Evaluation of Features for Defect Image Retrieval

J. Iivarinen, A. Ilvesmäki, and J. Pakkanen (Finland)

Keywords

defect classification, MPEG-7 descriptors, shape descriptors, content-based image retrieval

Abstract

In this paper different feature descriptors are evaluated for content-based retrieval of defect images. Especially the vi sual descriptors of the MPEG-7 standard are of interest. The evaluation is done with a small, pre-classified defect image database using the K-nearest neighbor (KNN) clas sification. The best features are then applied to a content based image retrieval (CBIR) system called PicSOM. The results indicate that some of the MPEG-7 descriptors work very well with our defect images, but there is a need for some additional shape descriptors.

Important Links:



Go Back