Kabushiki Kaisha Toshiba

Hisashi Aoki

Toshimitsu Kaneko

Kazunori Imoto

Makoto Hirohata

Koji Yamamoto

Osamu Hori

Osamu Yamaguchi

Yoshihiro Ohmori

Tatsuya Uehara

Kenichi Tabe

Shunsuke Takayama

In an example signal clustering apparatus, a feature of a signal is divided into segments. A first feature vector of each segment is calculated, the first feature vector having has a plurality of elements corresponding to each reference model. A value of an element attenuates when a feature of the segment shifts from a center of a distribution of the reference model corresponding to the element. A similarity between two reference models is calculated. A second feature vector of each segment is calculated, the second feature vector having a plurality of elements corresponding to each reference model. A value of an element is a weighted sum and segments of second feature vectors of which the plurality of elements are similar values are clustered to one class.

Signal clustering apparatus

A video editing apparatusincludes a registering unitconfigured to register a key candidate having a feature vector of a sound signal which is determined to be registered on the basis of a co-occurrence score to a managing unitas a search key, and a cutting out unitconfigured to obtain an integration score in each of the blocks from the degree of similarity of the registered search key in each of the blocks and cut out a group of blocks exceeding an integration threshold value from among the integration scores as one video scene.

Video editing apparatus

A video processing apparatus calculates displayed time of two input segments having a telop area in a video on the basis of a time displayed area, determines whether or not the two input segments are a series of scene segments on the basis of the two displayed times, and outputs the two input segments determined as the series of scene segments as an output segment.

Video processing apparatus and video processing method

When groups of coordinates of face areas respectively contained in mutually different frames are within a predetermined error range, a face attribute assigning unit assigns mutually the same face attribute value to each of the face areas. In the case where a difference in the feature amounts between the frames is within a predetermined error range, a similar shot detecting unit detects that the shots from which the frames have respectively been extracted are similar shots to each of which mutually the same shot attribute value is assigned. In the case where it is judged that face areas that respectively appear in the frames contained in the similar shots and to which mutually different face attribute values have respectively been assigned represent the face of mutually the same person, the face attribute re-assigning unit assigns mutually the same face attribute value to each of the face areas.

Apparatus, computer program product, and method for processing pictures

A signal processing unit includes a feature quantity extracting unit, a segmentalizing unit, a clustering unit, an existence probability function deriving unit, an existence probability function similarity calculating unit, a cluster integrating unit and a cluster information output unit. The signal processing unit classifies the signal feature quantity which characterizes the content signal segmentalized into segments according to the similarity with respect to each other, obtains functions which indicate the existence probabilities for clusters of classified segments, and integrates the clusters whose obtained functions are at the high level of similarity.

Signal processing apparatus and method thereof

A moving picture processor includes a similarity calculator which calculates a similarity between shots, which refer to temporal parts of a moving picture, into which the moving picture is divided at a point where a content of the moving picture changes over, a similar shot specifying unit which specifies similar shots based on the similarity, and a grouping unit which makes groups each including the similar shots. The moving picture processor also includes a lead group selector which selects a lead group from the groups. The lead group includes a lead shot to be a head of a metashot. The moving picture processor also includes a lead shot selector which selects the lead shot from shots included in the lead group, and a metashot generator which generates the metashot including the lead shot selected at the head.

Moving picture processor, method, and computer program product to generate metashots

A system which allows significant camera breaks to be automatically detected among a large number of camera breaks and which is suitable in retrieving or playing a digital video is realized. Using a detected result recorded in an analysis result recording unit, a camera break analyzing unit compares the camera breaks among different digital videos. Thereby, the camera break analyzing unit detects camera breaks in which similar frames are detected, like frames used in common among a plurality of digital video of the same category. Such camera breaks are detected as the significant camera breaks among the large number of camera breaks and are used as indexes for retrieving or playing the digital video.

Video processing system and video processing method

A video information processing apparatus includes an input device which inputs video, a memory device which stores identification information corresponding to the blinking pattern of a blinking light source, a blinking light decoder which converts the blinking pattern of the light source blinking in the video information input by the input device into corresponding identification information on the basis of the identification information stored in the memory device, and an output device which outputs together with the input video the identification information converted by the blinking light decoder.

Video information processing apparatus and transmitter for transmitting information to the same

The object of the present invention is to provide a moving picture processing apparatus capable of preventing the viewer from watching the already watched pictures repeatedly. The moving picture processing apparatus of the present invention records the feature amounts of the already watched pictures in a database every moment and judges whether or not the pictures the viewer is now watching have already been displayed. When the current pictures are what have already been displayed, the apparatus carries out the process of stopping the video output until the time set by the user has been reached. When a list of small screens appears to show pictures, the apparatus carries out the process of displaying only dissimilar pictures on the screen.

Growing community of inventors

Kanagawa, Japan

Hisashi Aoki