CSS Based Trademark Retrieval System

World is emerging with trade practices in the global scenario. Trademarks today play a very critical and important role. Trademark registration and its evaluation for distinctiveness is becoming very tedious job for registration offices. Millions of trademarks had already registered and millions of applications are filed for trademarks registration. There are different techniques and approaches currently in use for distinctness check for trademarks. The proposed method is used for retrieval of trademarks and it uses the maxima of curvature zero crossing contours of Curvature Scale Space image (CSS) as a feature vector to represent the shapes of object boundary contours. The matching algorithm, which compares two sets of maxima and assigns matching value as a measure of similarity. The major advantage with CSS technique is that CSS representation of the image is robust with respect to noise, scale, and orientation changes of the image. Each retrieval takes a reasonable amount of computation time. The top most retrieved images by the system agree with that obtained by human perception.