User authentication based on foot motion

Abstract

In nearly all current systems, user authentication mechanism is one time and static. Although such type of user authentication is sufficient for many types of applications, in some scenarios, continuous or periodic re-verification of the identity is desirable, especially in high-security application. In this paper, we study user authentication based on 3D foot motion, which can be suitable for periodic identity re-verification purposes. Three-directional (3D) motion of the foot (in terms of acceleration signals) is collected using a wearable accelerometer sensor attached to the ankle of the person. Ankle accelerations from three directions (up-down, forward-backward and sideways) are analyzed for person authentication. Applied recognition method is based on detecting individual cycles in the signal and then finding best matching cycle pair between two acceleration signals. Using experimental data from 30 subjects, obtained EERs (Equal Error Rates) were in the range of 1.6-23.7% depending on motion directions and shoe types. Furthermore, by combining acceleration signals from 2D and 3D and then applying fusing techniques, recognition accuracies could be improved even further. The achieved performance improvements (in terms of EER) were up to 68.8%.

Accelerometer-Based Gait Recognition by Sparse Representation of Signature Points With Clusters

“…As it was shown in Fig. 4, we manually 7 the cycle borders at the cyclic valley points of the gait acceleration series recorded at the ankle. 8 Normally, 7-14 full step cycles (one left and one right step constitute a full step) existed within the useful segment of a record.…”

“…A participant might also dress in different ways for the two sessions. What is more, as we did not use particularly designed clothes or shoes for acceleration acquisition (they are used in some existing pieces of works, see [7]), the Wii remotes could not be mounted on the specific body locations very precisely for different participants and sessions. It imitated the practical scenarios of wearable and portable devices.…”

“…7 To reduce the cost of manual labeling, we in fact develop a semiautomatic algorithm to help us predetect the valley points. This algorithm can detect most (>95%) valley points with a small amount of human interaction.…”

“…In particular, as portable or wearable accelerometers can monitor gait continuously at arbitrary time, accelerometer-based gait recognition would be especially well in continuous identity reverification [7], which may help secure the access to sensitive carry-on items like cellphones and car keys (provided they are smart).…”

Modified kNN Algorithm for Improved Recognition Accuracy of Biometrics System Based on Gait

“…It was Cutting and Kozlowski [2] who already conducted researches which demonstrated that a human has a skill of recognizing the people he knows from a long distance by their way of moving, even if they wear clothes different than usual and have changed their hairstyle. Gafurov [4] In case of video based methods the picture registered is usually converted frame by frame into silhouette sequences. Subsequently, depending on the applied methods there occurs an attempt at reading of selected parameter's of the human's gait and classification of a person [1], [6].…”