Deep Structure, Singularities, and Computer Vision DSSCV

Multi-Scale Singularity Trees (MSSTs) represents the deep structure of images in scale-space and provide both the connections between image features at different scales and their strengths. In this report we present and evaluate an algorithm that exploits the MSSTs for image matching. Two versions of the algorithm is presented: an exact and an approximation. Several experiments are conducted to empirically evaluate the MSST matching algorithm under image distortions. Further, the performance of the MSST matching algorithm is measured on three databases: the ORL face database, magazine covers, and the COIL database. Finally the performance is compared with algorithms based on the Scale Invariant Feature Transform (SIFT), and the Position of Catastrophes (CAT).