基于随机置乱的内容感知图像缩放算法

Content-aware image resizing based on random permutation

针对非等比例缩放算法中线裁剪技术动态规划的复杂性,提出基于随机置乱的内容感知图像缩放算法。该算法利用视觉显著图随机重置能量序列的方式,使得在保护主体区域不被破坏的情况下,避免过度删除非重要区域所造成的图像局部失真。仿真结果表明,与线裁剪算法相比,本文算法在有效保护图像内容的同时,显著提高缩放速度,并能避免图像失真。

A novel content-aware image resizing mechanism based random permutation was proposed for the dynamic programming in seam carving algorithm. The proposed algorithm exploits visual saliency to get a random scrambled energy vector, which is extracted uniform to protect important image content. This algorithm can efficiently avoid the local distortion caused by excessive deleting non-important area. The simulation results show that the proposed algorithm gets a better visual effect. Compared with the seam carving algorithm, the proposed algorithm not only effectively protects the important image content, but also increases the speed for image resizing and avoid image distortion.