Research On Visual Positioning And Guidance Method For Micro Assembly Operation

With the rapid development of electronic technology,various electronic products have become an integral part of people's daily life.People's demand for electronic products is increasing day by day,which promotes the reform and renewal of manufacturing technology.As an important part of electronic products,the chip have very high precision requirements in production line,especially electronic products are gradually lightweight and portable nowadays,the chip size will be smaller and smaller.In addition,chips produced in small quantities are still manufactured and assembled manually,but human vision gradually can not meet the requirements of assembly accuracy,so we need to use machine vision to help complete the chip positioning and installation.In this paper,the development trend of machine vision and related technologies are summarized,location the chips with the help of MATLAB.The specific contents are as follows:The internal and external parameters of the camera are calculated to correct the distortion of the image by studying the camera model and camera calibration method,and the relationship between image coordinates and world coordinates is established to help the chip positioning.For the chip image with white background,the dark contour of the chip is easier to extract;for the chip image with black background,the pin contour of the chip is more prominent.After taking the chip image,first eliminate the noise interference and call out the gray histogram of the original image,and the background and chip gray distribution are determined by observing the gray histogram to confirm the threshold value of threshold segmentation.Then the chip information and background factors are separated by threshold segmentation,which makes the chip features easier to identify.The edge information of chip pin in black background and the edge information of chip outline in white background are extracted by Canny edge detection.The corner information is obtained by Harris algorithm.The longest corner is extracted to obtain the longest edge rotation angle,which is the rotation angle of chip.Through the establishment of the chip template library,the NCC algorithm is used to match the both white background and black background with the chip template image,and the coordinates of the chip center point,which is the chip location information,are obtained.By combining the acquired information,the position information and rotation angle of the chip can be obtained.Through many experiments and comparison,the scheme proposed in this paper has the characteristics of high speed,high precision and good stability,which is feasible for chip recognition.