Abstract
The performance of cross-correlation functions can decrease computational complexity under optimal fingerprint feature selection. In this paper, a technique is proposed to perform alignment of fingerprints followed by their matching in fewer computations. Minutiae points are extracted and alignment is performed on the basis of their spatial locations and orientation fields. Unlike traditional cross-correlation based matching algorithms, ridges are not included in the matching process to avoid redundant computations. However, optimal cross-correlation is chosen by correlating feature vectors accompanying x-y locations of minutiae points and their aligned orientation fields. As a result, matching time is significantly reduced with much improved accuracy.
Highlights
Patterns of immutable friction ridges and valleys forming fingerprints that have been extensively used for identification in numerous fields may be located on the exterior of one’s fingertip that have been extensively used for identification in numerous fields
To introduce uniqueness in the matching process of fingerprints, two descriptors are created for each minutia points followed by a seventeen-dimensional feature vector and the greedy matching algorithm is used for classification [11]
In order to evaluate the performance of CC and proposed method triplet based cross correlation (TBCC), different parameters such as false nonmatch rate (FNMR), false match rate (FMR), sensitivity (S), specificity (P ) and accuracy (A) are used for evaluation [18]
Summary
Patterns of immutable friction ridges and valleys forming fingerprints that have been extensively used for identification in numerous fields may be located on the exterior of one’s fingertip that have been extensively used for identification in numerous fields. To provide fingerprint-based biometric authentication, different algorithms have been proposed, mainly minutiae-based, pattern-based, correlation-based, etc. Smartphones and related devices acquire very less area of finger for recognition through scanner In this regard, a secure algorithm is developed for fingerprint authentication using the cross correlation-based technique as well as entropy is obtained for the associated region. Partial fingerprint matching is performed by acquiring features involving ridgeshapes as well as minutiae points. Orientation field is extracted from ridge valley patterns followed by features (minutiae points). To introduce uniqueness in the matching process of fingerprints, two descriptors are created for each minutia points followed by a seventeen-dimensional feature vector and the greedy matching algorithm is used for classification [11]. Matching of fingerprint images is performed based on minutiae points by dividing into two blocks.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
