随着不同分辨率和纵横比的显示设备的迅猛增长,内容感知图像缩放技术逐渐成为图像处理领域新的研究热点之一。内容感知图像缩放的目标是在任意改变图像大小时保持图像中的主体特征不变。围绕其关键步骤:图像重要度识别和基于重要度的缩放,先概述重要度识别的相关方法,然后重点综述基于重要度的缩放技术。根据缩放是在像素级上操作还是亚像素级上操作,或者两者兼有,将其分为基于线裁剪缩放、基于图像变形缩放和多操作缩放3类,并比较各类方法的优缺点,同时给出各类方法所适合处理的图像类型。最后在分析各类研究方法的基础上,给出了内容感知缩放技术的可能发展方向。

With the rapid growth of the diversity and versatility of display devices which all come in different aspect ratios and resolutions, the content-aware image resizing has become one of the hot research fields in image processing. The main objective of such a technique is to preserve the image features when changing its size. The most content-aware image resizing methods have two basic steps: content significance recognition and image resizing based on a significance map. Firstly, the classic methods of the significance recognition are surveyed.Secondly, the resizing technologies based on significance maps are summarized. According to resizing methods based on pixel level discrete operating, sub-pixel level continuous operation or combination of the discrete operating and continuous operation, it can be categorized into image resizing based on seam carving, image resizing based on warping or multi-operator resizing. Thirdly, the algorithm effect comparisons between classes are given and their suitable image types are presented. Finally, future directions are discussed.