Browse > Article

A Study on Surface Defect Detection Model of 3D Printing Bone Plate Using Deep Learning Algorithm  

Lee, Song Yeon (Department of Mechatronics Engineering, Graduate School of Korea University of Technology and Education)
Huh, Yong Jeong (School of Mechatronics Engineering, Korea University of Technology and Education)
Publication Information
Journal of the Semiconductor & Display Technology / v.21, no.2, 2022 , pp. 68-73 More about this Journal
Abstract
In this study, we produced the surface defect detection model to automatically detect defect bone plates using a deep learning algorithm. Bone plates with a width and a length of 50 mm are most used for fracture treatment. Normal bone plates and defective bone plates were printed on the 3d printer. Normal bone plates and defective bone plates were photographed with 1,080 pixels using the webcam. The total quantity of collected images was 500. 300 images were used to learn the defect detection model. 200 images were used to test the defect detection model. The mAP(Mean Average Precision) method was used to evaluate the performance of the surface defect detection model. As the result of confirming the performance of the surface defect detection model, the detection accuracy was 96.3 %.
Keywords
Bone plate defect; Convolution neural network; Detection model; Surface defect; 3D printing defect;
Citations & Related Records
연도 인용수 순위
  • Reference
1 IRS Global, "The Entire 3D Printing(Printer, Material) that will Lead the New Industrial Revolution", IRS Global, 1st Edition, pp.310-551, 2016.
2 Dong-Hyun Go, Ji-Hye You, Eun-Kyo Kim, A-Hyeon Gyeon, Chun-Il Lim, Kyoung-Won Seo and Mi-Jeong Kim, "A Study on the Development of Performance Evaluation Guideline for Bone Plates in Maxillofacial Surgery", J.of The Korean Society of Food, Drug and Cosmetic Regulatory Sciences, Vol. 13, pp. 133-141, 2018.
3 Song-Yeon Lee and Yong-Jeong Huh, "A Study on Shape Warpage Defect Detection Medel of Scaffold Using Deep Learning Base CNN", J. of The Korean Society of Semiconductor & Display Technology, Vol.20, pp. 99-103, 2021.
4 Sung-Jin Hwang, Seok-Woo Hong, Jong-Seo Yoon, Hee-Min Park and Hyun-Chul Kim, "Deep Learning-based Porthole Detection System", J. of The Korean Society of Semiconductor & Display Technology, Vol. 20, pp. 88-93, 2021.
5 Chang-Hee Yang, Kyu-Sub Park, Young-Seop Kim and Yong-Hwan Lee, "Comparative Analysis for Emotion Expression Using Three Methods Based by CNN", J. of The Korean Society of Semiconductor & Display Technology, Vol.19, pp. 65-70, 2020.
6 Se-Rang Oh and Young-Chul Bae, "Braille Block Recognition Algorithm for the Visually Impaired Based on YOLO V3", J. of The Korean Institute of Intelligent Systems, Vol.31, pp. 60-67, 2021.   DOI
7 Jeong-Hwan Kim and Ho-Seok Moon, "A Model Development for Object Detection and Classification at Sea using Modified YOLO v4", J. of The Korean Society of Military Operations Research, Vol.47, pp. 13-25, 2021.
8 Ji-Soo Kang, Se-Eun Shim, Sun-Moon Jo and Kyung-Yong Chung, "YOLO based Light Source Object Detection for Traffic Image Big Data Processing", J. of The Korean Convergence for Information Technology, Vol.10, pp. 40-46, 2020.
9 Song-Yeon Lee and Yong-Jeong Huh, "A Study on Performance Comparison of Machine Learning Algorithm for Scaffold Defect Classification", J. of The Korean Society of Semiconductor & Display Technology, Vol.19, pp. 77-87, 2020.
10 Yi-Seul Kim and Jin-Su Cho, "The Telemedicine System based ECG Data using Bio-Signal Meter and Smart Device", J. of The Korean Society of Semiconductor & Display Technology, Vol.11, pp. 51-56, 2012.
11 Song-Yeon Lee and Yong-Jeong Huh, "A Study on Tensile Strength of the Product According to Humidity During 3D Printing Process", J. of The Korean Society of Semiconductor & Display Technology, Vol.20, pp. 177-181, 2021.