지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
이용수10
Ⅰ. Introduction····················································· 11.1 Research background···································· 11.2 Defect detection system································ 41.3 Research purpose and summary···················· 8Ⅱ. Imaging System················································92.1 Photometric stereo·········································92.2 Overview of Photometric stereo···················102.3 Optical system configuration························11Ⅲ. Defect detection deep-learning model···········133.1 Overview of Neural Network························133.2 CNN-based defect detection model·············163.2.1 CNN model···············································163.2.2 YOLO model·············································193.3 Proposed defect detection model·················213.3.1 Proposed model·······································213.3.2 Performance enhancement model···········23Ⅳ. Experiments and Results································254.1 Experiment environment and setting···········254.1.1 Definition of surface defects ···················254.1.2 Ground truth dataset ······························264.1.3 Experiment environment ·························284.2 Defect detection result·································334.2.1 Definition of performance metric············384.2.2 Quantitative measurement······················41Ⅴ. Conclusion and Future work··························47R e f e r e n c e s··················································49A b s t r a c t ·······················································54
0