Evaluation of 3D Interest Point Detection Techniques

Published

April 7, 2011

Author(s)

Helin Dutagaci, Chun Pan (Benny) Cheung, Afzal A. Godil

Abstract

In this paper, we compare the results of five 3D interest point detection techniques to the interest points marked by human subjects. This comparison is used to quantitatively evaluate the interest point detection algorithms. We asked human subjects to look at a number of 3D models, and mark interest points on the models via a web-based interface. We propose a voting-based method to construct ground truth out of humans’ selections of interest points. Evaluation measures, namely False Positive and False Negative Errors, are then defined based on the geodesic distance between the interest points detected by a particular algorithm and the human-generated ground truth.

Proceedings Title

Eurographics Workshop on 3D Object Retrieval

Conference Dates

April 10-15, 2011

Conference Location

LLandudno

Conference Title

Eurographics 2011

Pub Type

Conferences

Download Paper

Local Download

Keywords

3D salient point detection, 3D interest points

Citation

Dutagaci, H. , (Benny), C. and Godil, A. (2011), Evaluation of 3D Interest Point Detection Techniques, Eurographics Workshop on 3D Object Retrieval , LLandudno, -1, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=908053 (Accessed October 11, 2025)