1. Zhejiang Institute of Metrology, Hangzhou, Zhejiang 310018, China
2. College of Metrological Technology and Engineering, China Jiliang University, Hangzhou, Zhejiang 310018, China
3. Key Laboratory of Digital Precision Measurement Technology of Zhejiang Province, Hangzhou, Zhejiang 310018, China
Abstract：Due to some appearance defects in the production process of curved glass of mobile phone, a defect detection method of curved glass of mobile phone was proposed to solve the problems of difficult imaging and extraction of defects on curved glass. Firstly, shape matching was carried out on the curved glass plane images, and the matched images were processed by difference and morphology to extract the defect features. Secondly, a defect extraction algorithm based on connected domain analysis and area threshold segmentation was used for curved glass images. Thirdly, the image frequency domain enhancement and logarithmic transformation defect extraction algorithm were used for the R-angle image of curved glass. Finally, after extracting the defects of each part, the characteristics of all kinds of defects were calculated, and the defects were classified according to the characteristics, and the obtained defect data was compared with the data obtained by the image measurement instrument. The results showed that the algorithm can accurately extract the common scratches, stains, abrasions and bubbles on the curved glass surface of mobile phones, and the size accuracy of the defects can reach 20μm.
Martínez S S, Ortega J G, García A S, et al. An automatic procedure to identify the areas of interest for the automated inspection of headlamp lenses［C］//IEEE. Emerging Technologies & Factory Automation, 2010.
［5］
Ngo C, Park Y J, Jung J, et al. A new algorithm on the automatic TFT-LCD mura defects inspection based on an effective background reconstruction ［J］. Journal of the Society for Information Display, 2017, 25(12): 737-752.
Martínez S S, Ortega J G, García A S, et al. A sensor planning system for automated headlamp lens inspection ［J］. Expert Systems with Applications, 2009, 36(5): 8768-8777.
［4］
Chang Y C, Chang K H, Meng H M, et al. A Novel Multicategory Defect Detection Method Based on the Convolutional Neural Network Method for TFT-LCD Panels ［J］. Mathematical Problems in Engineering, 2022, 23(10): 828-833.
［6］
Lou W M, Cao P, Wang F Y, et al. Error analysis and measurement methods of curved optical element surface defects dark-field imaging inspection system based on multi-axis kinematics ［J］. Optics Communications, 2022, 52(1): 124-134.
Wang C S, Huang Y J, Zhang X A, A machine vision based method for detecting scratches and defects in curved glass ［J］. Instrumentation and Testing Technology, 2019, 39 (1): 134-139.
Guerra-Hernández J, Tomé M, González-Ferreiro E. Using low density LiDAR data to map Mediterranean forest characteristics by means of an area-based approach and height threshold analysis ［J］. Revista de Teledetección, 2016(46): 12-33.
Yao L J, Wang Y B, Jiang W, Optimization Design and Simulation Implementation of Butterworth High Pass Filter ［J］. Mechanical and Electrical Engineering Technology, 2023, 52 (2): 292-296.
［16］
Liu B, Zhou B, Kong J Z, et al. The Cut-Off Frequency of High-Pass Filtering of Strong-Motion Records Based on Transfer Learning ［J］. Applied Sciences, 2023, 13(3):1500.
［2］
Martínez S S, Ortega J G, García A S, et al. An expert knowledge based sensor planning system for car headlight lens inspection［C］//Computational Intelligence in Decision and Control-8th International FLINS Conference. 2008.
Hu W, Zhang Y J, Zhang T, et al. Median filtering detection based on multi residual learning and attention fusion ［J］. Optoelectron Laser, 2023, 34 (1): 81-89.
Jian C X, Gao J. Research on Visual Inspection Method for Surface Defects of Mobile Phone Glass Screen ［J］. Packaging Engineering, 2018, 39 (5): 16-21.
Ye Q, Song D, Cao Y J, et al. Research on Image Information Missing Detection Based on Fuzzy Difference Method ［J］. Computer Simulation, 2023, 40 (1): 85-88.
2023, Vol. 44 
