Research And Design Of Fingerprint Recognition System

Due to the uniqueness and invariability of fingerprints, the automated identification based on fingerprints is becoming an attractive alternative to the traditional methods of identification. It plays a more and more important role in many regions. Although, fingerprint recognition has been extensively studied and many advances have been made on it, there are still many problems expected to be solved which are shown in actual applications and evaluations. As a consequence, in recent years, many academies and industries have been making an in-depth research on fingerprint recognition technologies.However, there is much special noise in fingerprint images, and many methods wouldn't be publicized, so an ideal automated fingerprint identification system (AFIS) is still a difficult research subject.With the development of the computer, as a branch of intelligence technology, the development of neural network can promote the development of pattern recognition.Compared with the traditional pattern recognition methods, the nerve network has the distribution memory of information, parallel processing and learning capability by itself, thus, it receives widespread application.Based on this, this article chooses the artificial neural networks technology as the fingerprint recognition method, and provides a new Gabor filter-based alogthium after analysing traditonal fingerprint preprocess alogthium. This alogthium includes image normalizing, orientation estimation, image smooth, divising and binarying, thinning and removed noise. The main purpose of image normalizing is to reduce the variations in gray level values along ridges and furrows, but not to change the clarity of the ridge and furrow structures. Using point-orientation estimates the orientation at each pixel, computes the ridge frequency. Then adjust the parameters of Gabor filter using the orientation and ridge frequency at each pixel to realize adaptive filtering. Thus the system is robust to low quality of fingerprint image. Then dividing background block and foreground block and binarying image. The purpose of thinning image is to reduce a lot of inessential information and to get very integratedminutiae information. Then using some fingerprint's minute features for the fingerprint identification with the BP neural network to get the result.Experimental results show that with the methods based on details of fingerprints, the method of neural network has been reasonably used so that it effectively overcomes the effect of fingerprint circumrotation and moving, increases the resistibility to noise, it is proved to be relatively high effective in recognizing damaged or blurry fingerprint images.