期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2015
卷号：8
期号：8
页码：79-88
DOI：10.14257/ijsip.2015.8.8.09
出版社：SERSC
摘要：Image cropping is a technique to help people improve their taken photos' quality by discarding unnecessary parts of a photo. A novel method is presented for Image cropping by patches dissimilarities. In this paper, we propose a novel patches dissimilarities algorithm. Firstly, representing the image patches and reducing dimensionality. Then we extract the visual saliency map of these photos based on the patches dissimilarities. Finally, by the saliency map and face priors, we find a cropped region that can be best found. The experimental results demonstrate that our technique is applicable to a wide range of photos and produce more agreeable resulting photos
