PCB defect detection method, device, equipment and medium

The present disclosure provides a PCB defect detection method, a device, an equipment and a medium based on manual identification and artificial intelligence, wherein the detection method comprises: scanning a PCB to obtain a PCB image; performing AI identification on PCB image by a detection model of AOI equipment to obtain defect data comprising corresponding positions of one or more defects recognized; intercepting partial image as a PCB sub-image according to the defect data and sending the PCB sub-image to a manual detection workstation; manually identifying each PCB sub-image to obtain a first manual marking result; comparing the first manual marking result and an AI marking result of each PCB sub-image; if they are consistent, taking the first manual marking result or the AI marking result as a final detection result of the PCB sub-image, wherein the AI marking result is obtained by using an AI model to perform AI identification for PCB sub-image. The present disclosure judges whether the manual identi