基于GEP的图像情感分类算法研究-计算机应用技术专业论文.docxVIP

ABSTRACT Along with the massive growth of internet image data and the rapid development of the Human-Computer Interaction System, the question about how to effectively classify the image, which will make people to retrieve the desired image in the vast resources quickly, has increasingly get peoples attention. In recent years, the image emotional semantic classification has become an active field of computer vision research. It has important guiding significance in helping Computer to correctly explain and perceive image content, to achieve effective image organization, classification and management, etc. The study of the image emotional classification ,which is intended to better describe and explain the whole content of the image and achieve the effective management of image, relates to pattern recognition, affective computing, physiology, visual psychology and other disciplines, , has profound significance and great commercial value. In this thesis, we study the emotional image classification combined with the knowledge of visual cognition theory, psychology, pattern recognition and other fields. Because of GEP algorithm has efficient classification performance. we design and implement image emotion classification algorithm based on GEP， Firstly, we use CSIFT algorithms which is an improved SIFT feature extraction algorithm to extract image features, and get the color information and other related features with strong semantic discrimination for emotional. Secondly, in order to generating a digital image matrix ,we select the typical feature vectors that include emotional labels by using k-means clustering algorithm, Finally, we design a new kind of chromosome and fitness function , and implement image emotion classification algorithm based on GEP . The purpose of classifying the image emotion is achieved. We conducted classification experiment on eight kinds of emotion in image library which is from the two networks data sets: Flicr and Deviantart. The results