一個(gè)利用模糊匹配算法的指紋識(shí)別系統(tǒng)(外文文獻(xiàn)翻譯)

1、A Fingerprint Recognizer Using Fuzzy Evolutionary ProgrammingAbstractA fingerprint recognizing system is built with two principal components: the fingerprint administrator and the fingerprint recognizer. Fingerprints are

2、 identified by their special features such as ridge endings, ridge bifurcation, short ridges, and ridge enclosures, which are collectively called the minutiae. The fingerprint administrator uses the method of gray scal

3、e ridge tracing backed up by a validating procedure to extract the minutiae of fingerprints. The fingerprint recognizer employs the technique of fuzzy evolutionary programming to match the minutiae of an input fingerprin

4、t with those from a database. Experimental results show the methods used are highly effective.1. IntroductionFingerprints have been used for many centuries as a means of identifying people [8,16]. As it is well known th

5、at fingerprints of an individual are unique and are normally unchanged during the whole life, the use of fingerprints is considered one of the most reliable methods of personal verification. This method has been widely

6、used in criminal identification, access authority verification, financial transferring confirmation, and many other civilian applications.In the old days, fingerprint recognition was done manually by professional experts

7、. But this task has become more difficult and time consuming, particularly in the case where a very large number of fingerprints are involved. During the past decade, several automatic fingerprint identification systems

8、have been made available to meet the demand of new applications [7,16,20,30]. The methods used in these systems are still far from complete satisfaction, however, due to inaccurate extraction of fingerprint characterist

9、ics and ineffective pattern matching procedures, which are the two major tasks of fingerprint identification. The Federal Bureau of Investigation's method of identifying a fingerprint by its set of minutiae is widel

10、y used in automatic fingerprint identification systems [7,9,18,21,26]. However, the way of extracting a fingerprint's minutiae differs from system to system. Many systems require some form of image preprocessing su

11、ch as transforming the fingerprint into a binary image and trimming the image's ridges into single pixel lines, before the detection of minutiae is carried out [2,3,6]. This may cause some loss of information and re

12、sult in inaccurate detection of the fingerprint's minutiae.The task of matching an input fingerprint's minutiae with those from a database is much more difficult. The existing methods that are based on mathemat

13、ical approximation and string matching algorithms [4,10] or on relaxation and simulated annealing [1,25] have shown to be rather ineffective and time consuming. The method of discrete Hough transform [23,27] is obvious

14、ly inappropriate as the search space is continuous. These difficulties stem from possible skin elasticity, different scales, and difference in positions of fingerprints.A full fingerprint normally contains between 50 to

15、 80 minutiae. A partial fingerprint may contain fewer than 20 minutiae. According to the Federal Bureau of Investigation [7], it suffices to identify a fingerprint by matching 12 minutiae, but it has been reported that i

16、n most cases 8 matched minutiae are enough.3. Minutiae extractionFor convenience, we represent a fingerprint image in reverse gray scale. That is, the dark pixels of the ridges are assigned high values where as the light

17、 pixels of the valleys are given low values. Figure 3 shows a section of ridges in this representation.In a fingerprint, each minutia is represented by its location (x, y) and the local ridge direction ?. Figure 4 shows

18、 the attributes of a fingerprint's minutia. The process of minutiae detection starts with finding a summit point on a ridge, then continues by tracing the ridge until a minutia, which can be either a ridge ending or