Automatic Shape Annotation Using Rough Sets and Decision Trees

Annotation of images automatically assignstags to images by analyzing contents of images. Shape is themost important feature of images, by using this featurestagging of images is possible, can be termed as automaticshape annotation. In this paper, a novel classifiers usingmachine learning techniques viz. Rough Set (RS) andDecision Tree (DT) are presented to classify shape images ofa standard dataset for annotation purpose. Shape basedfeatures are extracted and organized to form a shape feature.Rough Set Exploration System (RSES) is used to developdecision tree based, rough set based classifiers for the taggingof shapes. The results obtained using these classifiers arepresented and discussed. The RS classifier significantlyimproves the annotation performance.