Fingerprint Ridge Orientation Extraction: A Review of State of the Art Techniques

Abstract

Personal identification based on fingerprints is very popular compared to identification based on other biometric features like iris, gait and face etc. Performance of automatic fingerprints identification systems depends upon the quality of fingerprints. Extraction of fingerprints features in poor quality fingerprints is challenging task. Accurate measurement of fingerprints feature improves the accuracy of identification systems. Fingerprints consists of ridge and valley structures and offers different types of features, they are categorized as level 1, level 2 and level 3 features. Level 1 features are singular points which are used for fingerprints registration, classification etc. Level 2 features are ridge features like minutiae points, ridge orientation etc., and commercially available fingerprint recognition systems are based on level 2 features. Level 3 features include sweat pores, incipient ridges etc. Among these features ridge orientation is used for fingerprint enhancement, fingerprint classification, indexing and fingerprint segmentation. This paper provides an overview of existing state of the art techniques for ridge orientation estimation.

Fingerprint Image Enhancement and Extraction of Minutiae and Orientation

“…The drawback in pixel-alignment based method is that its accuracy is limited to fixed number of 8 discrete reference orientation values and computational complexity increases proportional to the number of reference orientations. Some of the local methods are filter bank [22], wavelet projection [23], gradient based [24], [25] & spectral estimation of which the gradient based approach gives a more accurate result. The advantage of gradient based method is that the computed orientations are continuous.…”

Extraction and Refinement of Fingerprint Orientation Field

“…Matching, where a comparison is performed between the extracted features and the ones stored in the database [1][2][3].…”