VIDEO PROCESSING SYSTEM, VIDEO PROCESSING METHOD, AND VIDEO PROCESSING DEVICE FOR PORTABLE TERMINAL OR FOR SERVER AND METHOD FOR CONTROLLING AND PROGRAM FOR CONTROLLING SAME

摘要

The objective of the present invention is to report real-time recognition results with respect to a recognition subject in a video while maintaining recognition accuracy. A recognition subject is associated and recorded with m first local feature quantities each comprising a one-dimensional to i-dimensional feature vector, and n second local feature quantities each comprising a one-dimensional to j-dimensional feature vector are generated with respect to n local regions respectively containing n features from within an image in a video. The present invention is characterized by then selecting the smaller dimensionality from among dimensionality i and dimensionality j, and when it has been determined that at least a predetermined fraction of the m first local feature quantities comprising feature vectors up to the selected dimensionality correspond to the n second local feature quantities comprising feature vectors up to the selected dimensionality, recognizing that the recognition subject is present in the image in the video and displaying information indicating the recognition subject superimposed on the image that is in the video and in which the recognition subject is present.