基于指纹图像断裂纹线的修复方法研究

Research of healing method of the broken lines in fingerprint image

指纹图像因设备、图像增强处理等原因造成的纹线断裂会产生伪特征点,会对指纹识别产生负面影响。在结合传统方法优点的同时,针对间距大、方向偏移小和间距大、方向偏移大的断裂情况,本文设计出窗口制约法和改进的窗口制约法2种不同的修复方法。实验结果表明,该方法使修复更加全面、完整,提高了伪特征点去除率,易于编程实现,对细化指纹图像的断裂有很好的修复效果。

Broken lines in fingerprint image, caused by collection apparatus and image enhancement for fingerprint will generate false features and negative effect on fingerprint recognition. Some early methods only process the simplest breaks and some process by only one way the whole breaks with the expense of increase in calculation burden and resource waste. A new project, containing several new algorithms, was proposed in order to overcome the drawback of the traditional methods. Experiment results demonstrate that this project makes the healing process more complete and efficient, improves the rid ratio of false features and the convenience of programming, and performs much well on healing the broken lines in the thinned fingerprint image.