Translation-Invariant Representation for Cumulative Foot Pressure Images

TL;DR

This paper introduces a hierarchical translation-invariant feature extraction method for cumulative foot pressure images, enhancing pedestrian recognition robustness against shoe differences and noise.

Contribution

It proposes a discriminative hierarchical sparse coding scheme for effective feature learning from foot pressure images, improving biometric identification accuracy.

Findings

Effective recognition across different shoes

Robustness to local shape variations

High accuracy on the proposed dataset

Abstract

Human can be distinguished by different limb movements and unique ground reaction force. Cumulative foot pressure image is a 2-D cumulative ground reaction force during one gait cycle. Although it contains pressure spatial distribution information and pressure temporal distribution information, it suffers from several problems including different shoes and noise, when putting it into practice as a new biometric for pedestrian identification. In this paper, we propose a hierarchical translation-invariant representation for cumulative foot pressure images, inspired by the success of Convolutional deep belief network for digital classification. Key contribution in our approach is discriminative hierarchical sparse coding scheme which helps to learn useful discriminative high-level visual features. Based on the feature representation of cumulative foot pressure images, we develop a pedestrian recognition system which is invariant to three different shoes and slight local shape change. Experiments are conducted on a proposed open dataset that contains more than 2800 cumulative foot pressure images from 118 subjects. Evaluations suggest the effectiveness of the proposed method and the potential of cumulative foot pressure images as a biometric.