3D model retrieval using linear prediction coding descriptor

This paper presents the usage of linear prediction coding (LPC) coefficients as descriptor for 3D shape retrieval. In this approach, early shape is projected to the lateral surface of a cylinder parallel to main principal axes and centered at the centroid of the 3D object. For each projected shape, we extract the two-dimensional linear prediction coding coefficients. Rotation normalization is performed by employing the principal component analysis. Resulting descriptor is robust against rotation, translation and scaling. Experimental results demonstrate the effectiveness of the proposed descriptor compared with other methods.