For both datasets of biometric objects given by images and an ensemble of the different modality datasets, the lower bounds to error probability of person identification subject to a fixed amount of information have been investigated. The bounds are constructed using a probabilistic object classification model in metric spaces of the object representations. These bounds are independent on decision algorithms and they are formed by the inverses of the rate-distortion functions for the model of discrete source coding with Hamming distortion when the source letters are transmitted over a noisy channel. The difference between a unit and any obtained lower bound to error probability produces an appropriate upper bound to accuracy of person identification depending on a given amount of processed information in a given dataset of the object representations. The obtained bounds are useful for estimating an efficiency of the decision algorithms in terms of deviations of the algorithm error probability or accuracy relative to the boundary values subject to a given average amount of information for making the decisions.
Lange et al. (Wed,) studied this question.