Skip to Main Content
The study and implementation of a binocular vision based on human face description. In the traditional face recognition, we based on the principle of human visual design of the double cameras to extract three-dimensional information. For the two cameras input video frame, according to correlative coefficient and polar constraints to find the corresponding relationship of the two of the map's each point and then get the same 3D space point to a different camera images of the corresponding points of disparity, with disparity to characterize the depth of information. These depth data that 2D images do not have is the new method which is different from the traditional face recognition form. This realization of the algorithms' system structure and the final results will also be given. In this paper, the algorithm accuracy and the corresponding point on the matching rate have been enhanced and effective, accurate face recognition to provide a good way.