Analysis of Gait Recognition on Constrained Scenarios with Limited Data Information

Abstract

This paper is focused on the assessment of gait recognition on a constrained scenario, where limited information can be extracted from the gait image sequences. In particular we are interested in assessing the performance of gait images when only the lower part of the body is acquired by the camera and just half of a gait cycle is available (SFootBD database). Thus, various state-of-the-art feature approaches have been followed and applied to the data. Results show that good recognition performance can be achieved using such limited data information for gait biometric. A comparative analysis of the influence of the quantity of data used in the training models has been carried out obtaining results of 8.6% EER for the case of using 10 data samples to train the models, and 5.7% of EER for the case of using 40 data for training. Also, a comparison with a standard and ideal gait database (USF database) is also carried out using similar experimental protocols. In this case 10 data samples are used for training achieving results of 3.6% EER. The comparison with a standard database shows that different feature approaches perform differently for each database, achieving best individual results with MPCA and EGEI methods for the SFootBD and the USF databases respectively.