Fingerprint Reconstruction

794 Words2 Pages

the orientation field by adopting an orientation field model described in [5]. According to the orientation field and a predefined ridge frequency, the ridges of the fingerprint are iteratively grown from an initial image which records the minutiae local pattern.
This approach produces many obvious spurious minutiae in the reconstructed fingerprint, which can be easily detected. The fingerprint reconstruction (from minutiae) approach proposed by Feng et al. [4] takes advantage of the amplitude and frequency modulated (AM-FM) fingerprint model [6], in which the phase image is used to determine the ridges and minutiae. The phase image contains two parts: the continuous phase and the spiral phase (which corresponds to the minutiae). In [4], the authors propose to incorporate a piecewise planar model for the continuous phase reconstruction. This model predicts the continuous phase block by block based on the gradient of the continuous phase. The fingerprint is reconstructed by combining the continuous phase and the spiral phase, which has a good matching against the original fingerprint. However, the reconstructed fingerprint does not match well when compared with different impressions of the original fingerprint. Furthermore, the piecewise planar model introduces blocking affects in the continuous phase and the reconstructed fingerprint. For fingerprint with singularity, additional artifacts may appear in the reconstructed fingerprint due to the discontinuity in the continuous phase. The various applications of minutiae-based fingerprint recognition systems, it is very important to investigate to which extreme a reconstructed fingerprint can be similar to the original fingerprint. So as to prompt the research of counter measures a...

... middle of paper ...

...ge flow and pattern types, are prominent enough to align fingerprints directly. Nilsson [26] detected the core point by complex filters applied to the orientation field in multiple resolution scales, and the translation and rotation parameters are simply computed by comparing the coordinates and orientation of the two core points. Jain [27] predefined four types of kernel curves:first is arch, second is left loop ,third is right loop and fourth is whorl, each with several subclasses respectively. These kernel curves were fitted with the image, and then used for alignment. Yager [28] proposed a two stage optimization alignment combined both global and local features. It first aligned two fingerprints by orientation field, curvature maps and ridge frequency maps, and then optimized by minutiae. The alignment using global features is fast but not robust, because the

More about Fingerprint Reconstruction

Open Document