Abstract：In order to solve the problem of difficulty in identifying and locating lens defects, a multi-scale lens defect detection system based on lightweight feature selection (LFSN) is designed. First, in order to increase the image quality, the fault images are fused using the Fourier transform after being obtained through the design of a four-step phase-shifted raster optical imaging system; Then, aiming to optimise the model’s capacity to learn about various defect sizes, the LFSN computes the anchorless frame branching loss during training in order to acquire the ideal feature layer information and update the parameters; Additionally, the system employs depth-separated variable convolution to enhance the offset of pixel points in the plane via bilinear interpolation, thereby enhancing the defect morphology model’s capacity for active learning and somewhat lowering the number of model training parameters to shorten the detection time. Simultaneously, the optimisation of the regression localization loss identifies the training tasks in each stage. The early stage of the prediction frames regression is guided by the primary penalty term, and the late stage of the prediction frames regression is guided by the normalised quadratic term, which brings the prediction frame closer to the real value. Lastly, a dataset is created for comparative studies and lens defect photos were obtained experimentally. The research data demonstrate that this inspection method has a 96.3% accuracy of identifying and locating defects in lens, with a single frame detection time of 24.9ms.
YAO H B, MA G D, SHEN B G, et al. Resin lens defect classification based on image processing［J］. Journal of Optoelectronics Laser. 2014. 25(2): 330-335.
［2］
SATORRES MARTINEZ S, GóMEZ ORTEGA J, GáMEZ GARCíA J, et al. A machine vision system for defect characterization on transparent parts with non-plane surfaces［J］. Machine Vision and Applications, 2012, 23: 1-13.
［4］
KIM K B, SONG D H. Automatic Defect Inspection with Adaptive Binarization and Bresenhams algorithm for Spectacle Lens Products［J］. Journal of the Korea Institute of Information and Communication Engineering, 2017, 21(7): 1429-1434.
［1］
NG H F. Automatic thresholding for defect detection［J］. Pattern Recognition Letters, 2006, 27(14): 1644-1649.
［3］
YI J, KIM K H, JUNG S H. Lens Inspection System Using LoG and Multi-level Thresholds［C］//Sixth International Conference on Advanced Language Processing and Web Information Technology (ALPIT 2007). IEEE. Luoyang, China. 2007: 298-303.
2024, Vol. 45 
