Method and system for detecting defects in a targeted printed circuit board (PCB) based on an Artificial Intelligence (AI)

The present invention relates to a method 100 and system for detecting defects in a targeted printed circuit board (PCB) based on an Artificial Intelligence (AI) comprising: providing an image input of the targeted PCB into a pre-trained primary neural network 102; extracting a plurality of feature maps from the image input into a pre-determined number of layers based on semantic and spatial information, arranged in a top-down pathway 104; processing at least one pre-determined feature map layer via a pyramid-structured model coupled with a selective feature attention (SF-PSPyramid) 106; passing the processed feature map layer to a Region of Interest (ROI) align for normalisation 108; and outputting and visualising the processed layer through an output layer, wherein, the output layer displaying the result 110 of the defects on the targeted PCB.