摘要
在基于计算机视觉技术的齿轮测量中,齿轮图像中的边缘信息是极为有用的,它是进一步进行齿轮图像分割的基础,直接影响到齿轮几何参数测量结果的正确性和可靠性。传统的边缘检测算子大都是基于边缘的灰度不连续性利用梯度局部最大值或二阶导数过零点来检测边缘,容易受噪声干扰。文中采用图像的多尺度小波变换局部模最大值进行边缘检测。检测结果表明,此方法降噪能力强,定位精度高,克服了传统方法的缺点。
Based on computer vision technology in the gear measurement, the edge information of gear image is very useful, which is the basis of gear image segmentation. It can affect directly the results of correctness and reliability in gear geometry parameters measurement. Mostly, traditional arithmetic of image edge detection distill edge using gradient maximum or zero-crossing which bases on gray discontinuousness on edge, and it is affected easily by noise. Multidimensional edge detection on the basis of wavelet decomposition detail was applied to detect image edge. Experimental results show that the method accurately extracts the image edge and effectively reduces noise.
出处
《科学技术与工程》
2007年第8期1602-1604,共3页
Science Technology and Engineering
关键词
齿轮测量
边缘检测
小波变换
多尺度边缘检测
gear measurement edge detection wavelet transform multidimensional edge detection
