Apparatus and method for generating visual annotation based on visual language

The present invention relates to an apparatus and method for automatically generating an image annotation for extremely large image-based visual language (Visual language). Image annotation automatic creation of a visual language-based device according to one aspect of the invention and a video input for receiving an input image, the image analysis unit for extracting feature information of an image input unit receiving an input video, the feature information addition image analysis extract used by using a similar image, and similar to the search for text information including the search sub-picture and text information search part searches for the input image includes image parts of tin constituting the image annotation configuration for the input image.