Research And Realization Of Fingerprint Pre-processing Algorithm

With the development of the science and technology, fingerprint identification technology is widely used in the field of identity recognition and identification. Fingerprint identification is convenient, and have high efficiency, security and reliability. It has also been applied in many fields such as financial security, data encryption ,and electronically business and will play a more and more important role in our future life necessarily .However ,due to the complexity and uncertainty of the fingerprint identification ,there are still many problems to be resolved for further improvement of AFIS.In the system of fingerprint identification ,fingerprint identification is usually made up of three section :preprocessing, minutiae extraction and minutiae matching. Among them ,the purpose of preprocessing is to decrease the noise of the images , fingerprint image preprocessing is the one of the most critical part, which has provided preconditions for the accuracy of minutiae extraction and matching .Under normal circumstances ,fingerprint image preprocessing is divided into four parts:fingerprint image segmentation ,enhancement, binarization ,thinning. In this paper, all aspects of pre-processing algorithm has been studied and made the appropriate improvements.According to the basic principles of the fingerprint recognition techniques,the thesis discussed the workflow of the auto-fingerprint-identification system .Chancing the fingerprint image using the following method :normalization,directional image computation ,directional filtering(Gabor filtering),local self-adaptive binarization ,noise elimination and thinning. The segmented method based on EPCD and ClUD possesses of high accuracy and adaptability. In the process of fingerprint image's enhancement, using the circular Gabor filter to enhance the fingerprint image can get better images .Based on the traditional binarization algorithm ,using of the improved dynamic adaptive binarization method to binary the fingerprint image after filter. As for the fingerprint image thinning,we propose a rapid fingerprint image thinning method based on OPTA to solve the contradiction between thinning quality and thinning speed for the already proposed one pass thinning algorithm(OPTA).Changing the elimination templates and preservation templates to solve the contradiction between the quality and speed.