For the problem that the remaining fingerprint cannot be segmented easily

the authors propose a segmentation algorithm for fingerprint images with remaining ridges based on continuously distributed directional image. The algorithm firstly calculates the point directional image

and uses the histogram filtering technology to filter directional image

and then the continuously distributed directional image can be obtained. Secondly

according to the direction inconsistency on the location where the remaining ridges border on the fingerprints in the foreground

we mark out the boundary between the remaining fingerprint and normal ridge based on the sharp directional information change. After dealing with false points in the post-processing

these true boundary points are used for curve fitting. Finally we remove the remaining fingerprint. Experiments have shown that such a continuously distributed directional image transits smoothly and naturally. It not only has good continuity

gradual change and noise immunity

but also has very high accuracy. And it can effectively segment the remaining fingerprint from the foreground.