针对现有自动光学检测系统焊点定位自动化程度低的问题，提出了一种基于颜色特征的智能焊点定位算法．对样本焊点区域的灰度直方图进行统计分析，获得焊点分割的初始颜色阈值，并以最小像素损失为目标对阈值进行修正，得到最优分割阈值，实现了焊点颜色的自动抽取; 定位过程中，使用阈值对焊点图像进行二值化，并使用优化后的面积最大法来搜索焊点位置，实现了焊点的快速定位． 实验结果表明: 文中算法对焊点图像的分割效果理想，定位误差小，定位速度可以满足实际应用的要求．

In order to improve the automation degree of solder joint positioning by using the existing automatic opticalinspection systems,an intelligent positioning algorithm based on color features is proposed.In this algorithm,theinitial color thresholds of solar joint segmentation are calculated by statistically analyzing the gray histograms of solderjoint regions,and a minimum pixel loss method is used to correct the initial thresholds and to further obtain theoptimal threshold.Thus,the solder joint color is automatically extracted.Moreover,during the positioning,the imagesof solder joints are binarized with the obtained threshold,and the optical location of solder joints are fastsearched by using the optimized maximum area method.Experimental results show that the proposed algorithm iseffective because it helps to obtain properly-extracted solder joint images with small positioning error and high positioningspeed that meets the practical application requirements well.