Title | ||
---|---|---|
Evaluation of 3D interest point detection techniques via human-generated ground truth |
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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/s00371-012-0746-4 | The Visual Computer |
Keywords | Field | DocType |
interest point,human-generated ground truth,ground truth,false positive,interest point detection technique,evaluation strategy,evaluation measure,quantitative evaluation measure,interest point detection algorithm,false negative errors | Evaluation strategy,Computer vision,Data mining,Voting,Interest point detection,Computer science,Ground truth,Artificial intelligence | Journal |
Volume | Issue | ISSN |
28 | 9 | 1432-2315 |
Citations | PageRank | References |
53 | 1.29 | 23 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Helin Dutağaci | 1 | 179 | 12.51 |
Chun Pan Cheung | 2 | 84 | 3.43 |
Afzal Godil | 3 | 619 | 30.70 |