摘要
提出了一种改进的Harris角点检测方法。该方法在Harris角点检测求得角点响应函数后,利用双掩膜来定义进行非极大值抑制的局部范围,结合K均值聚类方法进行非极大值抑制,若像素点的角点响应函数值满足预设角点判定条件,则将该像素点定义为角点。实验结果表明,该方法无需进行阈值选择,提高了角点检测精度。
An improved harris-based corner detection method is presented in the paper.Firstly,the corner response function of the Harris corner detection should be obtained.Secondly,the two-masks are defined the scope of non-maxima suppression and the K means algorithm is used to start on the non-maxima suppression.Thirdly,if the value of the pixel corner response function is agree with the preset conditions,the pixel is defined as the corner.The experiments show that this method does not require the threshold selection and improve the precision of corner detection.
出处
《计算机与数字工程》
2011年第5期142-144,共3页
Computer & Digital Engineering
