Image matching is one of the most important tasks in computer vision. Most existing methods cannot achieve precise pattern matching under spatially varying illumination variations and partial occlusions. In this paper, we explicitly model spatial illumination variations as low-order polynomial functions in an energy minimization framework. Data constraints for the alignment and illumination parameters are derived from the first-order Taylor series approximation of the generalized brightness assumption with low-order polynomials used for modeling spatial illumination variations. We formulate the parameter estimation problem in a weighted least-squares framework by incorporating the influence function from robust estimation to derive an iterative reweighted least-squares algorithm. A dynamic weighting scheme, which combines the factors from the influence function, a measure of consistency between image gradients, and nonlinear image intensity sensing characteristics is used to improve the robustness of the image matching. In addition, a selective constraint sampling and an estimation-warping alternating strategy are used in the proposed algorithm to improve the efficiency and accuracy of the estimation. We have successfully applied the proposed algorithm to estimate affine transformations under partial occlusion and spatially varying illumination change for various industrial inspection tasks. Experimental results are shown to demonstrate the robustness, efficiency, and accuracy of the algorithm.