Abstract: A method and apparatus are provided for segmenting and summarizing a music video (507) in a multimedia stream (505) using content analysis. A music video (507) is segmented in a multimedia stream (505) by evaluating a plurality of content features that are related to the multimedia stream. The plurality of content features includes at least two of a face presence feature; a videotext presence feature; a color histogram feature; an audio feature, a camera cut feature; and an analysis of key words obtained from a transcript of the at least one music video. The plurality of content features are processed using a pattern recognition engine (1000), such as a Bayesian Belief Network, or one or more video segmentation rules (1115) to identify the music video (507) in the multimedia stream (505). A chorus is detected in at least one music video (507) using a transcript (T) of the music video (507) based upon a repetition of words in the transcript.

Abstract: Advertisers want to deliver their message in a relatively short period of time. This leads to the product name, company name and other identifying features being repeated frequently during a commercial broadcast. Transcript information can be used to detect commercials by detecting frequently occurring words in the commercials. This can also be used to identify an individual commercial from other commercials. Once the individual commercials have been identified, the transcript information corresponding to each commercial can be stored in a database to identify the commercial in subsequent broadcasts, or to provide a search mechanism for searching a particular commercial in the database.

Abstract: A system facilitates and enhances review of one or more multimedia input streams that includes some combination of video, audio and text information, generating a multimedia summary, thereby enabling a user to better browse and/or decide on viewing the multimedia input streams in their entirety. The multimedia summary is constructed automatically, based in part on system specifications, user specifications and network and device constraints. In a particular application of the invention, the input multimedia streams represent news broadcasts (e.g., television news program, video vault footage). In such a particular application, the invention can enable the user to automatically receive a summary of the news stream in accordance with previously provided user preferences and in accordance with prevailing network and user device constraints.

Abstract: A system and method is disclosed for indexing and summarizing music videos. A music video summary controller in a video playback device receives a multimedia data stream that contains a plurality of music videos. The music video summary controller (1) segments and identifies the music videos, and (2) creates a music video summary file for each music video. The music video summary file contains information such as title of the song and the name of the artist. The music video summary file also contains an identifying audio segment and video segment of the song. A user can access a list of the music video summary files and select which music video to play on the video playback device by selecting its corresponding music video summary file.

Abstract: A method for providing personalized news to a consumer is provided that includes receiving news from a plurality of external sources. A subset of the received news is identified based on a consumer profile for the consumer. The identified news is stored. The stored news is prioritized. At least a portion of the prioritized news is provided to the consumer.

Abstract: A method for providing name-face/voice-role association includes determining whether a closed captioned text accompanies a video sequence, providing one of text recognition and speech to text conversion to the video sequence to generate a role-name versus actor-name list from the video sequence, extracting face boxes from the video sequence and generating face models, searching a predetermined portion of text for an entry on the role-name versus actor-name list, searching video frames for face models/voice models that correspond to the text searched by using a time code so that the video frames correspond to portions of the text where role-names are detected, assigning an equal level of certainty for each of the face models found, using lip reading to eliminate face models found that pronounce a role-name corresponding to said entry on the role-name versus actor-name list, scanning a remaining portion of text provided and updating a level of certainty for said each of the face models previously found.

Abstract: A system and method for delivering relevant information to recipients in a timely manner. Information from a plurality of sources is received through interface devices that permit a central processor to evaluate each information stream in light of the dynamic profiles that are stored in a subscriber database. A plurality of location sensors track and report the location of the various recipients. The processor determines the content that will be provided to the recipient and the delivery mode to be used for delivering the selected information to the subscriber.

Abstract: A method of and system for detecting a cartoon in a video stream are provided. The system comprises a storage device for storing the encoded signal and a processor for processing low parameter information extracted from the encoded video signal. The information is extracted based on the predetermined characteristics of a typical cartoon. At least one value is computed based on the low parameter information and it is compared to the predetermined values for natural video. Based on the comparison the determination is made whether the video sequence contains a cartoon.

Abstract: A video signal is processed to generate one or more signatures associated with a broadcast program to be recorded by a recording device. The signatures are then processed to determine an actual start time and end time of the desired broadcast program, such that the program can be properly recorded despite delays or other changes in a pre-scheduled broadcast time of the program. One or more of the extracted signatures may be based at least in part on, e.g., a keyframe similarity measure, a histogram, one or more detected commercials, a transcript, a program logo or other detected object, detected text, and a sign-on or sign-off of the desired program. Other types of signatures can also be used.

Abstract: A content-based classification system is provided that detects the presence of object images within a frame and determines the path, or trajectory, of each object image through multiple frames of a video segment. In a preferred embodiment, face objects and text objects are used for identifying distinguishing object trajectories. A combination of face, text, and other trajectory information is used in a preferred embodiment of this invention to classify each segment of a video sequence. In one embodiment, a hierarchical information structure is utilized to enhance the classification process. At the upper, video, information layer, the parameters used for the classification process include, for example, the number of object trajectories of each type within the segment, an average duration for each object type trajectory, and so on. At the lowest, model, information layer, the parameters include, for example, the type, color, and size of the object image corresponding to each object trajectory.

Abstract: For use in a video recorder, there is disclosed a system and method for determining whether an incoming video program has been previously recorded by the video recorder. The system comprises a transcript processor that is capable of obtaining a transcript of the incoming video program from a number of different sources of text. The transcript processor is capable of assembling the transcript from closed caption text of the video program. The transcript processor compares the transcript of the incoming video program with transcripts of video programs that have been previously recorded by the video recorder in order to determine whether the incoming video program has been previously recorded by the video recorder. The incoming video program is not recorded a second time if it has been previously recorded.

Abstract: The present invention provides a method of detecting segment boundaries for a series of successive frames in a video sequence. The method includes the steps of acquiring color information from each frame, determining a color histogram for each frame, and applying a boundary detection technique utilizing the color histograms. Finally, the method includes segmenting the frames of the video sequence into uniform color segments. In addition, a system is provided for detecting segment boundaries for a series of successive frames in a video sequence. The system includes means for acquiring color information from each frame, means for determining a color histogram for each frame, and means for applying a boundary detection technique utilizing the color histograms. Finally, the system includes means for segmenting the frames of the video sequence into uniform color segments.

Abstract: An image processing device and method for classifying symbols, such as text, in a video stream employs a back propagation neural network (BPNN) whose feature space is derived from size, translation, and rotation invariant shape-dependent features. Various example feature spaces are discussed such as regular and invariant moments and an angle histogram derived from a Delaunay triangulation of a thinned, thresholded, symbol. Such feature spaces provide a good match to BPNN as a classifier because of the poor resolution of characters in video streams.

Abstract: System and method for recommending commercials are disclosed. Commercials from video signals are identified and extracted. Transcript information about the identified commercials are learned and extracted. Each commercials are then classified into different categories according to their transcript information. User preferences to the commercials are determined. The commercials with the user preferences are then used to build or train a decision tree in order to select commercials to recommend to the user. The selected commercials are then recommended using a personal channel.

Abstract: A system and method for detecting commercials from other programs in a stored content. The system comprises an image detection module that detects and extracts faces in a specific time window. The extracted faces are matched against the detected faces in the subsequent time window. If none of the faces match, a flag is set, indicating a beginning of a commercial portion. A sound or speech analysis module verifies the beginning of the commercial portion by analyzing the sound signatures in the same time windows used for detecting faces.

Abstract: The present invention provides a method, system and program product for generating a content-based table of contents for a program. Specifically, under the present invention the genre of a program having sequences is determined. Once the genre has been determined, each sequence is assigned a classification. The classifications are assigned based on video content, audio content and textual content within the sequences. Based on the genre and the classifications, keyframe(s) are selected from the sequences for use in a content-based table of contents.

Abstract: A method for operating a neural network, and a program and apparatus that operate in accordance with the method. The method comprises the steps of applying data indicative of predetermined content, derived from an electronic signal including a representation of the predetermined content, to an input of at least one neural network, to cause the at least one network to generate at least one output indicative of either a detection or a non-detection of the predetermined content. Each neural network has an architecture specified by at least one corresponding parameter. The method also comprises a step of evolving the at least one parameter to modify the architecture of the at least one neural network, based on the at least one output, to increase an accuracy at which that at least one neural network detects the predetermined content indicated by the data.

Abstract: A system and method is disclosed for indexing and summarizing music videos. A music video summary controller in a video playback device receives a multimedia data stream that contains a plurality of music videos. The music video summary controller (1) segments and identifies the music videos, and (2) creates a music video summary file for each music video. The music video summary file contains information such as title of the song and the name of the artist. The music video summary file also contains an identifying audio segment and video segment of the song. A user can access a list of the music video summary files and select which music video to play on the video playback device by selecting its corresponding music video summary file.

Abstract: A content maintenance system uses a time-dependent precipitation function for iteratively augmenting or removing content over time, after an initial demonstration of user interest. A plurality of parallel precipitation processes can be launched simultaneously in response to different facets of a user expression of interest. Precipitation is dependent on highlighting or extracting segment descriptors from content of interest to the user. Then segments are filtered, rated, annotated and/or prioritized from that content. The remaining segments are matched against stored search structures. When the segments match, they are precipitated out for storage and can generate new search structures.

Abstract: An image processing device and method for classifying symbols relies on a connected-component technique for isolating symbol regions. The device and method form connected components from an image derived by the application of an edge detection filter. The formation of connected components from this filtered image defines the edges of character shapes. As a result, the number of pixels that must be connected to define each connected component is substantially reduced and the speed of processing thereby increased. The application of the method is discussed primarily with respect to text in a video stream.