基于标记盒的指纹分割  

Fingerprint image segmentation based on label box

作　　者：任春晓[1] 尹义龙[2] 

机构地区：[1]山东大学齐鲁软件学院,山东济南250101 [2]山东大学计算机科学与技术学院,山东济南250100

出　　处：《山东大学学报（工学版）》2006年第5期54-57,共4页Journal of Shandong University（Engineering Science）

基　　金：国家自然科学基金项目(60403010);山东省自然科学基金重点项目(Z2004G05)

摘　　要：为增强指纹图像分割的效果,首先,基于方向一致性、局部灰度均值和灰度方差指标,提出了像素空间分布并进行了分析;然后,给出了使用标记盒来建立模型和进行指纹图像分割的算法步骤;最后,为了评估该方法的性能,分别使用线性分割器和二次曲面分割器的方法进行了对比实验.实验结果表明新方法提供了更精确的分割结果,仅有0.80%的像素分割错误,而二次曲面分割法的错误率为0.97%.In order to enhance the effects of fingerprint image segmentation, spatial distribution model of pixels based on Coherence, Mean and Variance was advaced and analyzed at first. Secondly, the label box was used to establish the model and to deal with fingerprint image. Lastly, experiments were performed to evaluate the performance of this method in comparison with the methods using linear classifier and quadric surface. The results show that the proposed method provides accurate high-resolution segmentation resuhs, which has only 0.80% misclassified pixels, while the quadric surface classifier has 0.97% misclassified pixels.

关 键 词：指纹 指纹识别 图像分割 标记盒 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]