论文部分内容阅读
为了解决硅片厚度在0.1 mm以下时,激光传感器扫描检测容易发生硅片漏扫的提出一种基于OpenCV的硅片层级分布定位检测方法,利用图像预处理技术得到各层级硅片前边缘轮廓样本库,将测试图像的边缘轮廓与样本库中的图像依次做差值运算,从而通过像素点总和是否达到规定阈值,来判定该层是否存在硅片,从而达到硅片层级分布定位检测的目的.结果表明,该方法能够有效提高硅片盒中0.1 mm以下硅片层级分布定位检测的可靠性,且算法简单,实时性及兼容性较好.
In order to solve the problem that the laser sensor scanning detection is easy to occur when the thickness of the silicon wafer is less than 0.1 mm, a detection method based on OpenCV for the distribution of the wafer level is proposed. Using the image preprocessing technique, The difference between the edge of the test image and the image in the sample library is calculated sequentially so as to determine whether there is a silicon wafer in the layer according to whether the total sum of the pixels reaches a predetermined threshold or not so as to achieve the purpose of locating and detecting the silicon level distribution. The results show that the proposed method can effectively improve the reliability of the position detection of silicon wafer distribution below 0.1 mm in silicon cassette. The method is simple, real-time and compatible.