3D Model Retrieval Using Linear Prediction Coding Descriptor

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 acylinder parallel to main principal axes and centered at the centroid of the 3D object. For each projected shape, we extractthe two-dimensional linear prediction coding coefficients. Rotation normalization is performed by employing the principal component analysis. Resulting descriptor is robust againstrotation, translation and scaling. Experimental results demonstrate the effectiveness of the proposed descriptor compared with other methods