Empirical Evaluation Methods in Computer Vision

We have provided this page because it has information that may be of interest to our users. NIST does not necessarily endorse the views expressed or the facts presented on this page.Please address comments to craig.watson@nist.gov

ANNOUNCEMENT AND CALL FOR PARTICIPATION

Third Workshop on

Empirical Evaluation Methods in Computer Vision

Monday 10 December 2001, In Conjuntion with CVPR 2001
(Call for paper, Postscript, PDF)

MOTIVATION

This workshop is one in a continuing series of workshops on empirical evaluation and characterization of computer vision algorithms. As with the workshops, the primary goal of the workshop is to bring together researchers in the computer vision community to present papers and discuss evaluation and characterization methods for vision algorithms. The workshop program will include invited speakers, presentations of contributed papers, and panel discussion. Presented papers will appear in an edited book or a proceedings volume. Select papers from the workship will be reviewed for a special issue on empirical evaluation in Image and Computer Vision Journal.

PROGRAM

Contributed papers will be reviewed based on content relevant to the theme of the workshop, with an emphasis on sound empirical methods and results. Relevant topics include, but are not limited to:

methods / tools / databases for performance evaluation,
empirical comparison of different algorithms for vision problems,
evaluation of medical imaging algorithms in clinical settings,
evaluation of algorithms for industrial applications,
using the web to set evaluation standards,
performance characterization of algorihtms,
and statistical analysis of algorithm performance results.

PROGRAM

Session 1 8:30-9:50

Classification experiments on real-world texture
    R. Castano, R. Manduchi, and J. Fox
Analysis and detection of shadows in video streams: a comparative evaluation
    A. Prati, I. Mikic, R. Cucchiara, and M. M. Movadi
Empirical evaluation of graph partitioning measures for perceptual organization
    P. Soundararajan and S. Sarkar

Break 9:50-10:20

Session 2 10:20-Noon

Empirical Evaluation on the Performance of Contour Trackers
    P. Tissainayagam and D. Suter
Empirical Performance Evaluation of Object Recognition Methods
    Ulrich and C. Steger
A Performance evaluation protocol for content-based image retrieval
    L. Wenyin, Z. Su, S. Li, Y-F. Sun, and H. Zhang
A system for performance evaluation of arc segmentation algorithms
    L. Wenyin, J. Zhai, D. Dori, and T. Long

Lunch Noon-1:30

Session 3 1:30-3:10

Performance Evaluation of Tracking and Surveillance
    James Ferryman
Parametric and nonparametric methods for the statistical evaluation of HumanID algorithms
    R. Beveridge, B. Draper, K. She, and G. Givens
Confidence interval measurement in performance analysis of biometrics systems using the bootstrap
    R. M. Bolle, N. K. Ratha, and S. Pankanti
A Stratified Methodology for Classifier and Recognizer Evaluation
    R. Michaels and T. Boult

Break 3:10-3:40

Session 4 3:40-4:55

Meta-analysis of Face Recognition Algorithms
    P. J. Phillips and E. Newton
Quo Vidas Face Recognition?
    R. Gross, J. Shi, and J. Cohn
Empirical Studies of Kernel Methods for Face Recognition
    M. Yang

Related Resources:

We have provided links to these sites because they have information that may be of interest to our users. NIST does not necessarily endorse the views expressed or the facts presented on these sites. Further, NIST does not endorse any commercial products that may be advertised or available on these sites.Please address comments to craig.watson@nist.gov

Related webpages

Click here for European Computer Vision Net Benchmarking web page.

Click here for Workshop on Performance Characterisation and Benchmarking of Vision Systems web page.

Click here for link to Workshop on Evaluation and Validation of CV Algorithms

U of Toronto's "Delve" - "Data for Evaluating Learning in Valid Experiments"