Deformable matching of hand shapes for user verification

Abstract

We present a method for personal authentication based on deformable matching of hand shapes. Authentication systems are already employed in domains that require some sort of user verification. Unlike previous methods on hand shape-based verification, our method aligns the hand shapes before extracting a feature set. We also base the verification decision on the shape distance which as automatically computed during the alignment stage. The shape distance proves to be a more reliable classijication criterion than the handcrafted feature sets used by previous systems. Our verification system attained a high level of accuracy: 96.5% genuine accept rate us. 2% false accept rate. This performance is further improved by learning an enrollment template shape for each user.

Comparative analysis of global hand appearance-based person recognition

“…Jain and Duta were the first to propose deformable shape analysis and to develop an algorithm where hand silhouettes are registered and compared in terms of the mean alignment error. 24 The hand shape, surprisingly, exhibits great variation among individuals. The silhouettes contain much richer information than geometrical measures of the hand.…”

“…Thus, researchers often use pegs to fix the position of the hand and the orientation of the fingers. 24 Konukoglu et al 11 and Yörük et al 12 developed a detailed hand normalization algorithm, where hands are brought to a normalized posture from any uncontrolled positioning. Konukoglu et al experimented with various shape features; for example, they used a modified Hausdorff distance for hand contours and independent component analysis ͑ICA͒ features of the binary hands.…”

A biometric identification system based on eigenpalm and eigenfinger features

“…Most of these systems use handposition constraints, such as pegs. In [24], a system based on deformable shape matching is proposed. A number of commercial systems based on hand geometry [25] and palm prints [26], [27] are available.…”

Personal authentication using palm-print features

“…Zunkel [5] introduced a commercial product of hand geometry-based recognition and applied it to many access control systems. Jain et al [6] used the deformable matching techniques to verify the individuals via the hand shapes. 96.5% accuracy rate and 2% false acceptance rate(FAR) are achieved by their approaches.…”