Earticle

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.

It is shown that distance computations between SIFT-descriptors using the Euclidean distance suffer from the curse of dimensionality. The search for exact matches is less affected than the generalisation of image patterns, e.g. by clustering methods. Experimental results indicate that for the case of generalisation, the Hamming distance on binarised SIFTdescriptors is a much better choice. It is shown that the binary feature representation is visually plausible, numerically stable and information preserving. In an histogram-based object recognition system, the binary representation allows for the quick matching, compact storage and fast training of a code-book of features. A time-consuming clustering of the input data is redundant.