一种快速的手掌轮廓特征点提取方法 - 智能信息处理研究室 - 延边大学.pdf

32 23 武 汉 理 工 大 学 学 报 Vol. 32 No.23 2010 12 JOURNAL OF WUHAN UNIVERSITY OF TECHNOLOGY Dec.2010 DOI: 10. 3963/j. issn. 2010. 23.039 1 2 1 金 璇 , 王红纪 , 崔荣一 ( 1. , 133002; 2. , 462002) : 快速而准确地提取手掌轮廓特征点是精确提取在线掌纹图像感兴趣区域的关键为 效地解决这 一问题, 提 出了快速的手掌轮廓特征点的提取方法首先, 把掌纹图像的灰度直方图谷底对应的灰度值作为全局阈值将图像二值 化; 其次, 利用Log 算子检测出手掌的轮廓线并进行跟踪以获得轮廓线的8邻域链码; 最后,根据8邻域链码在特征点附 近的变化规律提取出手掌轮廓特征点为了验证该方法的 效性, 根据提取出的特征点对300 幅掌纹图像的感兴趣区 域按比例进行了定位分割实验结果表明该方法效率高且具 良好的平移旋转不变性 : 掌纹图像; 分割; 边界链码; 特征点提取 : P 391. 41 : A :2010) A Rapid Feature Points Extra tion Method for Palm Outline 1 2 1 JIN Jingx uan , WAN G H ongj i , C UI Rongy i ( 1.Intelligent Information Processing Lab, Department of Computer Science and echnology, Yanbian University, Yanji 133002, China; 2. Department of Computer Engineering, Luohe Vocational and echnology College, Luohe 462002, China) Abstra t: Extracting feature points quickly and accurately is the key to extract ROI( regionofinterest) from palmprint im age accurately. In order to solve this problem, a rapid method to extract feature points of palm outline was proposed. Firstly, palmprint image was converted into binary image , the globalthreshold of binary process was the gray value corresponding to the valley bottom of gray histogram. hen, Log operator w as used to detect palm outline, subsequently 8neighborhood boundary tracking algorithm wasused to obtain palm outline chaincode. Finally, feature points of palm outline was ext