PIPS Image Classification with Customized Associative Classifiers ⋆

In recent years the concept of utilizing association rules for classification emerged. This approach proved to often be more efficient and accurate than traditional techniques. In this paper we extend existing associative classifier building algorithms and apply them to the problem of image classification. We describe a set of photographs with features calculated on the basis of their color and texture characteristics and experiment with different types of rules, which make use of the information about the existence of a particular feature on an image, its occurrence count and spatial proximity to accurately classify the images. We suggest using association rules more closely tied to the nature of image data and compare the results of classification with simple rules, taking into consideration only the existence of a particular feature on an image.