In order to detect the broken yarn visually in the production of the spinning,according to the particularity of the yarn images in the direction, a method for realizing the yarn breakage detection was developed. Industrial cameras were used to capture the movement of the yarn, firstly wavelet denoising was used for smoothing images, then the exact information of the yarn were extracted by the simplified Hough transform and collinearity test,and finally according to the actual yarn distance characteristics,it was determined whether the yarn was broken. The sym4 wavelet bases ware chosen from many wavelet transforms,the results show that according denoising effect is optimal when the threshold is 10, and the edge detection operator prewitt is used to detect according the vertical direction, optimize the Hough transform to reduce the detection angle to[-10°,10°],enlarge the angular interval to 4°,and shorten the operation time from 0.46 s to 0.31 s, which reduces the operation time and improves the operation speed. Experiment results show that the algorithm can accurately determine the yarn breakage information.%为通过视觉方式在细纱生产中检测断头,根据纱线图像在方向上的特殊性,开发一种实现细纱断头检测的算法.借助工业相机捕获运动中的纱线,首先经小波去噪平滑图像,然后通过优化的霍夫变换和共线性检验提取纱线准确信息,最后根据实际纱线的距离特征判断是否存在断头.实验选用sym4小波基,结果表明:阈值为10时去噪效果最优,以边缘检测算子prewitt筛选垂直方向进行检测,并对霍夫变换优化,将检测角度缩小到[-10°, 10°],角度间隔扩大为4°,运算时间由0.46 s减少为0.31 s,缩短了运算时间,提高了运算速度,该算法可准确地判断纱线的断头信息.
展开▼
