Abstract: A sound recognition device includes a storage for storing a comment that is input while the user listening to sounds emitted as multimedia data being played. The sound recognition device further includes an extractor for extracting a word that appears in a set of sentences that contains the stored comment, and candidate words that contain co-occurrences of the word in the set of sentences. Furthermore, the sound recognition device includes a sound recognizer for recognizing sounds emitted as the multimedia data being played, based on the extracted candidate words.

Abstract: Since an image projected from a projector has basically not high quality due to degradation of brightness and mixture of outside light, the image shot by the conventional technology includes the projected image with basically not high quality. In order to solve the above deficiency, in an aspect of the present invention provides an image system, where live performance is provided to audience by image projection on the screen, and the image to be shot does not include the projected image with low quality. For example, the image system can later synthesize a high-quality image having the same content as the projected image.

Abstract: In the conventional technology for edge detection by normalizing brightness value of a target pixel C for edge determination and brightness of peripheral blocks of the target pixel C, an effect on an image due to a camera lens has not been considered. Specifically, the camera lens has a circular shape and the photographed image is basically formed by circularly collected light. In the conventional technology, however, it has been difficult to carry out high-precision edge detection due to rectangular shape of the peripheral blocks. In order to solve the above deficiency, in an aspect of the present invention provides an edge detection apparatus having a function of weighting the pixel values in the ‘peripheral area’ to be compared with the target pixel C for edge determination, such that the peripheral area has the circular shape.

Abstract: A video of a field of view of a patron in a venue is made different from a video delivered to a viewer of a user terminal. A video from an imaging device that images the video is received as an input, and the video includes all or a part of an image display device arranged near a performer and the performer. A mask process is performed on all or a part of a portion of the video in which the image display device is imaged. The video that has been subjected to the mask process is transmitted via a network.

Abstract: A keyword related to a user's interest is acquired. A keyword acquiring device including a tree storage unit that stores a keyword tree obtained by performing hierarchization according to the number of appearances and relevance in advance using a keyword associated with content as a node records a keyword associated with content previously selected by a user as a log, extracts a plurality of keywords based on a predetermined condition from a log corresponding to a certain user recorded in the log, extracts a partial tree including the extracted keywords from the keyword tree, and acquires a keyword in a node having no other lower node as a keyword related to the user's interest.