Image specific error rate: A biometric performance metric
Image-speciﬁc false match and false non-match error rates are deﬁned by inheriting concepts from the biometric zoo. These metrics support failure mode analyses by allowing association of a covariate (e.g., dilation for iris recognition) with a matching error rate without having to consider the covariate of a comparison image. Image-speciﬁc error rates are also useful in detection of ground truth errors in test datasets. Images with higher image-speciﬁc error rates are more difficult to recognize, so these metircs can be used to assess the level of difﬁculty of test corpora or partition a corpus into sets with varying level of difﬁculty. Results on use of image-speciﬁc error rates for ground-truth error detection, covariate analysis and corpus partitioning is presented.sion on a per-user basis.
August 22-26, 2010
20th International Conference on Pattern Recognition ICPR)
Image specific error rate: A biometric performance metric, 20th International Conference on Pattern Recognition ICPR), Istanbul, -1, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=904876
(Accessed December 1, 2023)