Identity verification using palm print microscopic images based on median robust extended local binary pattern...

Area of Science:

• Biometrics and Identity Verification
• Image Processing and Pattern Recognition

Background:

• Automatic identity verification is crucial, with biometrics offering reliable solutions.
• Palm print biometrics are highly accurate but face challenges like rotation, scaling, and noise.

Purpose of the Study:

• To introduce a new identity verification method using palm prints.
• To address challenges in palm print image analysis and improve verification accuracy.

Main Methods:

• Image normalization and Region of Interest (ROI) extraction.
• Feature extraction using the Median Robust Extended Local Binary Pattern (MRELBP) algorithm.
• Dimensionality reduction followed by classification with a k-nearest neighbor (KNN) classifier.

Main Results:

• Achieved identity verification rates of 97.2% on IITD and 96.6% on CASIA datasets.
• Demonstrated stable detection rates against salt-and-pepper noise (up to 0.16), rotation (up to 5°), displacement (up to 6 pixels), and scale changes (up to 94%).

Conclusions:

• The MRELBP method offers a robust and accurate solution for palm print-based identity verification.
• The proposed method effectively handles common image distortions, enhancing practical applicability.