Content-Based Emotion Image Retrieval Model

With the rapid development and popularity of the Internet and multimedia,emotion information processin ghas become a great challenge faced by artificial intelligence today. The research of emotion image retrieval is an intersectional research. Inspired from the research products of psychology and painting,a content-based emotion image retrieval model which includes common emotion and individual emotion has been proposed in this paper. First, based on the idea of "dimension" from psychology,an emotion space is constructed. Second,dominant colors,moment invariants,color and gray compositions,which can stimulate the emotion of human very easily,have been extracted from images to construct the feature space. Then,support vector machines are used to map images from the low level feature space to the high level emotion space,and automatically annotate unevaluated images based on user's common emotion. After that, the common emotion image retrieval has been indexed in the common emotion space and quickly grasps user's subjectivity inherent in vision,while an interactive individual emotion image retrieval using visualized interactive genetic algorithm is presented to adapt to individual variation and improve accuracy of the retrieval results. Based on image content ,an emotion scenery image retrieval system has been realized. The experimental results demonstrate the effectiveness of our approach.