Stereo matching is to obtain disparity map from two or more images whose pixels show disparity between each other. Because adaptive support-weight algorithm is difficult to meet both accuracy and speed

an improved adaptive support-weight sparse region approach based on HVS （human visual system） is proposed. First

we improve the traditional support-weight formula

and the support-weight of the points can be calculated according to the improved support-weight formula. Second

the dense disparity map is obtained by using sparse region-based matching. Third

left-right consistency check and blocking filling is performed for the obtained disparity map. Final- ly

median filter is used to remove isolated mismatching points and noise points. Experiment results show that

by using the presented method

the matching efficiency is above 90 times faster than that of the adaptive support-weight algorithm proposed rithm is verified for by Yoon

and the matching accuracy is 12. 34% higher than that of SSD

so the improved algoobtaining accurate disparity map at a fast pace and meeting the requirements of system practicability.