基于细节特征的自动指纹识别系统的研究-光学专业论文.docxVIP

中南大学硕士学位论文 中南大学硕士学位论文 ABSTRACT ABSTRACT In recent years，there is a great progress in fingerprint identification technology,but it still is a hot topic at present，which is focused on how to improve the accur哟r and recognition speed of the automatic fingerprint identification system．Therefore，it’S very important to research the automatic fingerprint identification technology both in theory and in application． In the automatic fingerprint identification system，the fingerprint matching relies on the quality ofthe features heavily．When the quality ofthe features is very well，all the algorithms can get a good result．In addition, fingerprint feature extraction process is the most time—consuming in the automatic fingerprint identification system．So the fingerprint feature extraction is the current and future key problem in fingerprint identification technology．By anal)rsis of the fingerprint feature extraction process which includes the fingerprint image segmentation，computing ridge direction， computing ridge period，image enhancement，minutiae extraction and details of the matching，some new views ale proposed，which mainly include： improving orientation extraction algorithm based on the gradient，based on the integration of the fingerprint image segmentation algorithm，based on the one—dimensional Fourier Transform ridge period computing algorithm，a new way of Gabor filter function designed which improves the adaptive capacity of the filter．In the minutiae extraction process，based on the direction and ridge waveform values of the binary method is designed，a new feature details filtering algorithm is introduced which Can retrench the resuming time of eliminating burr and improve the reliability of the details．In the fingerprint matching process，A statistic model is proposed,which can compute the move—rotation parameters not from the local of fingerprint but from the whole fingerprint，overcome