2009, pp 101-111

Biometric Sample Quality

This is an excerpt from the content


Biometric quality evaluation; Performance of biometric quality measures


The intrinsic characteristic of a biometric signal may be used to determine its suitability for further processing by the biometric system or assess its conformance to preestablished standards. The quality score of a biometric sample signal is a scalar summary of the sample's quality.

Quality measurement algorithm is regarded as a black box that converts an input sample to an output scalar. Evaluation is done by quantifying the association between those values and observed matching results. For verification, these would be the false match and non-match rates. For identification, the matching results would usually be false match and nonmatch rates [1], but these may be augmented with rank and candidate-list length criteria. For a quality algorithm to be effective, an increase in false match and false nonmatch rates is expected as quality degrades.