carving, Seam Distribution
Status : Paper Accepted (Oral Presentation)