Aiming at the problems of traditional manual inspection methods of electronic wire harness product dimensions such as low efficiency and large subjective measurement errors, a non-contact inspection method based on machine vision is proposed. Design and build a visual inspection system, use Zhang Zhengyou calibration method to calibrate the camera and collect product image information, use the improved Canny algorithm to detect the edges of the image, extract the product outline and perform horizontal tilt correction on the image; the corrected product outline is divided and the least squares method is used to perform straight line fitting on the contour edge sampling points; the product size in the world coordinate system is calculated based on the image coordinates of the measurement points on the contour edge and the camera calibration results; traditional vernier caliper measurement and visual measurement tests are performed on the product. The test results show that the repeated measurement error and absolute measurement error of this method do not exceed 0.1 mm, the average detection time is within 1 s, and it can achieve rapid and accurate detection of the dimensions of electronic wire harness products.
LUR S, LIY F, YUQ. On-line measurement of the straightness of seamless steel pipes using machine vision technique[J]. Sensors and Actuators A: Physical, 2001, 94(1/2): 95-101.
[6]
KAWASUEK, KOMATSUT. Shape measurement of a sewer pipe using a mobile robot with computer vision[J]. International Journal of Advanced Robotic Systems, 2013, 10(1): 52.
XIEHong, LIAOZhijie, XINGTingwen. A non-contact detection of the dimensional of circular parts[J]. Electronic Design Engineering, 2016, 24(19): 155-158. (in Chinese)
CHENQianqian, WANGXiaokai, ZHAOXiaohong. Bullet core size precision detection algorithm research based on Halcon[J]. Journal of Test and Measurement Technology, 2018, 32(2): 112-118. (in Chinese)
ZHANGZ. A flexible new technique for camera calibration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(11): 1330-1334.
[13]
CAOY, WUD, DUANY. A new image edge detection algorithm based on improved Canny[J]. Journal of Computational Methods in Sciences and Engineering, 2020, 20(2): 629-642.
[14]
KIMY W, KRISHNAA V N. A study on the effect of Canny edge detection on downscaleed images[J]. Pattern Recognition and Image Analysis, 2020, 30: 372-381.
[15]
MOHAPATRAB N. Image edge detection techniques[J]. ACCENTS Transactions on Image Processing and Computer Vision, 2019, 5(15): 15-16.