Minutiae has been comsidered as the most distinctive feature of a fingerprint and thus widely used in finger reconition/verification.Instead of using those conventional extraction methods based on binarization and ridgeline thinning

D.Maio and D.Maltoni proposed a totally different approach to detect the minutiae directly in gray-scale images in 1997.In this approach minutiae were extracted based on ridge tracing directly in gray images

so it showed more robust performance by avoiding the errors introduced by binarization and thinning.However

there are also drawbacks of this approach

such as the difficulties to decide the 7 thresholds

inaccurate ridge ending determination and etc.In this paper

an approach with several important improvements on D.Maio and D.Maltoni's method is presented.A novel method based on canny operator and morphology is used for fingerprint foreground segmentation

and both ridge tracing angle and the change of gray-level are introduced into the stop criteria of ending point.Other improvements include the selection of a better filter

and a post-processing to eliminate the spurious ridgelines and false minutiae by considering the length of ridgeline and the local structure of ridgelines where minutiae are detected.The efficiency and robustness of the proposed algorithm have been shown in the experiments.