The Arithmetic Study Of Automated Fingerprint Identification System

Due to their uniqueness and persistence, fingerprints are used as main basis of personal identity. Automated fingerprint identification system, a technology of fingerprint identification using computer, is of convenience, high efficiency, security and reliability. It has been applied in many fields such as financial security, data encryption, electronic business and will play a more and more important role in our life.Many fingerprint products have been offered nowadays, however, most of the key technologies have not been publicized on account of commercial interest, while the better performance is required. So more reliable and accurate automated fingerprint identification systems have been of great interest to researchers.Based on plenty of papers, technology reports and dissertations, the author has studied and designed the automated fingerprint identification system. According to the process of the design, the paper can be divided into three components: pre-processing, feature extraction, matching of fingerprint images.Fingerprint image pre-processing has four parts: image segmentation, enhanced process, thinning and dealing with in the thinning image. The enhanced project is very important and its result affects the thinning and feature extraction. So the author gives emphasis to this part and designs two enhanced projects. Finally she chooses one after doing many experiments. Image pre-processing can be described approximately like this: above all we should segment the fingerprint image which is collected from fingerprint collecting instrument and wipe off the background which does not contain the fingerprint. After this, we can work out the directional image from the gray-scale image, then design orientation filters based on directional image of fingerprint and employ them to denoise gray-scale image and get the binary image lastly. Afterwards, by using thinning templates, we get the skeleton fingerprint image from the binary image. After thinning, we should get rid of the noises from the acquired skeleton image in order to make the next step easily and more accurately.Fingerprint image feature extraction mainly extracts the minutiae and saves the true minutiae's property. Firstly, we can extract all minutiae from the pre-processed image by using feature extraction templates. Secondly, we should get rid of bogus minutiae by using...