Content-Based Image Retrieval at the End of the Early Years
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Safari Guidebook with Image Retrieval
ICMCS '99 Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems - Volume 02
Image query by impression words-the IQI system
IEEE Transactions on Consumer Electronics
Case-Based facial action units recognition using interactive genetic algorithm
ACII'05 Proceedings of the First international conference on Affective Computing and Intelligent Interaction
Hi-index | 0.00 |
In the design of multimedia database system, one of the important issues is how to deal with kansei of human beings. A kansei-oriented image retrieval has been proposed in this paper. Human kansei includes two aspects: common kansei and individual kansei. Our approach also consists of common kansei retrieval and individual kansei retrieval. First, avoiding the dependence on the method of selecting impression words, factor analysis is applied to construct an orthogonal psychological space based on common human kansei. After that, a radial basis function neural network is used for learning and memorizing the common kansei, then automatically evaluates and annotates each image with adjective words in the orthogonal psychological space. Furthermore interactive evolution computation is presented to realize individual kansei retrieval. Last an interesting experimental result is shown.