Concerning the collinearity problem between the regressors in functional Magnetic Resonance Imaging (fMRI) model, a method of orthogonalization was proposed. Firstly, the regressors of interest and the regressors to be orthogonalized were determined. Then, the related part with regressos of interest was removed from the regressors to be orthogonalized, and the collinear regressors of the model were orthogonally decomposed into independent parts to eliminate the effect of collinearity. The influence of orthogonalization on General Linear Model (GLM) was also discussed and analysed. Finally, the experiments were carried out through some synthetic data and a current popular fMRI data analysis software package-Functional magnetic resonance imaging of the brain Software Library (FSL).The experimental results show that, the method of orthogonalization can eliminate the collinearity in the model and improve the significance of the regressors of interest to achieve accurate brain functional localization. The proposed method of orthogonalization can be used for the basic research and clinical treatment of brain.