Research On Method Of Fingerprint Recognition

Fingerprint recognition is one of the technologies of biometric recognition. 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 problems which are shown in actual applications and evaluations. In recent years, many academies and industries have been making an in-depth research on fingerprint recognition technologies. This thesis has studied the main technologies of fingerprint recognition, mainly including fingerprint pretreatment, feature extraction and fingerprint matching.The main contribution woks are as follows:1. An improved fingerprint enhancement algorithm based on Gabor filter is proposed. A method for ridge orientation acquirement is improved, and the orientation map is more accurate. A method for ridge frequency acquirement is improved, and the false ridge lines are avoided. Experiment results indicate that the method has dramatic effect to low quality fingerprint images.2. An improved index table fingerprint thinning algorithm is proposed. The non-thorough thinning bifurcations are thinned thoroughly. The false character points are effectively removed. The fingerprint skeleton is in the centre of ridge lines. It is faster and easier to implement.3. The algorithms of fingerprint feature extraction and fingerprint matching are researched. The cross number algorithm is used for fingerprint feature extraction. The fingerprint matching method based on edit distance is used for fingerprint matching. Experiment results indicate that the methods are effective for fingerprint feature extraction and fingerprint matching.