Performance Assessment through Bootstrap

Kyujin Cho(1), Peter Meer(1) and Javier Cabrera(2)

(1)Department of Electrical and Computer Engineering
(2)Department of Statistics
Rutgers University, Piscataway, NJ 08855, USA

A new performance evaluation paradigm for computer vision systems is proposed. In real situation, the complexity of the input data and/or of the computational procedure can make traditional error propagation methods unfeasible. The new approach exploits a resampling technique recently introduced in statistics, the boostrap. Distributions for the output variables are obtained by perturbing the nuisance properties of the input, i.e., properties with no relevance for the output under ideal conditions. From these bootstrap distributions, the confidence in the adequacy of the assumptions embedded into the computational procedure for the given input is derived. As an example, the new paradigm is applied to the task of edge detection. The performance of several edge detection methods is compared both for synthetic data and real images. The confidence in the output can be used to obtain an edgemap independent of the gradient magnitude.

Appeared in IEEE Trans. Pattern Anal. Machine Intell, 19, 1185-1198, 1997.
Return to Research: Bootstrap as a tool for computer vision       Return to List of Publications
Download the paper