基于Freeman链码的二维曲线匹配  

2D curve matching based on Freeman code

作　　者：靳秋霞 张彩霞[1] 

机构地区：[1]北方工业大学模式识别与图像处理研究所,北京100144

出　　处：《计算机应用》2015年第A01期247-251,共5页journal of Computer Applications

基　　金：北方工业大学优秀青年教师培养计划项目(14085)

摘　　要：快速地提取曲线的拐角点是进行曲线匹配的关键。为了解决这一问题,提出提取拐角点的快速方法,根据Freeman链码在拐角点附近的变化规律,将Freeman链码分为两类,根据这两类的判断规律分别确定拐角点,然后根据特征线段的长度和特征点的曲率去除一些伪拐角点,以得到标准拐角点。最后根据标准拐角点的曲率序列求得的归一化互相关系数进行粗匹配,再通过长序列的归一化互相关系数进行精确匹配。这种方法不受曲线旋转和平移的影响,易于实现,根据实验证明该方法的合理性、有效性。It is one of the key issues of curve matching to extract corner points of 2D curves quickly and accurately. To solve this problem, a rapid method is proposed. Freeman code was divided into two categories based on the change of Freeman code near the corner point, then, two judgment criteria were used to determine corner points. Some false corner points were removed according to the lengths of the feature lines and the curvatures of the feature points to get the standard corner points. Finally, curves were matched together using the normalized cross correlation of the length and curvature. This method may be implemented easily and not affected by rotation and translation. The experiments show the rationality and effectiveness of this method.

关 键 词：FREEMAN链码 曲线匹配 拐角点 归一化互相关性 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]