Abstract: Image data identifying multiple pixels in an image is received, and a multi-resolution hierarchical structure is created from the image data. Further, output values are calculated for the pixels in the image using a wavelet-based retinex algorithm by propagating pixel values computed at lower resolution levels of the multi-resolution hierarchy to higher levels of the multi-resolution hierarchy and refining the propagated pixel values at the higher resolution levels.

Abstract: An occurrence description scheme that describes an occurrence of a semantic entity in multimedia content is encoded into a content description for the content. The occurrence description scheme is extracted from the content description and used by an application to search, filter or browse the content when a full structural or semantic description of the content is not required.

Abstract: A method and apparatus of training a neural network. The method and apparatus include creating a model for a desired function as a multi-dimensional function, determining if the created model fits a simple finite geometry model, and generating a Radon transform to fit the simple finite geometry model. The desired function is fed through the Radon transform to generate weights. A multilayer perceptron of the neural network is trained using the weights.

Abstract: A method and apparatus for organizing data pertaining to audiovisual content are described. According to one embodiment, an exemplary method for organizing data pertaining to audiovisual content includes defining at least one descriptive list for a descriptive portion of the data pertaining to audiovisual content, defining at least one accessing list for an accessing portion of the data pertaining to audiovisual content, and generating a matrix that connects the accessing list to the descriptive list.

Abstract: A method and an apparatus of designing a set of wavelet basis trained to fit a particular problem. The method and apparatus include constructing a neural network of arbitrary complexity using a discrete and finite Radon transform, feeding an input wavelet prototype through the neural network and its backpropagation to produce an output, and modifying the input wavelet prototype using the output.

Abstract: A system and method for allowing synchronized execution of a set of commands is provided. A first system contains a content description tree that may be dynamically updated by a set of commands from a second system. In the set of commands, commands may be executed in parallel or in sequence. If the group of commands are tagged to be executed in parallel, parallel execution of commands implies that there are no dependencies between the execution of the commands. As the result, the decoder will have more flexibility to schedule the execution of these commands. If the group of commands are tagged to be executed sequentially, then the order of execution matters. Therefore, in order to synchronize the execution of the group of commands in a set, a parallel or sequential tag is included identifying whether this group of commands should be executed in parallel or in sequence.

Abstract: A method and apparatus of reconstructing data from higher moment data. The method and apparatus include performing a finite Radon transform, generating an average function to allow inversion of transform in one step and correlating the transform output at each point. A resultant set of duplications is calculated using the correlation process to generate a new average function. Partial backprojections of the Radon transform are summed at each point, and the new average function for each point is subtracted from the sum of the partial backprojections at that point.

Abstract: The present invention provides improved techniques for spatial representation of data and browsing based on similarity. For example, improved techniques for spatial representation of image data and browsing the image data based on the similarities (or dissimilarities) of the images are provided. In one embodiment, a hierarchical MultiDimensional Scaling (MDS) database for a set of images is provided, which allows for computationally efficient querying and updating of an image database. In one embodiment, techniques for modifying an MDS database for images are provided to allow for more intuitive browsing (or searching) of the images.

Abstract: A method and apparatus for organizing data pertaining to audiovisual content are described. According to one embodiment, an exemplary method for organizing data pertaining to audiovisual content includes defining at least one descriptive list for a descriptive portion of the data pertaining to audiovisual content, defining at least one accessing list for an accessing portion of the data pertaining to audiovisual content, and generating a matrix that connects the accessing list to the descriptive list.

Abstract: A method and apparatus for determining quality of a description are described. According to one embodiment, an exemplary method for determining quality of a description includes posing a classification task concerning at least one audiovisual object to a descriptive method that is used to create the description, generating a set of probabilities from a result of the classification task, and measuring an entropy of the result using the set of probabilities.

Abstract: The invention relates to a brush comprising a plurality of bristles and each bristle comprises a plurality of fibers. A palette of virtual paint is provided for the brush to contact at least one paint. The brush contacts the tablet and applies paint to the surface of the tablet or image that is created.

Abstract: A method and an apparatus of compressing data. The method and apparatus include constructing a neural network having a specific geometry using a finite and discrete Radon transform. The data is then fed through the neural network to produce a transformed data stream. The transformed data stream is thresholded. A fixed input signal is fed back through the neural network to generate a decoding calculation of an average value. The thresholded data stream is entropy encoded.

Abstract: A method, apparatus and article of manufacture for updating a new node in a multidimensional scaling (MDS) database having an existing node. The new node is compared to the existing node to obtain a disparity value. A distance value is calculated between the new node and the existing node, a sum of differences value is calculated for the disparity value and the distance value, and a sum of squares value is calculated for the disparity value and the distance value. The position of the new node is modified according to the sum of differences value and the sum of squares value.