Study on the Fingerprint Image Multi-Segmentation Algorithm

The better fingerprint segmentation can not only improve the accuracy of the feature extraction but also reduce the time of subsequent processing effectively.It is important in fingerprint processing.The paper improves on the method of computing the directional image,then proposes a fingerprint segmentation method based on the directional image,gray variance and the run-length code,after analyzing the advantages and disadvantages of the traditional methods.Experiment proves that the method can resolve the disadvantages of the traditional methods,and has a high adaptability for different fingerprint images.