Medicine bottle defect automatic detection method and device and storage medium

• Main Authors: LI BOZHI, WANG SURONG, LI XIN, LI CONG, TANG HONG
• Format: Patent
• Language: Chinese; English
• Published: 25.10.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention provides a medicine bottle defect automatic detection method and device and a storage medium, and the method comprises the steps: detecting the appearance contour defect of a medicine bottle through a Res-Seg semantic segmentation network, and carrying out the foreground extraction and horizontal correction of the medicine bottle; generating medicine bottle defect data through a CycleGAN generative adversarial network; detecting the surface defect of the medicine bottle and the defect of foreign matters in the bottle through a Retinanet target detection network; and detecting the deformation defects of the bottle head and the bottle tail of the medicine bottle through a Resnet image classification network. According to the invention, appearance defects of the medicine bottle and foreign matters in the bottle can be detected, the adaptability to the environment is strong, fine defect characteristics can be effectively detected, a large amount of pre-training work is not needed, and the operation