The Research And Realization Of Fingerprint Image Preprocessing And Minutia Extraction Algorithm

Fingerprint identification is one of the most important biometric technology which has been paid amount of attention. It is the significant part of individual authentication in the future. Studies on the theory and application of fingerprint recognition have significant meanings both in theory and application. Base on plenty of papers, this dissertation makes some research on common fingerprint recognition, which including algorithms on fingerprint preprocessing, fingerprint feature extraction . Advance a integrate, ameliorate and executable algorithm and realize each of algorithm above with VC++ in Windows system. Through analyzing and comparing the result of the program, the thesis advances a set of ideal algorithm to establish well foundation for mach.At the time, the key problems are discussed and some new methods are presented aiming at the status now in this field. The main points of the dissertation are as follows:Study and realize the algorithms on fingerprint image preprocessing which including fingerprint image segmentation, enhancement, binarize, thinning. The fingerprint image segmentation algorithm include normalize, soft,the direction of point,the segmentation of background. The result of the experiment indicate it has good compatibility.The availability region of fingerprint image can be segment correctly for different fingerprint.The clear edge of fingerprint can be gained. The algorithm on enhancement include orientation image estimation, frequency image estimation and Gabor filtering. The result of the experiment indicate the algorithm on enhancement has good effect. Study three algorithm on binarize:using immobile threshold, smoothming threshold, direction. Study and realize the fast thin and ameliorate OPTA thin algorithm. As a result, entirety thin and smooth fingerprint ridge can be extraced.And the skeleton approach the midline of ridge.Base on the research of algorithms on fingerprint preprocessing, study and realize the algorithms on feature extraction. The algorithm for minutias extraction is based on tracing the thin ridge, express the type of current point and the states of its 8-neighborhood pixels by 8-neighbour coding. The experimental results shows the correct minutias are extracted and fake minutias are filtered. Also the algorithm has improved the speed of extracting minutias, shorten the time of processing images, so that can meet demands of practical application basically.Experiments show that the algorithms we mentioned above can enhance the quality of fingerprint image efficiently and it is robust against those noisy fingerprints. These algorithms have good process result and run faster and easily to be programmed which has effectively solved the problem of fingerprint image's preprocess.