Evaluation Method, Dataset Size or Dataset Content: How to Evaluate Algorithms for Image Matching?

被引:0
作者
Nadia Kanwal
Erkan Bostanci
Adrian F. Clark
机构
[1] Lahore College for Women University,Computer Engineering Department
[2] Ankara University,School of Computer Science & Electronic Engineering
[3] University of Essex,undefined
来源
Journal of Mathematical Imaging and Vision | 2016年 / 55卷
关键词
Performance characterization; Feature matching; Homography;
D O I
暂无
中图分类号
学科分类号
摘要
Most vision papers have to include some evaluation work in order to demonstrate that the algorithm proposed is an improvement on existing ones. Generally, these evaluation results are presented in tabular or graphical forms. Neither of these is ideal because there is no indication as to whether any performance differences are statistically significant. Moreover, the size and nature of the dataset used for evaluation will obviously have a bearing on the results, and neither of these factors are usually discussed. This paper evaluates the effectiveness of commonly used performance characterization metrics for image feature detection and description for matching problems and explores the use of statistical tests such as McNemar’s test and ANOVA as better alternatives.
引用
收藏
页码:378 / 400
页数:22
相关论文
共 62 条
[1]  
Benjamini Y(1995)Controlling the false discovery rate: a practical and powerful approach to multiple testing J. R. Stat. Soc. Ser B (Methodol) 57 289-300
[2]  
Hochberg Y(2001)The control of the false discovery rate in multiple testing under dependency Ann. Stat. 29 1165-1188
[3]  
Benjamini Y(2014)Spatial statistics of image features for performance comparison IEEE Trans. Image Process. 23 153-162
[4]  
Yekutieli D(2010)Brief: binary robust independent elementary features Comput. Vis. ECCV 2010 778-792
[5]  
Bostanci E(2011)A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms Swarm Evolut. Comput. 1 3-18
[6]  
Kanwal N(2003)Analysis of clustered matched-pair data Stat. Med. 22 2417-2428
[7]  
Clark A(2001)Rates of torsades de pointes associated with ciprofloxacin, ofloxacin, levofloxacin, gatifloxacin, and moxifloxacin Pharmacotherapy 21 1468-1472
[8]  
Calonder M(2001)Statistical issues in analysis of diagnostic imaging experiments with multiple observations per patient1 Radiology 221 763-767
[9]  
Lepetit V(2010)Small-sample precision of roc-related estimates Bioinformatics 26 822-830
[10]  
Strecha C(1950)The use of range in analysis of variance Biometrika 37 271-280