Hyunkyu Shin1, Yonghan Ahn2, Mihwa Song3, Heungbae Gil3, Jungsik Choi4,*, Sanghyo Lee5,*
CMC-Computers, Materials & Continua, Vol.75, No.3, pp. 4753-4766, 2023, DOI:10.32604/cmc.2023.038362
Abstract Recently, convolutional neural network (CNN)-based visual inspection has been developed to detect defects on building surfaces automatically. The CNN model demonstrates remarkable accuracy in image data analysis; however, the predicted results have uncertainty in providing accurate information to users because of the “black box” problem in the deep learning model. Therefore, this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect identification. The visual representative gradient-weights class activation mapping (Grad-CAM) method is adopted to provide visually explainable information. A visualizing evaluation index is proposed to quantitatively analyze visual representations; this index reflects a rough estimate… More >
Login
Register
