By Topic

A Shape Distributions Retrieval Algorithm of 3D CAD Models Based on Normal Direction

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Hongshen Wang ; Key Lab. of Contemporary Designing & Integrated Manuf. Technol., China Northwestern Polytech. Univ. Xi''an, Xi''an ; Shusheng Zhang ; Kaixing Zhang ; Xiaoliang Bai

This paper describes a new 3D model retrieval approach based on shape distributions, which represents a 3D shape as three D2 shape histograms. First, generate a sufficiently large number of random sample points on surface of 3D model and note the normal of each point. Second, we adopt the D2 shape function to measures the distance between two random points on the surface of the model, at the same times, compute the angles between the normals of the points and the line segment which is formed by the two random points. Last, according to the angles, we sort the line segments into three sets. For each set, we calculate shape distribution histograms associated with the D2 shape distribution function. Compare each pair of shape distribution histograms using well-known curve matching techniques and add the three weighted results. The sum is regarded as the similar coefficient of the two models. Experimentation shows this algorithm can efficiently give the similar degree of the two models and as well reflecting human perceptual similarity.

Published in:

Young Computer Scientists, 2008. ICYCS 2008. The 9th International Conference for

Date of Conference:

18-21 Nov. 2008