To overcome

To overcome Nilotinib IC50 the problems of vein recognition systems, finger vein recognition methods have been researched [1,25]. Yanagawa et al. proved that each finger from the same person has unique vein patterns [26]. Miura et al. proposed a finger vein extraction method using repeated line tracking [27]. Zhang et al. proposed a finger vein extracting method based on curvelet information of the image profile and locally interconnected a structural neural network [28]. Recently, Miura reported that finger vein thickness could be altered by blood flow or weather conditions [29]. Inhibitors,Modulators,Libraries He also proposed a finger vein pattern extraction method that allows for various pattern thicknesses [29]. In addition, a commercial product was introduced by Hitachi [30,31].

In our previous research, a local binary pattern (LBP)-based finger vein recognition method was proposed, in which a binary pattern was extracted from Inhibitors,Modulators,Libraries a stretched rectangular finger region [24]. Further, a modified Hausdorf distance (MHD)-based minutiae matching method has been used, in which vein pattern Inhibitors,Modulators,Libraries extraction should be performed to extract minutiae (bifurcation and ending) points [25]. According to previous finger vein recognition methods, vein-pattern or finger-region extraction procedures should be performed for feature extraction or matching. Vein pattern extraction procedures increase the time complexity. Moreover, if a finger image includes noise factors such as shadows or fingerprints, a falsely extracted pattern may occur, degrading the recognition accuracy.

Even in finger-region extraction methods, stretched quadrangle Inhibitors,Modulators,Libraries finger vein images include distortions due to the stretching procedure [1].Therefore, in a previous research [1], features of finger veins, finger geometry, and fingerprints were extracted using a Gabor filter, and the hamming distance based on binarization was used for matching. However, since the directions and widths of finger veins vary, it is difficult to determine the optimal directions and frequencies of the Gabor filter. Further, the extracted binary codes of the same finger region obtained through binarization can be altered owing to local shadows on the finger area [1].To solve these problems, we propose a new finger recognition method. In addition to vein patterns, IR finger images also have features reflecting section of geometrical finger edge information, as shown in Figure 1.

Anacetrapib Among these three components, finger geometry appears most clearly. Furthermore, finger vein patterns are totally less clearly appeared. Because these two components include a brightness change factor, their features can Vorinostat be extracted using a single high-pass filter. Consequently, instead of performing a separate localization procedure for each component, an appearance-based method is selected. Therefore, we say that the proposed method is regarded as finger recognition and not for finger vein recognition.

Leave a Reply

Your email address will not be published. Required fields are marked *

*

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>