基于坐标变换的轴承缺陷检测

On Bearing Defects Detecting Based on Coordinate Transformation

针对传统的人工检测以及称重检测的效率低下,检测准确度不高等问题,提出了一种图像处理技术中利用坐标变换来对轴承的缺陷进行检测的方法,在Visual C++6.0下开发检测软件.主要包括图像预处理、圆中心获取、双坐标系间转换、缺陷量值的计算与存储.实验结果表明,基于坐标变换的轴承缺陷检测方法的准确率能够达到99.5%,检测一个轴承所需时间在200 ms以内,即可达到检测既定的要求与目标.

Aiming at the problems that the traditional artificial detection and the weigh detection have low efficiency and low accuracy, the paper proposes a coordinate transformation method used for the bearing defects detection in image processing field. The detection software is developed in Visual C＋＋6.0, including the image preprocessing, the circle center acquisition, the double coordinate system＇s conversion and the defect value＇s calculation and store. With a series of experiments, the result shows that accuracy rate of the bearing defect detecting method based on coordinate transformation is up to 99.5 percent and the detection period for one bearing is less than 200 milliseconds, and meets the request and the goal.