点击次数：

发表时间：2014-01-01

发表刊物：计算机工程

期号：2

页面范围：219-223

ISSN号：1000-3428

摘要：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.

备注：新增回溯数据