TAILIEUCHUNG - Surface Area Distribution Descriptor for object matching

Matching 3D objects by their similarity is a fundamental problem in computer vision, computer graphics and many other fields. The main challenge in object matching is to find a suitable shape representation that can be used to accurately and quickly discriminate between similar and dissimilar shapes. In this paper we present a new volumetric descriptor to represent 3D objects. The proposed descriptor is used to match objects under rigid transformations including uniform scaling. The descriptor represents the object by dividing it into shells, acquiring the area distribution of the object through those shells. The computed areas are normalised to make the descriptor scale-invariant in addition to rotation and translation invariant. The effectiveness and stability of the proposed descriptor to noise and variant sampling density as well as the effectiveness of the similarity measures are analysed and demonstrated through experimental results. | Journal of Advanced Research 2010 1 233-241 Cairo University Journal of Advanced Research ORIGINAL ARTICLE Surface Area Distribution Descriptor for object matching Mohamed F. Gafar Elsayed E. Hemayed Computer Engineering Department Faculty of Engineering Cairo University Giza Egypt Received 29 October 2009 received in revised form 28 January 2010 accepted 12 February 2010 Available online 2 August 2010 KEYWORDS 3D object recognition Volumetric descriptor Surface area distribution Shape matching Abstract Matching 3D objects by their similarity is a fundamental problem in computer vision computer graphics and many other fields. The main challenge in object matching is to find a suitable shape representation that can be used to accurately and quickly discriminate between similar and dissimilar shapes. In this paper we present a new volumetric descriptor to represent 3D objects. The proposed descriptor is used to match objects under rigid transformations including uniform scaling. The descriptor represents the object by dividing it into shells acquiring the area distribution of the object through those shells. The computed areas are normalised to make the descriptor scale-invariant in addition to rotation and translation invariant. The effectiveness and stability of the proposed descriptor to noise and variant sampling density as well as the effectiveness of the similarity measures are analysed and demonstrated through experimental results. 2010 Cairo University. All rights reserved. Introduction With recent advances in technologies designed for the digital acquisition of 3D models there has been an increase in the availability and usage of 3D objects in a variety of applications. Examples of such applications include database models searching industrial inspection autonomous vehicles surveillance and medical image analysis. As a result there is a large collection of 3D objects available. This motivates the need to be able to retrieve 3D objects that are similar in .

• Vật lý
• 3D object recognition
• Volumetric descriptor
• Surface area distribution
• Shape matching
• Surface Area Distribution Descriptor
• Abstract of Doctoral dissertation
• Abstract of Doctoral dissertation Computer science
• 3D object detections
• Recognition system
• Geometrical constraints