GVU Technical Report Number: GIT-GVU-01-10

Title: Expected Confusion as a Method of Evaluating Recognition Techniques

Authors: Aaron F. Bobick, Amos Y. Johnson

Abstract:
We derive an expected confusion metric, as opposed to reporting percent correct with a limited database, as a method to evaluate recognition techniques. This metric allows us to predict how well a given feature vector will filter identity in a large population. Our expected confusion is the ratio of the average individual variation of a feature vector. We evaluate our gait-recognition technique that recovers static body and stride parameters of walking subjects with the expected confusion metric to demonstrate its use.

Keywords: expected confusion, recognition techniques, gait-recognition

You can access this technical report via: PDF , Postscript