PCB positioning device and method based on projection filtering

Abstract

The invention discloses a PCB positioning device and method based on projection filtering, wherein the device includes: an image acquisition module, an angle calculation module, a projection module, a peak value extraction module, a threshold value calculation module and a background filtering module, and the image acquisition module is used for Collect the grayscale image of the PCB board to be positioned; the angle calculation module is used to calculate the slope of the PCB board to be positioned; the projection module is used to correct the grayscale image according to the slope, and count the projection array in the X and Y axis directions; the peak value The extraction module is used to extract the peak sequence in the projection array; the threshold calculation module is used to calculate the filtering threshold of the projection array peak sequence; the background filtering module is used to filter the grayscale image by using the filtering threshold and the peak sequence to obtain the PCB board area. The device does not need to print marking points on the PCB and extract image feature points, and can perform pixel-level positioning only by using the statistical information of the image, and greatly reduces the amount of calculation.

Description

technical field [0001] The invention relates to the technical field of computer software engineering, in particular to a new technology for correcting printed circuit board image deflection by using computer vision, that is, a PCB positioning device and method based on projection filtering. Background technique [0002] PCB (Printed Circuit Board, printed circuit board) image positioning is to identify the rotation angle and area coordinates of the PCB from the pictures containing the PCB and the background collected on the PCB production line. Accurate positioning is an important step in the PCB defect detection process. The accuracy and speed of positioning have a great influence on the PCB detection effect. At present, the commonly used PCB positioning method is to mark holes according to Mark or extract SIFT feature points from the image, and calculate the transformation matrix for positioning. However, the positioning method based on marker points is easily affected by...

AI Technical Summary

Problems solved by technology

However, the positioning method based on marker points is easily affected by the production accuracy and positioning algorithm, resulting in large errors in registration

And not all PCB boards have marking points, so the scope of application of this method is very limited

Although the positioning method based on image features has a wide range of applications, due to the large amount of calculation for extracting features, the efficiency is very low, which will greatly affect the running speed of the algorithm.

Images