掌纹的纹线结构特征明显,稳定且具有足够的辨别信息。由于掌纹线很不规则,很难用数学表达式的方式对其结构进行精确描述。该文提出一种新的用于掌纹识别的纹线结构特征描述和匹配方法。该方法应用改进的注水算法从二值的纹线图像上提取纹线的统计结构特征;标记纹线方向,提取纹线的方向结构特征;将掌纹线的全局统计结构特征和局部细节方向结构特征整合为一个特征向量描述掌纹纹线的结构特征;最后定义一个加权距离衡量不同纹线结构特征之间的相似度。实验表明,该方法不仅具有较好的匹配性能,而且可以获得较高的识别精度。
Palm line structure features are clear and stable, and they can uniquely describe a palmprint. Because the directions of palm lines are arbitrary and irregular, it is very difficult to accurately represent their structure features with an expression. This paper presents a new approach to line structure features representation and matching for palmprint recognition. It uses improved water-filling algorithm to extract the statistical structure features and direction structure features and label palm lines direction information from the extracted palm lines image. Finally, the extracted global statistical structure features and local detail direction structure features are combined as a feature vector, which is used in the next recognition. The experimental results show the method not only has a good property in matching, but also it can get a better accuracy.