Grid-Based Image Resizing with User-Selected Constraint

摘要：

We present a novel method for content-aware image resizing based on grid transformation. In our proposed method, an original image is projected onto a grid, and then the vertical and horizontal grid lines are moved to resize the image. For obtaining plausible results, our method preserves not only important regions but also aspect ratios of objects and shapes of lines. We define three distortion measures for achieving these preservations. Experimental results demonstrate that our proposed algorithm resizes images with less distortion than other resizing methods.

作者: Kazu MISHIBA Masaaki IKEHARA

作者单位: Keio University, Yokohama, Japan

会议类型: 国际会议

会议名称: 2011亚太信号与信息处理协会年度峰会(APSIPAASC 2011)

会议地点: 西安

会议语种:英文

页码: 1-4

在线出版日期: 2011-10-18（万方平台首次上网日期，不代表论文的发表时间）