Compositional rule of thirds detection

According to the latest Internet usage statistics, more than 4.5 million photos are being uploaded to Flickr every day. An automated system that can provide feedback about aesthetic value or quality based on learned rules could be a very useful support in picture searching, sorting and editing. This is a challenging problem as it requires semantic understanding of images, which is beyond the state-of-the-art in computer vision. In this paper, we present a saliency-based method for compositional rule of thirds detection. We make use of discriminant analysis to determine whether a photo respects the rule of thirds. The method is faster than previous methods and requires no tuning of many threshold control values and parameters. The results of the experiment demonstrate the validity and efficiency of the proposed method.