AUTHOR=Gong Guoqiang , Huang Jun , Wang Hemin 

TITLE=Flaw Detection in White Porcelain Wine Bottles Based on Improved YOLOv4 Algorithm

JOURNAL=Frontiers in Bioengineering and Biotechnology

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.928900

DOI=10.3389/fbioe.2022.928900

ISSN=2296-4185

ABSTRACT=Aiming at the problems of low detection accuracy and slow detection speed in the flaw detection of white porcelain wine bottles, an improved flaw detection algorithm based on YOLOv4 was proposed. By adding CA (Coordinate Attention) to the backbone feature extraction network, the extracting ability of flaw features of white porcelain bottle was improved. Deformable convolution is added to locate flaws more accurately, so as to improve the detection accuracy of flaws by the model. EIoU (Efficient Intersection over Union) was used to replace CIoU (Complete Intersection over Union) in YOLOv4 to improve the loss function and improve the model detection speed and accuracy. Experimental results on the surface flaw data set of white porcelain wine bottle show that the proposed algorithm can effectively detect the flaws of white porcelain wine bottle, the mean Average Precision (mAP) of the model can reach 92.56%, and the detection speed can reach 37.17 frames /s.