Automatic adaptation method in intelligent image retrieval system
Yong Hwan Kim, Phill Kyu Rhee · 2003
Information overload in modern electronic life is an inevitable problem. It is more difficult for users to find information that they need. For resolving this problem, we present the framework design and implementation issues of an image retrieval system called IIRS with the capability of user adaptation. Even though much research has been performed on the development of efficient image retrieval engines, most of this has focused on the performance of the system, not the friendliness and efficiency of the user interface. The satisfaction of users is at least as important as the functionality and performance in image retrieval systems. An intelligent user interface adaptation method enables IIRS to be more intelligent, natural and efficient. We address the adaptation method that consists of a decision tree and backpropagation neural network. They have been employed for long-term and short-term adaptations respectively. Experimental results show that the automatic adaptation method can improve the performance of the IIRS.