Due to the influence of various factors in the production process of metal industrial products, there will be many kinds of defects on the surface. Quality inspection on the surface of metal products is particularly important to ensure the quality of industrial production. This paper based on the Inception-Resnet-V2 network to study the defect detection of steel plates. The network model is improved by adding a CBAM attention module to the original network, which increases the weight of defect-related information, reduces the interference of useless features, and then improves detection accuracy. At the same time, we use Softpool replace the traditional Maxpool pooling method to retain fine- grained feature information and fully capture more image features. Then the detection accuracy can be further improved. In this paper, the steel plate defect images are used as the dataset to train the improved network model. The improved network model can effectively identify cracks, impurities, pitting surface, oxide scale, scratches and other defects on the surface of steel plate. We compare the detection accuracy of the proposed network model with the VGG16, Resnet50 and YOLOv5 network models. The results show that the proposed network architecture significantly improves the defect detection accuracy
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.