光学精密工程2026，Vol.34Issue(7)：1111-1127,17.DOI:10.37188/OPE.20263407.1111
SAM提取多维灰度作为输入的视觉测量误差补偿
Visual measurement error compensation based on multi-dimensional grayscale extracted by SAM
摘要
Abstract
To mitigate measurement errors induced by illumination variations in precision image measure-ment,an error compensation model is proposed based on multidimensional grayscale features extracted via the Segment Anything Model(SAM)and fitted using a Whale Optimization Algorithm-optimized Radial Basis Function(WOA-RBF)neural network.A mathematical model describing illumination-induced edge shift is established to characterize the nonlinear effects of light intensity and surface scattering proper-ties on measurement accuracy.Leveraging SAM's zero-shot segmentation capability,average grayscale values from heterogeneous material regions are automatically extracted as multidimensional feature inputs to represent complex image characteristics.The WOA is employed to optimize the parameters of the RBF neural network,enabling accurate compensation of edge shift errors.Comparative experiments on chromi-um-zirconium-copper fixture measurements,benchmarked against one-dimensional linear fitting,GA-LSSVM,and SVR methods,demonstrate that the proposed model achieves an RMSE of 2.07 μm,an MAE of 1.73 μm,and an R² of 0.99(with the Zernike moment sub-pixel algorithm as a representative case).Consistent accuracy and strong robustness are observed across various sub-pixel edge detection al-gorithms,indicating that the proposed approach provides an effective solution for illumination-induced er-rors in precision image measurement.关键词
计算机视觉/边缘检测/误差补偿/SAM模型/鲸鱼优化/径向基函数神经网络Key words
computer vision/edge detection/error compensation/segment anything model/whale opti-mization algorithm/radial basis function neural network分类
信息技术与安全科学引用本文复制引用
王宇恒,谷玉海,王亚冰,张伟伟,孙海洋..SAM提取多维灰度作为输入的视觉测量误差补偿[J].光学精密工程,2026,34(7):1111-1127,17.基金项目
国家自然科学基金资助项目(No.12405374,No.12475330) （No.12405374,No.12475330）
中国科学院科技基础资源专项(No.2025000148) （No.2025000148）
