Universiti Teknologi Malaysia Institutional Repository

The evaluation of shape distribution for object recognition based on kinect-like depth image

As'ari, M. A. and Supriyanto, Eko and Sheikh, Usman Ullah (2012) The evaluation of shape distribution for object recognition based on kinect-like depth image. In: Proceedings - 2012 4th International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2012. IEEE, New York, USA, pp. 313-318. ISBN 978-076954821-0

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/CICSyN.2012.65

Abstract

Shape distribution is a common 3D shape descriptor that has been widely used for 3D object retrieval. In this study, we evaluate the feasibility of shape distribution for object recognition based on Kinect-like depth image obtained from RGB-D object dataset; consisting of several household instances from 51 classes; and each instance consists of depth images from different rotational angle view. The proposed evaluation procedures are called (1) inter-class evaluation and (2) intra-class evaluation and were used to evaluate the shape distribution performance. Based on these evaluations, shape distribution performance was found to be slightly decreased in inter-class manner while significantly decreased for intra-class. It is evident that the minimal performance degradation in inter-class evaluation is due to variety of formed shapes when the instance is rotated while shape distribution suffers from not only shape variation among different rotational angle view but also among different instance per class in intra-class evaluation. This preliminary attempt shows that shape distribution is a relevant candidate applicable in object recognition for Kinect-like depth image.

Item Type:Book Section
Additional Information:Indexed by Scopus
Uncontrolled Keywords:3D object retrieval, instance, inter-class, intra-class, kinect-like depth imag
Subjects:Q Science > Q Science (General)
Divisions:Biosciences and Medical Engineering
ID Code:36048
Deposited By: Fazli Masari
Deposited On:02 Dec 2013 12:18
Last Modified:02 Feb 2017 13:04

Repository Staff Only: item control page