Product quality detection method based on machine vision

The invention belongs to the technical field of intelligent detection, and provides a product quality detection method based on machine vision, which comprises the following steps: selecting video data based on the contour of the sealing part of a detection part, framing the selected video data to obtain a plurality of frame numbers of images, calculating the air tightness evaluation parameters of the detection part, and determining the air tightness of the detection part according to the air tightness evaluation parameters. And comparing the air tightness evaluation parameters of the detection part with a preset air tightness evaluation parameter threshold value of the detection part to judge the air tightness of the detection part, obtaining use data corresponding to the detection part after air tightness evaluation, and substituting the use data into an air tightness influence degree model to obtain the air tightness influence degree of the detection part in a use cycle. And calculating the air tightness c