Efficient access to and retrieval from a shape image database

Sequential comparison of image visual features, so as to perform similar shape retrieval, is time-consuming and impractical. Access methods that utilize image shape features from different perspectives to narrow down the search space are necessary and essential. We propose a two-stage matching scheme, combining global and local features, to enhance the efficiency of a search operation. In addition, two shape feature encoding algorithms, concerning local feature extraction, are presented in the pursuit of effective representation of shape features. Substantial experiments are conducted and our results demonstrate the reliability of the proposed scheme.