| Title |
Appropriate Scaled Deep Learning Model for Surface Defects Classification |
| DOI |
https://doi.org/10.5370/KIEE.2020.69.12.1957 |
| Keywords |
Deep learning; Convolutional neural network; Appropriate Scaled Model; Surface Defects Detection |
| Abstract |
In this paper, we propose a method of surface defect image classification for metal cases using a Convolutional Neural Network (CNN) deep learning model. We show the feasibility and effectiveness of our appropriate scaled CNN model using real-word data on metal case images with and without defects under different surface and lighting conditions. In addition, we analyze learning behaviors on three different data sets. The results of our work in this study have the potential to have a significant impact on the manufacturing industry |