Browse > Article

A Comparative Study on Deep Learning Models for Scaffold Defect Detection  

Lee, Song-Yeon (Mechatronics Engineering, Graduate School of Korea University of Technology and Education)
Huh, Yong Jeong (Department of Mechatronics Engineering, Korea University of Technology and Education)
Publication Information
Journal of the Semiconductor & Display Technology / v.20, no.2, 2021 , pp. 109-114 More about this Journal
Abstract
When we inspect scaffold defect using sight, inspecting performance is decrease and inspecting time is increase. We need for automatically scaffold defect detection method to increase detection accuracy and reduce detection times. In this paper. We produced scaffold defect classification models using densenet, alexnet, vggnet algorithms based on CNN. We photographed scaffold using multi dimension camera. We learned scaffold defect classification model using photographed scaffold images. We evaluated the scaffold defect classification accuracy of each models. As result of evaluation, the defect classification performance using densenet algorithm was at 99.1%. The defect classification performance using VGGnet algorithm was at 98.3%. The defect classification performance using Alexnet algorithm was at 96.8%. We were able to quantitatively compare defect classification performance of three type algorithms based on CNN.
Keywords
Algorithm Evaluate; Classification Performance Compare; CNN; Defect Detection Model; Scaffold Defect;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Sang-Ho Park, Joo-Hyeong Lee and Jung-Min Kim, "Development of Heating System for Ensuring Accuracy of Output for Open 3D Printer", J. of The Korean Society of Mechanical Engineers, Vol.41, pp. 477-482, 2017.
2 Song-Yeon Lee and Yong-Jeong Huh, "A Study on Shape Warpage Defect Detection Model of Scaffold Using Deep Learning Based CNN", J. of The Korean Society of Semiconductor & Display Technology, Vol.19, pp. 59-64, 2021.
3 Soo-Hyeon Lee, Dong-Hyun Kim and Hae-Yeoun Lee, "Camera Model Identification Using Modified DenseNet and HPF", J. of Korean Institute of Information Technology, Vol.17, pp. 11-19, 2019.
4 Sung-Soo Hong and Jung-Hee Han, "Semiconductor Process Inspection Using Mask R-CNN", J. of The Korea Society of Semiconductor & Display Technology, Vol.19, pp.12-18, 2020.
5 Song-Yeon Lee and Yong-Jeong Huh, "A Study on Square Pore Shape Discrimination Model of Scaffold Using Machine Learning Based Multiple Linear Regression", J. of The Korean Society of Semiconductor & Display Technology, Vol.19, pp. 59-64, 2020.
6 Song-Yeon Lee and Yong-Jeong Huh, "A Study on Prediction Model of Scaffold Pore Size Using Machine Learning", J. of The Korean Society of Semiconductor & Display Technology, Vol.18, pp. 46-50, 2019.
7 Yong-Hwan Lee and Heung-Jun Kim, "Implementation of Fish Detection Based on Convolution Neural Networks", J. of The Korea Society of Semiconductor & Display Technology, Vol.19, pp.124-129, 2020.
8 Chang-Hee Yang, Kyu-Sub Park, Young-Sub Kim and Yong-Hwan Lee, "Comparative Analysis for Emotion Expression Using Three Methods Based by CNN", J. of The Korea Society of Semiconductor & Display Technology, Vol.19, pp.65-70, 2020.