Discovering association rules for mining images datasets: a proposal

Our focus for data mining in this paper is concerned with knowledge discovery in image databases. The Author present a data mining algorithm to find association rules in 2-dimensional colour images. The algorithm has four major steps: feature extraction, object identification, auxiliary image creation and object mining. A synthetic image set containing geometric shapes will generate to test the initial algorithm implementation. The experiments results show that there is promise in image mining based on content. Finally, the association rules will determine using an adaptation of the Apriori Algorithm. The proposed approach is applied to an image datasets to demonstrate the kinds of knowledge and association rules to discover interesting patterns and new knowledge. The Author analyse the reasons for discrepancies. And it also suggests directions for future work