Content-based image retrieval of Web surface defects with PicSOM

This work describes the application of PicSOM, a content-based image retrieval (CBIR) system based on self-organizing maps, on a defect image database containing 2004 images from a Web inspection system. Six feature descriptors from the MPEG-7 standard and an additional shape descriptor developed for surface defect images are used in the experiments. The classification performance of the descriptors is evaluated using K-nearest neighbor (KNN) leave-one-out cross-validation and PicSOM's built-in CBIR analysis system. The KNN results show good performance from three MPEG-7 descriptors and our shape descriptor. The CBIR results using these descriptors show that PicSOM's SOM-based indexing engine yields efficient and accurate retrieval of similar defect images from our database.