Grip-pattern verification for a smart gun

Abstract

In the biometric verification system of a smart gun, the rightful user of the gun is recognized based on grip-pattern recognition. It was found that the verification performance of grip-pattern recognition degrades strongly when the data for training and testing the classifier, respectively, have been recorded in different sessions. The major factors that affect the verification performance of this system are the variations of pressure distribution and hand position between the probe image and the gallery image of a subject. In this work, three methods are proposed to reduce the effect of the variations by using different sessions for training, image registration, and classifier fusion. Based on these methods, the verification results are significantly improved.

Finding Common Ground

“…The concern is that these models are fragile, and therefore will likely break if any environmental changes occur [179]. Unfortunately, such changes are inherent in capacitive sensing through varying ground-coupling [119], changing user behavior over time [180], or environmental noise [38,37,225]. Although real-world deployments are very challenging, especially in terms of collecting ground-truth data, they are essential to demonstrate feasibility beyond a controlled lab setting.…”

Grip-Pattern Verification for Smart Gun Based on Maximum-Pairwise Comparison and Mean-Template Comparison

“…Having analyzed the data collected in all sessions, we found that the grip patterns of a subject recorded across sessions varied greatly, even though those of this subject recorded in the same session were fairly similar [2]. There were mainly two types of acrosssession variations.…”

“…2(a). Further research showed that these variations were the main reason for the unsatisfactory across-session verification performance [2]. On the other hand, one can also see that the hand shape remains constant for the same subject across sessions.…”

“…Note that only three fingers are present, because the index finger is near the trigger of the gun and its pressure pattern is therefore not measured. We recorded the grip patterns from a group of police officers in three sessions, with a time lapse in between [2]. The data were processed for verification, using a likelihood-ratio classifier described in [3].…”

“…First, a variation of pressure distributions occurred between the grip patterns from a subject recorded in different sessions. A second type of variation resulted from hand shift of a subject across sessions [2]. Fig.…”