Affiliations: [a] School of Information Technology, Deakin University, Burwood, VIC, Australia | [b] Gippsland School of Information Technology, Monash University, Churchill, VIC, Australia | [c] Department of Computer Science and Computer Engineering, La Trobe University, VIC, Australia
Correspondence:
[*]
Corresponding author: Prof. Phoebe Chen, PhD., School of Engineering and Information Technology, Deakin University, VIC 3125, Australia, and Department of Computer Science and Computer Engineering, La Trobe University, VIC 3086, Australia. Tel.: +61 3 92517684; Fax: +61 3 92517604; E-mail: phoebe@deakin.edu.au.
Abstract: In this paper, we propose a spectral descriptor for shapes of objects. The method relies on transforming the 2D objects into 3D space; distance transform and scale space theory is used to transform objects into 3D space. Spherical harmonics of the voxel grid are used to obtain shape descriptors. The proposed methods are compared against two existing methods which use spherical harmonics for shape based retrieval of images. Comparison is done based on ranking of images which is articulated in recall-precision curves. MPEG-7 Still Images Content Set is used for performing experiments. Experimental results show that the performance of the proposed descriptor is significantly better than other methods in the same category.
