金屬二次加工自動化光學檢測技術 文 / 劉曉薇工研院量測中心智能感測系統技術部工程師陳思翰明志科技大學工業工程與管理系助理教授 摘要 (Highly Specular Reflection HSR) 3K 1K 80 一 前言 100 (Machine Vision) (Field Programmable Gate Array FPGA) 二 文獻探討 (Machined Surface) (Anodized Surface) (Plated Surface) (Painted Surface) (Highly Specular Reflection HSR) (Manual Detection) (Flashlight Detection) 14 March 2017 Taiwan Machinery Monthly
1 HSR Suresh et. al (1983) Garacia et al (1994) Sakurai (2002) Mahaut et. al (2004) Ng (2007) Yun et al. (2008) Medina (2008) Tang et. al (2009) Perng et al. (2010) Zhang et al. (2011) Li et al. (2013) Neogi et al (2014) Chen (2016) IC Hot-Al-Cu (Stereo Microscope) CCD Medina Gabor Kirsch (Industrial Endoscope) Z (Back Light) (Polarizing Filer) (Polarized Light) LED 1K 2K 4K (Dark-field Illumination) CCD 2017/3 15
HSR HSR HSR HSR HSR (a) 1 (a) 三 技術概況說明 3.1 金屬表面瑕疵檢測光 學系統 6K F-Mount LED LED 40mm LED 3 400mm 140mm 145µm 圖 1(a) 圖 1(b) 3.2 影像前處理 圖 1((a) 圖 2(a) 3K 1K (b) (b) 10 圖 2(b) 圖 2(c) 0 1,000 0 255 圖 2(d) α β 圖 2(e) (Region of Interesting ROI) (Mask Image) 3.3 瑕疵檢測演算法 (Edge Detection) (Morphology) 圖 3 圖 4 16 March 2017 Taiwan Machinery Monthly
(a) (b) (c) (e) (d) 300 250 200 150 100 50 0 Histogram 1 101 201 301 401 501 601 701 801 901 1001 1101 1201 1301 1401 1501 1601 1701 1801 1901 2001 2101 2201 2301 2401 2501 2601 2701 2801 2901 3001 2 (a) (b) (c) (d) (e) -1-2 -1-1 0 1 0 0 0-2 0 2 1 2 1-1 0 1 3 4 (Gupta and Mazumdar, 2013) (Sobel Operation) γ (Dilation) 四 技術成果說明 1,000 75mm 145mm α 100 β 75mm γ 25 2017/3 17
表 2 表 2 98.5% 98.1% 99.3% (Over Kill Rate)0.3%(Under Kill Rate) 18.75% 59.3% 24.3% 34.8% 0.1% 98.6% 表 3 2 18.75% (12/64) 0.3% (3/936) 98.5% (985/1000) 59.3% (19/32) 0.0% (0/968) 98.1% (981/1000) 24.3% (7/29) 0.0% (0/971) 99.3% (993/1000) 34.8% 0.1% 98.6% 表 4 20 FPGA 80 13 3K 1K 五 二次加工的未來需求與展望 75mm 98.6% 34.8% 0.1%80 37.5MBytes 3 4 18 March 2017 Taiwan Machinery Monthly
六 機器視覺的未來應用與挑戰 OEM 參考文獻 1. 2012 101 AOI Forum & Show Chen, S. H. (2016). Inspecting lens collars for defects using discrete cosine transformation based on an image restoration scheme. IET Image Processing, 10(6), 474-482. 2.Gupta, S., & Mazumdar, S. G. (2013). Sobel edge detection algorithm. International Journal of Computer Science and Management Research, 2(2), 1578-1583. 3.Li, L., Wang, Z., Pei, F., & Wang, X. (2013). Improved illumination for vision-based defect inspection of highly reflective metal surface. Chinese Optics Letters, 11(2), 021102. 4.Mahaut, S., Godefroit, J. L., Roy, O., & Cattiaux, G. (2004). Application of phased array techniques to coarse grain components inspection. Ultrasonics, 42(1), 791-796. 5.Neogi, N., Mohanta, D. K., & Dutta, P. K. (2014). Review of vision-based steel surface inspection systems. EURASIP Journal on Image and Video Processing, 2014(1), 50. 6.Ng, T. W. (2007). Optical inspection of ball bearing defects. Measurement Science and Technology, 18(9), N73-N76. 7.Perng, D. B., Chen, S. H., & Chang, Y. S. (2010). A novel internal thread defect auto-inspection system. The International Journal of Advanced Manufacturing Technology, 47(5-8), 731-743. 8.Suresh, B. R., Fundakowski, R. A., Levitt, T. S., & Overland, J. E. (1983). A real-time automated visual inspection system for hot steel slabs. IEEE Transactions on Pattern Analysis and Machine Intelligence, (6), 563-572. 9.Tang, B., Kong, J. Y., Wang, X. D., & Chen, L. (2009, April). Surface inspection system of steel strip based on machine vision. In Database Technology and Applications, 2009 First International Workshop on (pp. 359-362). IEEE. 10.Yun, J. P., Choi, S., Seo, B., & Kim, S. W. (2008). Realtime vision-based defect inspection for high-speed steel products. Optical Engineering, 47(7), 077204-077204. 11.Zhang X. W., Ding Y. Q., Lv Y. Y., Shi A. Y., and Liang R. Y. (2011). A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM. Expert Systems with Applications, 38(5), 5930-5939. 2017/3 19