基于SIFT相似性度量的图像缩放

Image Scaling Based on SIFT Similarity Measure

针对传统图像缩放算法存在的图像内容破坏与失真等问题,提出一种结合接缝雕刻和标准缩放的图像缩放算法。利用接缝雕刻算法对原始图像进行尺寸调整,分别从原始图像和缩放图像上提取尺度不变特征变换(SIFT)特征,并对2幅图像的SIFT特征进行匹配计算,得到两者的相似性距离。当原始图像与缩放图像之间的相似性距离达到某阈值时,即在图像重要目标或内容将要被破坏之前,停止使用接缝雕刻算法,采用标准缩放算法进行整体尺寸的调整操作。实验结果表明,该算法不仅可以有效避免图像内容的破坏与失真,而且可以较好地保护图像局部结构和全局视觉效果。

Aiming at the problem of the damage and distortion of image content existing in the traditional image resizing, an effective image scaling algorithm combining seam carving with scaling is proposed. An image is first resized using seam carving, then the Scale Invariant Feature Transform（SIFT） features are extracted from the original image and the resized one respectively, and the SIFT features between two images are matched and calculated to obtain their similarity distance. When the similarity distance between the original and the resized image reaches a certain threshold, namely, before the salient object and content are damaged obviously, seam carving is stopped and scaling is adopted for the residual task. Experimental results show that this algorithm is able to avoid the damage and distortion of image content and preserve both the local structure and the global visual effect of the image graciously.