A Novel Fingerprint Bifurcation Extraction Algorithm Based on Neural Network Template Matching

Abstract

Fingerprint feature detection is one of the key techniques of automatic fingerprint identification. There are some problems of rotation and shift in the present fingerprint feature detection. This paper has given an algorithm of bifurcation detection based on neural network template matching. Correlative matching is to calculate the correlative value between template and target image according to a certain criteria when the template moves on the target image. The center of best matching is considered as fingerprint feature. The criteria of scaling the matching value is regarded as optimization function. Thus, matching recognition is converted into function optimization. The designed matcher based on neural network template can keep rotation invariant when the target image has the rotation of a certain angle. Finally, bifurcation can be extracted by multi-input and singleoutput there-layer feed forward neural network. The experimental results based on FVCX, have shown that the algorithm has rotation and shift invariant.

A Fingerprint Matching Algorithm Based On Minutiae And Local Ridge Orientation

“…Neural networks have been used in problems of fingerprint recognition in several ways. In [2] and [3] the parameters extraction is performed using neural networks and in [4], a comparison between several neural networks for fingerprint classification is performed. Despite that, the neural networks use for fingerprint matching is not well explored.…”

Detection of Bifurcation Pixels in Edge Images

“…Similar to Lou et al, Leng et al. [5] proposed a learning framework for the detection of bifurcation points in fingerprint images based on a feed forward neural network with a template matching scheme. In the context of vessel bifurcation detection, Calvo et al [1] focused on the application of filtering and morphologic operations.…”

Source localization on solids for touch interfaces

“…When employed in signal processing, particularly in the domain of image and speech processing, template matching has been found to be useful in scenarios where automated digital systems are employed to identify analog signals. Such applications include the use of automated fingerprint readers [27] [28] [29], voice commands on mobile phones and computers [30] [31], and even sound recognition for different musical instruments [32].…”