Fingerprint Image Quality Evaluation And Repair Algorithms Research And Applications

With the development of computer science, more attentions have been paid to the fingerprint identification technology due to its convenience, high accuracy and low cost. The technique of fingerprint identification has become one of the widest used biometric identification techniques. It has been widely used in electronic commerce, criminal identification, information safety etc. So the research of an automatic fingerprint identification system (AFIS) has important technical value and practical value.The automatic fingerprint identification system is a synthetic system that integrates photoelectric technique, image process, computer and network, database technique and pattern identification technique. It commonly includes fingerprint image collection, fingerprint image process, minutiae extraction, minutiae matching etc. Because of many reasons, the quality of each image is different in the process of image collection. Some automatic fingerprint identification systems do not include the evaluation process, so the preprocessing of bad quality image is not good enough, which could increase the False Reject Rate (FRR). Therefore, the paper studies the synthesis evaluation of fingerprint image, fingerprint processing and fingerprint repair, which synthesis evaluation, repair problem and on-line fingerprint identification system are mainly discussed. The main work of this dissertation is as follows:1. A practical synthesis evaluation method of fingerprint image is proposed, which includes rough evaluation and fine evaluation. The parameters of rough evaluation and fine evaluation are introduced. Rough evaluation and fine evaluation are used in registration process, which can guarantee the reliability of fingerprint template. Rough evaluation is adopted in identification process to accelerate the identification.2. A fingerprint image classification repair algorithm based on MLP is proposed. Based on analyzing the feature of ridge structures, the structures that can cause false minutiae are classified into three types by using the Multilayer Perceptrons (MLP) neural networks, which includes simply type (5 structures), broken type (1 structure) and cross connection type (3 structures). Different methods are used for different types. The repair algorithm is experimented by using 500 images of retiree fingerprint images in database built by myself. The experiment shows that the algorithm can repair the above false minutiae structures.3. The fingerprint identification technique is successfully applied in the on-line fingerprint identification system of retirement pension payment. The background, structure and function of the system and the realization are expounded. The file database and fingerprint database of retirees in 17 units are estabished by using Visual C++ and SQL server2000. The flow of pension payment is similar to the general payment in the bank. The retiree can receive the pension payment after pressing fingerprint when he receives the hint to input the password. The flow does not affect other operation of the bank. Thus, the on-line fingerprint identification of pension payment is implemented and the identity verification can be carried in real time. The system has been successfully operated in a region of Shandong province, which solved the imitating drawing problem of the retirement pension to a great extent. The system is of great social benefit, and of great spread value.