Relative Radiometric Normalization for Multi-sensors and Multi-temporal based on Pseudo-invariant Feature Extraction Technology developments promote the abundance availability of multi-temporal satellite imagery data. Otherwise, the utilization of such satellite data have not been implemented optimally due to several limitation requirements. The utilization of the multi-temporal satellite images for change detection is advantageous for modelling and predicting spatial changes in particular period of time. However, in the implementation, the radiometric correction on either multi-temporal or also multi-sensors is required. In this research, weighted regularized generalized canonical correlation analysis (WRGCCA) is proposed to select invariant features or pseudo-invariant features (PIFs) for multi-sensors and multi-temporal images. The method is the improvement of multivariate alteration detection (MAD) that adopts canonical correlation analysis (CCA) and its extension, generalized canonical correlation analysis (GCCA), to detect bitemporal and multi-temporal data respectively. However, each of the methods, CCA and GCCA, has the limitation on differentiating acceptable PIFs due to sensitive to spatial changes. Therefore, with the utilization of weighting and regularization functions to the algorithm, the proposed method WRGCCA with the aid of iterative reweighted multivariate alteration detection (IRMAD) can select reliable PIFs and yielding more accurate PIFs significantly to 10% - 50% determined from root mean square error (RMSE). The improved PIFs selection can be explained by qualitative and quantitative analysis based on the multi-temporal image normalization.