Stereoscopic image quality assessment is an effective way to evaluate the performance of stereoscopic video system.However,how to utilize human visual characteristics in quality as sessment is still an issue. In this paper,an objective stereoscopic image quality assessment method based o n disparity space image (DSI) is proposed.In this method,we first construct DSIs from the original and distorted stereoscopic images,respectively. Then,three-dimensional discrete cosine transformation (3D-DCT) and principal c omponent analysis are used to extract the stereoscopic image feature information from the DSIs that reflect the image qual ity and depth perception.Finally,support vector regression (SVR) is performed to predi ct the objective scores of stereoscopic images by establishing the relationship between the stereoscopic image feature information and the subjecti ve scores.Experimental results show that compared with other methods,the Pearson linear correlation coefficien t (PLCC) and Spearman rank-order correlation coefficient (SROCC) indicators r each 0.94on symmetric stereoscopic image database, and the PLCC indicator reaches 0.94and the SROCC indicator reaches 0.91o n asymmetric stereoscopic image database,which indicate the proposed method can achieve higher consistenc y with subjective assessment of stereoscopic images for both symmetric and asymm etric databases.