Shape Retrieval Using Matching Pursuit Decomposition

This paper presents an approach of shape retrieval using linear regression. This approach extracts object edges from decomposed images in different scale levels and approximates them by the linear regression algorithm Matching Pursuit (MP). MP uses linear combination of circular Gaussian basis functions to reconstruct target edges. Each Gaussian basis function contains several features: scale, position and amplitude, which are used to compute distance of two contours. Shapes are retrieved according to the distances between query image and all images in a database.