Abstract
This paper presents an improved Convolutional Neural Network (CNN) architecture to recognize surface defects of the Calcium Silicate Board (CSB) using visual image information based on a deep learning approach. The proposed CNN architecture is inspired by the existing SurfNet architecture and is named SurfNetv2, which comprises a feature extraction module and a surface defect recognition module. The output of the system is the recognized defect category on the surface of the CSB. In the collection of the training dataset, we manually captured the defect images presented on the surface of the CSB samples. Then, we divided these defect images into four categories, which are crash, dirty, uneven, and normal. In the training stage, the proposed SurfNetv2 is trained through an end-to-end supervised learning method, so that the CNN model learns how to recognize surface defects of the CSB only through the RGB image information. Experimental results show that the proposed SurfNetv2 outperforms five state-of-the-art methods and achieves a high recognition accuracy of 99.90% and 99.75% in our private CSB dataset and the public Northeastern University (NEU) dataset, respectively. Moreover, the proposed SurfNetv2 model achieves a real-time computing speed of about 199.38 fps when processing images with a resolution of 128 × 128 pixels. Therefore, the proposed CNN model has great potential for real-time automatic surface defect recognition applications.
Highlights
Today, Artificial Intelligence (AI) has become the mainstay keystone of industrial development.Manufacturing plants have replaced their workforces with machines and are moving towards complete automation to achieve the goal of reducing labor costs and improving efficiency
The last two models might significantly increase the parameters of the Convolutional Neural Network (CNN) model, but they can help us to understand the effect of the PReLU function and the wider receptive field on the defect recognition performance of the proposed SurfNetv2 model
We compare the experiment results of the proposed SurfNetv2 model with five state-of-the-art methods, and conduct some discussions based on our observations
Summary
Artificial Intelligence (AI) has become the mainstay keystone of industrial development. This manual inspection method usually increases labor costs, and it is difficult to maintain 24 h operation. CSB dataset, the performance of the proposed CNN model is evaluated by comparing it with other state-of-the-art methods. Experimental results show that the proposed SurfNetv produces an average recognition rate of 99.90% and 99.75% in our private CSB dataset and the public NEU dataset, respectively, which accuracy rate of 99.90% and 99.75% in our private CSB dataset and the public NEU dataset, clearly outperforms the other five state-of-the-art methods. We discuss some possible directions for future research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
