Knowledge Discovery of Traffic/People Behaviors Based on Image Mining Approach
Fatemeh Safara, Amir Masoud Eftekhari Moghadam · 2006
The increasing number of image archives has made image mining an important task because of its potential to discover useful image patterns and relationships from a large set of images. We proposed a framework for extracting knowledge from a sequence of images. The structure of the framework composed of two modules: image analysis and knowledge processing. In this paper, we customized the knowledge-processing module for checking normality/abnormality of vehicles/people behaviors in each image sequence