Emotional Semantic Calculation Model and Retrieval of Wedding Image based on Color Features

Content-based retrieval is now commonly used in image retrieval system. One of the disadvantages of the traditional content-based image retrieval technology is the "semantic gap", which means could not get the semantic meaning from the basic image features. In the context of wedding image, considering the subjectivity of emotion, this paper will present a further research on emotion semantic extracting of wedding image based on color features. Firstly, we will extract the color eigenvector of images using asymmetrical quantized color histogram, and then propose an optimized formula, which helps to classify colors for better visual characteristic. Secondly, five basic emotional classes will be put forward, along with a mapping model that calculates images' emotional eigenvector by using fuzzy function based on the five classes. Moreover, the use of crossing method to measure similarity degree between images will also be applied. Finally, we will carry out retrieval experiments whose recall ratio and precision ratio indicate the correctness and effectiveness of this system.