ES-RU: an entropy based rule to select representative templates in face surveillance.

ES-RU is a system for video sequence indexing. Video frames are annotated according to the identities of appearing subjects. Different interacting as well as interchangeable modules perform different processing steps, so that each can be possibly substituted with a different one performing the same task using a different method. The system implements both face location and analysis, and an algorithm to select the most representative templates for the selected identities. The algorithm for template analysis and selection relies on the concept of entropy. This idea is the base of most techniques that exploit relative entropy to estimate the degree of uniqueness which is assured by a biometric trait when processed by a Feature Extraction Technique (FET). In this paper, entropy is introduced as a tool to evaluate the contribution of each sample in guaranteeing a suitable diversification of the templates in a subject gallery. ES-RU was tested on 6 video clips and on a subset of the SCFace database to assess its performances.