摘要 |
The present invention relates to an apparatus for making an image into a text using image analysis and, more specifically, to an apparatus for making an image into a text using image analysis, which analyzes at least one object included in image data inputted from an image acquisition device and provides motion information and property information of the object in the form of a sentence or word arrangement according to patterns. According to the present invention, the apparatus for making an image into a text using image analysis includes: an analysis unit which receives, from an image acquisition device, an input of image data consisting of a plurality of frames, extracts area information of at least one object represented in each frame of the image data, and analyzes, from the extracted area information of the object, property information of the object together with motion information of the object which changes in each time zone; a generation unit which classifies a plurality of patterns according to the motion information of the object and the property information of the object analyzed by the analysis unit and selectively generates one among a plurality of events to correspond to the patterns; a database unit which stores a group of words which correspond to the motion information of the object and the property information of the object analyzed by the analysis unit; and a creation unit which searches words, which correspond to the motion information and property information of the object which becomes a subject of the event generated by the generation unit, from the group of words stored in the database unit, and combines the searched words according to the property information, the motion information and the patterns to create a sentence or word arrangement. |