A Comparative Study of Various Fingerprint Image Texture Characteristics

Abstract Fingerprint recognition stands out as one of the most reliable biometric identification methods, primarily due to the unique, universal, and permanent nature of fingerprint patterns. Among the various techniques employed to improve recognition accuracy, texture analysis has emerged as a critical component, especially when dealing with noisy or low-quality fingerprint images. This study conducts a comprehensive comparative analysis of several prominent fingerprint texture feature extraction methods to determine their effectiveness in enhancing recognition performance. The methods explored include ridge frequency and orientation analysis, minutiae density estimation, Local Binary Patterns (LBP), Gabor filters, and Gray-Level Co-occurrence Matrix (GLCM) features. Each of these techniques offers distinct advantages in capturing the inherent texture and structural patterns of fingerprint images. Ridge frequency and orientation features help in modeling the global flow of ridges, while minutiae