A wave-front aberration measurement method of lithographic projection lens based on adaptive aerial image denoising is proposed. Principal component analysis (PCA) and multivariate linear regression analysis are used for model generation. Weighted least-square (WLSQ) method based PCA is used to get the principal component coefficients that are used for extracting the actual Zernike coefficients. Both the noise model of aerial images and the standard deviation model of noises are obtained by statistical analysis of actually measured aerial images. The standard deviation of the noise is used as weighting factors of the weighted least-square method. Accurate principal component coefficients and Zernike coefficients can be calculated because of the adaptive and lossless denoising ability of this method. Compared with wave-front aberration measurement techniques based on principal component analysis of aerial images (AMAI-PCA), the new method can provide more accurate results. Simulations show that AMAI-WLSQ can enhance the accuracy by more than 30% when the range of wavefront aberration is within 0.1λ. Experiments also show that AMAI-WLSQ can detect aberration shifts more accurately.