Deep Learning Approaches for Dynamic Object Understanding and Defect Detection

Yuan-Tsung Chang,
W. K. T. M. Gunarathne,
Timothy K. Shih,

Abstract


Industrial product defect detection has been known for a while to make sure the released products meet the expected requirements. Earlier, product defect detection was commonly done manually by humans; they have detected whether the products consist of defects or not by using their human senses based on the standard. In this industrial era, product defect detection is expected to be faster and more accurate, while humans could be exhausted and become slower and less reliable. Deep learning technology is very famous in the field of image processing, such as image classification, object detection, object tracking, and of course the defect detection. In this study, we propose a novel automated solution system to identify the good and defective products on a production line using deep learning technology. In the experiment, we have compared several algorithms of defect detections using a data set, which comprises 20 categories of objects and 50 images in each category. The experimental results demonstrated that the proposed system had produced effective results within a short time.


Citation Format:
Yuan-Tsung Chang, W. K. T. M. Gunarathne, Timothy K. Shih, "Deep Learning Approaches for Dynamic Object Understanding and Defect Detection," Journal of Internet Technology, vol. 21, no. 3 , pp. 783-790, May. 2020.

Full Text:

PDF

Refbacks

  • There are currently no refbacks.





Published by Executive Committee, Taiwan Academic Network, Ministry of Education, Taipei, Taiwan, R.O.C
JIT Editorial Office, Office of Library and Information Services, National Dong Hwa University
No. 1, Sec. 2, Da Hsueh Rd., Shoufeng, Hualien 974301, Taiwan, R.O.C.
Tel: +886-3-931-7314  E-mail: jit.editorial@gmail.com