Person identification in surveillance video using gait biometric cues

In this paper, we proposed a novel approach for establishing person identity based on gait cues in surveillance videos using simple feature extraction and classifier methods. Person identity verification is an exigent task. When we go for identification or verification, first thing we count; the process or the method. Robust identification always depends on trait selection and robust method. From the beginning of the automated identification; classifiers and specific trait was the main concern, because, classifier is the tool which enables scientists to identity a person or classify a person in respect to provided input, on the other hand, biometric trait has to be unique, reliable and should have expected applicability. We used classifier approaches based on two different classifiers-NaiveBayes and C4.5 [1].