Image emotional classification: static vs. dynamic

Abstract

Grouping images into emotional categories is an important and challenging problem in content-based image retrieval. In this paper, we propose an approach to classify art paintings into emotional categories (dynamic vs. static). The key points are feature selection and classification algorithm. According to the strong relationship between notable lines of image and human sensations, a novel feature vector WLDLV (weighted line direction-length vector) is proposed, which includes both orientation and length information of lines in an image, Then classification is performed by SVM (support vector machine) and images can be classified into dynamic vs. static. Experimental results demonstrate the effectiveness and superiority of our approach.