Laplacian-Based Image Retargeting with Salient Object Magnified

摘要：

A compelling image retargeting approach aims at maintaining the important contents in the original image as much as possible, while mini mizing the visual distortions on the image geometric structures. In this paper we present such an approach that succeeds in preserving the shape and size of the important contents and the geometric structures. We first encourage salient objects to be magnified hy handling the staling factor according to the corresponding saliency map. However, this may lead to over-magnification and distort the geometric structures (e.g. straight line and curve). We solve these problems by enforcing the deformed Laplacian coordinate of each grid vertex to be close to its original version, by which dramatic changes among neighboring quads are smoothed. All these constraints are integrated into a quadratic programming. The performance of the proposed approach ii demonstrated by comparing with the state-of-the-art methods.

关键词： Image Retargeting Laplacian Geometric Struc-ture Quadratic Programming

作者: Wenyu Hu Zhongxuan Luo Xin Fan Jielin Zhang

作者单位: School of Mathematical Sciences, Dalian University of Technology. Dalian 116024, China School of Mathematical Sciences, Dalian University of Technology. Dalian 116024, China School of Sof School of Software, Dalian University of Technology, Dalian 116620, China

会议类型: 国际会议

会议名称: 2011 4th International Congress on Image and Signal Processing(第四届图像与信号处理国际学术会议 CISP 2011)

会议地点: 上海

会议语种:英文

页码: 1966-1970

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）