Palm-Print Pattern Matching Based on Features Using Rabin-Karp for Person Identification.

Area of Science:

• Biometrics
• Computer Science
• Pattern Recognition

Background:

• Palm-print identification is a reliable method for personal identification.
• Palm prints contain rich features like lines, ridges, and textures.
• Existing feature-based matching methods struggle with spatial variations.

Purpose of the Study:

• To propose an effective palm-print feature matching method.
• To improve the accuracy and efficiency of palm-print identification.
• To address spatial positional variations in feature matching.

Main Methods:

• Developed the Rabin-Karp Palm-Print Pattern Matching (RPPM) method.
• Employed double hashing to enhance pattern matching accuracy.
• Utilized Aho-Corasick Multiple Feature matching and bit parallel ordering for efficiency.

Main Results:

• RPPM demonstrated improved cumulative accuracy through enhanced hashing.
• The method achieved efficient matching of multiple palm-print features.
• Experiments confirmed high pattern matching efficiency and minimal processing time.

Conclusions:

• The proposed RPPM method offers an effective solution for palm-print based identification.
• Double hashing and bit parallel ordering significantly improve matching accuracy and speed.
• RPPM addresses key challenges in palm-print feature matching, enhancing biometric security.