On the use of the Karhunen-Loeve transform and expansion matching for generalized feature detection

A novel generalized feature extraction method based on the Expansion Matching (EXM) method and the Karhunen-Loeve (KL) transform is presented. This yields an eecient method to locate a large variety of features with a single pass of parallel ltering operations. The EXM method is used to design optimal detectors for diierent features. The KL representation is used to deene an optimal basis for representing these EXM feature detectors with minimum trun-cation error. Input images are then analyzed with the the resulting KL bases. The KL coeecients obtained from the analysis are used to eeciently reconstruct the response due to any combination of feature detectors. The method is successfully applied to real images and extracts a variety of arc and edge feature as well as more complex junction features formed by combining two or more arcs or line features.