NIST logo

Publication Citation: Evaluation of 3D Interest Point Detection Techniques via Human-generated Ground Truth

NIST Authors in Bold

Author(s): Afzal A. Godil; Helin Dutagaci;
Title: Evaluation of 3D Interest Point Detection Techniques via Human-generated Ground Truth
Published: June 29, 2012
Abstract: In this paper, we present an evaluation strategy based on human-generated ground truth to measure the performance of 3D interest point detection techniques. We provide quantitative evaluation measures that relate automatically detected interest points to human-marked points, which were collected through a web-based application. We give visual demonstrations and a discussion on the results of the subjective experiments. We use a voting-based method to construct ground truth for 3D models and propose three evaluation measures, namely False Positive and False Negative Errors, and Weighted Miss Error to compare interest point detection algorithms.
Citation: Visual Computer
Keywords: 3D Interest Points; 3D Salient Points; 3D Shape Analysis
Research Areas: Data Mining, Modeling, Software, Information Processing Systems, Information Technology, Imaging
PDF version: PDF Document Click here to retrieve PDF version of paper (3MB)