Efficient and Accurate 3D Finger Knuckle Matching using Surface Key Points.

Area of Science:

• Biometrics and Pattern Recognition
• Computer Vision
• Human-Computer Interaction

Background:

• Traditional 3D finger knuckle recognition methods are computationally intensive due to complex matching algorithms.
• Existing approaches require extensive computation for translational and rotational parameters, impacting efficiency and accuracy.
• Drawbacks of conventional matching algorithms in biometric studies often go unnoticed.

Purpose of the Study:

• To develop a more efficient and accurate matching approach for contactless 3D finger knuckle recognition.
• To overcome the computational complexity and potential accuracy degradation of current methods.
• To validate the proposed method's effectiveness on diverse 3D biometric databases.

Main Methods:

• Extraction of surface key points from 3D finger knuckle surfaces.
• Development of an efficient matching algorithm utilizing these key points.
• Comparative experimental analysis against state-of-the-art methods on public databases.

Main Results:

• The proposed method achieves over 23 times faster recognition than the state-of-the-art.
• Performance improvements in accuracy were observed with the new approach.
• The method demonstrated effectiveness on 3D palmprint and 3D fingerprint databases.

Conclusions:

• The surface key point-based approach offers a significant advancement in 3D finger knuckle recognition efficiency and accuracy.
• This method provides a viable and improved alternative for personal identification systems.
• The approach's versatility is confirmed across various 3D biometric patterns.