Flexible PCB defect detection method, visual system, device and medium

Abstract

The invention provides a flexible PCB defect detection method, a visual system, a device and a medium, and the method comprises the steps: obtaining a PCB at a plurality of shooting angles, and obtaining a first PCB image; performing image restoration processing on the first PCB image through an adaptive fidelity term and a Riemannian manifold regularization model to obtain a second PCB image; and performing registration on the second PCB image and the flexible PCB template, and performing feature comparison according to a registration result to determine PCB defects. The method can accurately describe geometric deformation under the condition that the speed and the acceleration are not zero in the image acquisition process, overcomes the defect that all parts of the image obey unified prior, realizes maintenance of detail structure characteristics of the image, and further realizes high-progress and high-speed defect sample identification; and the intelligent process can save certain labor cost, so that the method can be widely applied to the technical field of image processing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a defect detection method of a flexible PCB board, a vision system, a device and a medium. Background technique [0002] Flexible printed circuit board (Flexible Printed Circuit, FPC), generally uses polyimide as the base plate, and copper foil is attached to the surface as a printed circuit conductor, which has excellent electrical characteristics. Compared with traditional PCBs, FPC has extremely high flexibility, making it naturally suitable for circuit interconnection in three-dimensional space. Under the premise of meeting high reliability, FPC can save a lot of installation controls, make electronic equipment thinner and smaller, and at the same time have the characteristics of good heat dissipation and easy installation. Today, with thinner and smarter equipment, the demand for FPC continues to rise due to the strong impetus from markets such as mobile phones, ta...

AI Technical Summary

Problems solved by technology

[0005] First, the geometric deformation such as bending and warping of the flexible PCB board image details collected by the existing inspection system cannot be well described;

[0006] Second, it is currently used in industrial inspection to identify defective PCB boards and adopt unified processing for defective samples. There is no corresponding high-precision and speed system to classify defective samples, and subsequent manual classification processing is required, which is low in intelligence and high in cost;

[0007] Third, the existing models and solution methods mostly focus on a single noise, which is not suitable for flexible PCB board images, and it is difficult to meet the accuracy and speed requirements of industrial inspections.

Images