二次识别算法在工件识别中的应用

Abstract

针对工业流水线上机器视觉系统工件识别的问题，提出了一种有效的基于模板匹配的二次识别算法。在识别之前，根据已知工件建立模板库并对每个模板提取一组特征组合。一次识别采用基于像素点的匹配算法，计算待匹配图像与模板图像的像素点灰度值的整体相似性，作为一次识别系数；二次识别采用基于特征的匹配算法，计算待匹配图像与模板图像的特征区域的细节吻合性，作为二次识别系数。综合两次识别系数，两者之和最大者为最佳匹配结果。实验结果表明，本文的方法简单有效且识别率高。 According to the work piece detection problems based on the machine vision system on the in-dustrial pipeline, an effective two-time recognition algorithm based on template matching is pro-posed. Before recognition, the template library in which each template has a set of features should be established. First, the point matching recognition is used to compare the collected image and all the template images in the library one by one, during which the gray value of the pixels is compared and the first matching coefficient is recorded. Then, the feature matching is used to compare the feature area of the collected image and the templates, and the second coefficient is recorded. The final matching coefficient is added by the first matching coefficient and the second one. The highest matching coefficient will be outputted as the result. The experimental results show that the method is simple and efficient with high accuracy.