機器視覺應用於車載鏡頭鏡片表面瑕疵之檢測

The Application of Machine Vision to Improve the Surface Defect Detection of Vehicle Camera Lens

陳昭雄(CHAIO-SHIUNG CHEN)；梁世承(SHE-CHENG LIANG)；呂至翔(ZHI-XIANG LU)；簡伯丞(BO-CHENG JIAN)

車載鏡頭 ； 機器視覺 ； 影像處理 ； 瑕疵檢測 ； vehicle camera lens ； machine vision ； image processing ； effect detection

科學與工程技術期刊

19卷2期（2023 / 09 / 01）

73 - 83

繁體中文;英文

本文主要針對車載鏡頭的塑膠鏡片利用影像處理技術做表面瑕疵的自動檢測，塑膠鏡片在製程中容易產生刮痕、汙垢、氣孔等的瑕疵，這些瑕疵很難用人工目視檢測出來。首先，建立機械視覺的實驗平台，包括個人電腦、Basler Gige乙太網路、遠心鏡頭、CCD照相機、LED環形燈光和定電流調光器。然後發展影像處理方法以檢測鏡片瑕疵。在影像定位方面，本文利用模板匹配和二維計量演算法以找出鏡片所在的位置。在瑕疵檢測方面，先以高斯拉普拉斯濾波器強化瑕疵的邊緣形狀，以動態閥值二值化分割出瑕疵的影像。再以形態學的膨脹和侵蝕法連接破碎瑕疵圖像，以斷開與連通域的方法標示瑕疵的位置，然後透過特徵篩選對瑕疵面積大小進行計算。最後，透過實際的塑膠鏡片的檢測實驗來驗證本文所提方法的有效性，瑕疵辨識成功率可達97%。

This paper examines the image processing technology to automatically detect surface defects happening to the vehicle plastic lens. Defects usually happen during the lens manufacturing process such as scratches, dirt, and pores, and these defects are difficult to detect manually. To deal with these issues, firstly, an experimental platform is established for machine vision, including a personal computer, Basler Gige Ethernet, telecentric lens, CCD camera, LED ring light and constant current dimmable driver. Image processing methods are then developed to detect lens defects. Secondly, template matching and 2D metrology algorithms are used to position the lens. Thirdly, Gaussian Laplacian filter is used to enhance the defect edge, and then dynamic binarization is used to segment the defect. Fourthly, the defect image is connected by morphological expansion and erosion method. Fifthly, the location of the defect is marked by opening and closing method, and the size of the defect area is calculated through feature extraction. Finally, the effectiveness of the method proposed in this paper is verified through the actual plastic lens detection experiment, and the defect identification success rate is up to 97%.

1. Anupama, S.,Prajwalasimha, S. N. ,Swapna, H.(2018).Finger print image enhancement using thresholding and binarization techniques.2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT)
2. Azam, M.,Bouguila, N.(2019).Texture image categorization in wavelet domain via naive bayes classifier based on Laplace and generalized gaussian distribution.2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)
3. Bao, N.,Fan, Y.,Simeone, A.,Li, T.,Luo, Z.(2021).Defect detection system for smartphone front camera based on improved template matching algorithm.Procedia CIRP,103,268-273.
4. Bazin, A. I.,Cole, T.,Kett, B.,Nixon, M. S.(2006).An automated system for contact lens inspection.ISVC 2006,4291,141-150.
5. Cho, C. S.,Chung, B. M.,Park, M. J.(2005).Development of real-time vision-based fabric inspection system.IEEE Transactions on Industrial Electronics,52(4),1073-1079.
6. Ding, Z. J.,Zhang, Y. ,Yang, A. Q. ,Li, D.(2012).Image matching of gaussian blurred image based on sift algorithm.2012 International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)
7. Kuo,C. F. J.,Lo, W. C.,Huang, Y. R.,Tsai, H. Y.,Lee, C. L.,Wu, H. C.(2017).Automated defect inspection system for CMOS image sensor with micro multi-layer nonspherical lens module.Journal of Manufacturing Systems,45,248-259.
8. Lin, C. S.,Loh, G. H.,Fu, S. H.,Yang, S. W.,Chang, H. K.,Yeh, M. S.(2010).An automatic evaluation method for the surface profile of a microlens array using an optical interferometric microscope.Measurement Science and Technology,21(10),105304.
9. Lin, C. S.,Loh, G. H.,Tien, C. L.,Lin, T. C.,Chiou, Y. C.(2013).Automatic optical inspection system for the micro-lens of optical connector with fuzzy ratio analysis.Optik -International Journal for Light and Electron Optics,124(17),3085-3090.
10. Lin, H. D.,Chiu, Peter Y. S.,Hsu, S. Y.(2011).A visual inspection system for quality control of optical lenses.International Journal of the Physical Sciences,6(11),2701-2709.
11. Mallick, A.,Roy, S. ,Chaudhuri, S. S.(2014).Optimization of Laplace of gaussian (log) filter for enhanced edge detection: a new approach.2014 International Conference on Control, Instrumentation, Energy & Communication(CIEC)
12. Mitra, A.,Roy, S. ,Setua, S. K.(2014).Morphologically contour extraction of decisive objects from image.2014 First International Conference on Automation, Control, Energy and Systems (ACES)
13. Narayanan, V. S.,Kasthuri, N.(2018).Performance evaluation of image binarization technique for recognition of ancient historical documents.2018 International Conference on Intelligent Computing and Communication for Smart World (I2C2SW)
14. Ramesha, M. S.,Sridhara, B. ,Anughna, N. ,Anne, A. B, ,Gowda,Veeresh, P. T.(2020).Centroiding and connected component labeling for radar images using image processing algorithms.2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE)
15. Tang, H. Y.,Liang, S.,Yao, D.,Qiao, Y. G.(2023).A visual defect detection for optics lens based on the YOLOv5 -C3CA-SPPF network model.Optics Express,31(2),2628-2643.
16. Tsai, T. H.,Lee, T. Y. ,Chen, P. H.(2017).The ROI of rice planthopper by image processing.2017 International Conference on Applied System Innovation (ICASI)
17. 王泓翔(2017)。國立台北科技大學工業工程與管理系。
18. 吳志玲(2007)。國立交通大學工業工程與管理學系。
19. 柳長志(2013)。崑山科技大學電機工程系。
20. 張峻睿(2019)。國立雲林科技大學電機工程系。
21. 許佳蓉(2017)。國立台北科技大學自動化科技研究所。
22. 蔡傳暉(2013)。華梵大學機電工程學系。