Principles for the construction of automatic recognizing systems that use stereoscopic vision are discussed. Methods, algorithms, and software are developed for person identification on the basis of stereo images of faces. These facilities are implemented in research prototypes of an automatic recognizing system on the basis of a personal computer. problems of development of computer systems aimed at person identification on the basis of stereo images of faces acquired in real time, as well as the choice of efficient informative features are considered. Methods for processing images with the use of a system for stereoscopic computer vision are also discussed. It is shown that the use of stereo vision allows us to reduce the effect of the face aspect and the distance to the face on the possibility of its recognition by a computer system.
展开▼
