指纹图像复合分割算法研究

Study on the Fingerprint Image Multi-Segmentation Algorithm

良好的指纹分割能够有效提高特征提取精度和减少后续处理时间,在指纹图像预处理中具有重要作用。文章在分析了传统指纹分割方法优缺点后,改进了传统方向图计算方法,然后提出了一种基于方向图法、方差法和跑长码目标标记法的复合分割方法,通过实验证明,这种方法能够有效解决传统方法的一些缺点,并对不同类型指纹图像有较高的适应性。

The better fingerprint segmentation can not only improve the accuracy of the feature extraction but also reduce the time of subsequent processing effectively.h 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.