【摘要】 针对线束线序检测过程中，人工检测方法准确率低、检测效率低的问题，提出一种基于HALCON的线序检测方法。首先，采用中值滤波、图像对比度增强、阈值分割技术对原始采集图像进行预处理，利用仿射变换技术调整线束倾斜角度，提高后续模板匹配的准确率;其次，使用基于相关性的模板匹配技术区分线束正反面，再根据线束连接器的位置选取线序检测区域;将待测图像的RGB颜色空间转换为HSV颜色空间，根据H和S分量的颜色均值和偏差确定线束颜色，将其与标定的正确线序结果进行比较，判断线序是否正确;最后，通过HALCON与PyQt5联合编程显示测量结果，实现检测软件界面搭建。实验结果表明:文中检测算法的总体准确识别率为97.33%，可应用于实际生产现场。更多还原

【Abstract】 Aiming at the problems of low accuracy and low efficiency of manual detection method in the process of wire harness wire sequence detection,a method of wire sequence detection based on HALCON was proposed. First,median filtering,image contrast enhancement and threshold segmentation were used to preprocess the original acquired image,and affine transform technology was used to adjust the angle of inclination of the wire harness to improve the accuracy of subsequent template matching.Secondly,the template matching technology based on correlation was used to distinguish the front and back of the wire harness,and then the wire sequence detection area was selected according to the position of the wire harness connector.The RGB color space of the image to be measured was converted into HSV color space,and the harness color was determined according to the color mean and deviation of H and S components,which was compared with the correct line sequence result of calibration to determine whether the line sequence was correct. Finally,the measurement results were displayed through HALCON and PyQt5 joint programming,and the detection software interface was built. The experimental results show that the overall accuracy recognition rate of the proposed detection algorithm is 97.33%,and it can be applied to the actual production site.更多还原