Fingerprint Image Segmentation: A Review of State of the Art Techniques
Keywords:Ridge Orientation, AFIS, Segmentation, Level 1, Level 2, Level 3, Singular points, Biometrics
In Automatic Fingerprint Identification System (AFIS), pre-processing of the image is a crucial process in deciding the quality and performance of the system. Pre-processing is consists many stages as Segmentation, Enhancement, Binarisation, and Thinning. In this segmentation is one of the steps of pre-processing which differentiate foreground and background region of fingerprint images. Segmentation is the separation of the fingerprint region or extraction of the presence of ridges from the background of the initial image. Segmentation is necessary because it constructs the region of interest from the input image, reduces the processing time, increases the recognition or matching process performance, and reduces the probability of false feature extraction. A 100% accurate segmentation is always very difficult, especially in the very poor quality image or partial image filled with noise such as the presence of latent. Fingerprints are made of Ridge and Valley structure and their features are classified in three levels as Level 1, Level 2, and Level 3. Level 1 Features are singular macro details like ridge pattern and ridge flows. Level 2 is ridge local features like ridge bifurcation and ridge ending or simply minutiae points or ridge orientation. Level 3 is micro details like sweat pores, incipient ridges. This paper provides an overview of the state of the art techniques of fingerprint image segmentation and contribution of other researchers on segmentation. This paper also discusses a different class of segmentation algorithms with its measuring parameters, computational complexity, advantages, limitations, and applications.