Development and Implementation of a YOLOv5-based Adhesive Application Defect Detection Algorithm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study investigated the use of YOLOv5 for defect detection in transparent adhesives, comparing two distinct trainingmethods: one without preprocessing and another incorporating edge operator preprocessing. In the first approach, the originalcolor images were labeled in various ways and trained without transformation. This method failed to distinguish between theoriginal images with properly applied adhesive and those exhibiting adhesive application defects. An analysis of the factors contributingto the reduced learning performance was conducted using histogram comparison and template matching, with performancevalidated by maximum similarity measurements, quantified by the Intersection over Union values. Conversely, thepreprocessing method involved transforming the original images using edge operators before training. The experiments confirmedthat the Canny Edge Detection operator was particularly effective for detecting adhesive application defects and provedmost suitable for real-time defect detection.
Abstract
This study investigated the use of YOLOv5 for defect detection in transparent adhesives, comparing two distinct trainingmethods: one without preprocessing and another incorporating edge operator preprocessing. In the first approach, the originalcolor images were labeled in various ways and trained without transformation. This method failed to distinguish between theoriginal images with properly applied adhesive and those exhibiting adhesive application defects. An analysis of the factors contributingto the reduced learning performance was conducted using histogram comparison and template matching, with performancevalidated by maximum similarity measurements, quantified by the Intersection over Union values. Conversely, thepreprocessing method involved transforming the original images using edge operators before training. The experiments confirmedthat the Canny Edge Detection operator was particularly effective for detecting adhesive application defects and provedmost suitable for real-time defect detection.
참고문헌 (18)
- K. J. Kim, "Implementation of an Image Based Tire Wear Diagnosis System", M.S., pp.2018
- J. Y. Lee, "Implementation of Pedestrian Recognition Based on HOG using ROI for Real Time Processing", J. Inst. Korean Electr. Electron. Eng., 18(4), pp.581~585 (2014)
- S. Y. Jung, "A Method for Detecting Concrete Cracks using Deep-Learning and Image Processing", J. Archit. Inst. Korea Struct. Constr., 35(11), pp.163~170 (2019)
- Y. M. Kim, "Review of Recent Automated Pothole-Detection Methods", Appl. Sci., 12(11), pp.5320~ (2022)
- B. S. Kim, "Detection of corrosion on steel plate by using Image Segmentation Method", J. Korean Inst. Surf. Eng., 54(2), pp.84~89 (2021)
- J. G. Kim, "Development of a Normal", Abnormal RBC Detection Algorithm using YOLOv5, 2022, pp.31(2), 94~100
- J. H. Hwang, "Feature Map Analysis of Neural Networks for the Application of Vacant Parking Slot Detection", Appl. Sci., 13(18), pp.10342~ (2023)
- Z. Liu, "Improved Rectangle Template Matching Based Feature Point Matching Algorithm", Proc. of Chin. Control Decis. Conf., pp.2275~2280 (2019)
- Y. Wen, "Defect Detection of Adhesive Layer of Thermal Insulation Materials Based on Improved Particle Swarm Optimization of ECT", Sensors, 17(11), pp.2440~ (2017)
- M. Barus, "Boron nitride inclusions within adhesive joints: Optimization omechanical strength and bonded defects detection", Int. J. Adhes. Adhes., 98, pp.102531~ (2020)
- J. H. Hwang, "An Approach to Feature Map Based Model Compression of Deep Learning", M. S., pp.2022
- D. Y. Yun, "Development of Kid Height Measurement Application based on Image using Computer Vision", J. Korea Inst. Electron. Commun. Sci., 16(1), pp.117~124 (2021)
- Y. T. Baek, "Intelligent Missing Persons Index System Implementation based on the OpenCV Image Processing and TensorFlow Deep-running Image Processing", J. Korea Soc. Comput. Inf., 22(1), pp.15~21 (2017)
- Y. T. Baek, "Design of OpenCV based Finger Recognition System Using Binary Processing and Histogram Graph", J. Korea Soc. Comput. Inf., 21(2), pp.17~23 (2016)
- C. Wang, "Automotive adhesive defect detection based on improved YOLOv8", Signal Image Video Process., 18, pp.2583~2595 (2024)
- J. S. Jang, "Implementation of an OpenCV based Low-Cost Surface Pressure Analysis System", Asiapac. J. Converg. Res. Interchange, 10(4), pp.37~49 (2024)
- M. A. Ilani, "Automatic Image Annotation (AIA) of AlmondNet-20 Method for Almond Detection by Improved CNN-based Model", M. S., pp.2024