Abstract: A computer-based matchmaking method utilizing numerical representations of voice as well facial features to improve matchmaking capabilities, the voice features preferably including articulation quality measures, speed of speech measures, audio energy measures, fundamental frequency measures, and relative audio periods. Certain preferred embodiments include: plastic-surgery-unique anthropometric facial measures to enhance system effectiveness; use of both standard and non-standard facial points identified by Gabor kernel-based filtering; and adapting to user preferences by adjusting system parameters based on user responses to potential matches.

Abstract: Systems and methods to enable real-time and near real-time storyboarding on the World Wide Web in addition to a graphical user interface for video parsing and browsing the of the storyboard. Specifically, storyboarding can be accomplished on the World Wide Web by parsing an input video into representative or key frames. These frames then can be posted to a web document, or the like, for subsequent viewing by a user. This allows a video to be distilled down to the essential frames thus eliminating storage and bandwidth problems as well as eliminating the need for a user to view the entirety of the video. Furthermore, the graphical user interface allows a user to visually interact with an input video signal to determine the key or representative frames, or to retrieve video segments associated with already determined key frames.

Abstract: A system and a method for wavelet-based low bitrate video coding is provided. The system and method of this invention processes each frame of a video sequence based on its content. The discrete wavelet transform of each frame is taken separately. If the difference between the contents of a first frame and a second frame is above a threshold, then the wavelet transformed second frame is quantized and lossless encoded. If the difference is less than a threshold, then motion estimation is employed in wavelet domain. Then the difference between the wavelet transformed second frame and the motion compensated wavelet transformed second frame is quantized and lossless encoded. The quantization is applied by using dynamic adjustment. The quantization tables are optimized based on the coded frame characteristics. In addition to the coded frames, the lossless coded motion vectors are also transmitted to the decoder unit.

Abstract: A wavelet domain filtering technique is disclosed that removes or at least minimizes checkerboard-like noise artifacts that result from capturing a composite NTSC video signal. A Haar basis filter bank is used to obtain a two-level wavelet decomposition. Low-pass filtering is performed on the high-high (HH) and the high-low (HL) bands of the wavelet decomposition since the checkerboard-like noise artifact is primarily visible on the vertical and the diagonal edges of the captured composite NTSC video frame.

Abstract: Systems and methods to enable real-time and near real-time storyboarding on the World Wide Web in addition to a graphical user interface for video parsing and browsing the of the storyboard. Specifically, storyboarding can be accomplished on the World Wide Web by parsing an input video into representative or key frames. These frames then can be posted to a web document, or the like, for subsequent viewing by a user. This allows a video to be distilled down to the essential frames thus eliminating storage and bandwidth problems as well as eliminating the need for a user to view the entirety of the video. Furthermore, the graphical user interface allows a user to visually interact with an input video signal to determine the key or representative frames, or to retrieve video segments associated with already determined key frames.

Abstract: Systems and methods to enable real-time and near real-time storyboarding on the World Wide Web in addition to a graphical user interface for video parsing and browsing the of the storyboard. Specifically, storyboarding can be accomplished on the World Wide Web by parsing an input video into representative or key frames. These frames then can be posted to a web document, or the like, for subsequent viewing by a user. This allows a video to be distilled down to the essential frames thus eliminating storage and bandwidth problems as well as eliminating the need for a user to view the entirety of the video. Furthermore, the graphical user interface allows a user to visually interact with an input video signal to determine the key or representative frames, or to retrieve video segments associated with already determined key frames.

Abstract: The scanned image registration systems and methods according to this invention register sets of scanned subimages of an original document into a composite scanned image of the original document. The subimages are formed by scanning portions of the original document on a scanner having a scan area, or window or footprint, that is smaller than the size of the document. An appropriate set of affine parameters, or more generally, transformation parameters, is obtained for each subimage relative to a fixed coordinate system. The set of affine parameters for each subimage defines the rotational and translational deformation necessary to place that subimage into the fixed coordinate system. The fixed coordinate system is preferably defined by selecting one of the subimages as a base image. The other images are then warped into registration with the selected base subimage based on the determined affine parameters.

Abstract: Systems and methods for detecting robust fade and dissolve and video sequences. The systems and methods use a two step approach to detect both discontinuous cuts and gradual changes in a video sequence. Specifically, an input video signal is first divided into video segments based on the location of the discontinuous cut. A gradual change detector is then applied to the discontinuous cut segments to determine further cuts based on editing characteristics. By using this two part approach, the systems and methods of this invention can robustly detect scene breaks within a video.

Abstract: A system and a method for wavelet-based low bitrate video coding is provided. The system and method of this invention processes each frame of a video sequence based on its content. The discrete wavelet transform of each frame is taken separately. If the difference between the contents of a first frame and a second frame is above a threshold, then the wavelet transformed second frame is quantized and lossless encoded. If the difference is less than a threshold, then motion estimation is employed in wavelet domain. Then the difference between the wavelet transformed second frame and the motion compensated wavelet transformed second frame is quantized and lossless encoded. The quantization is applied by using dynamic adjustment. The quantization tables are optimized based on the coded frame characteristics. In addition to the coded frames, the lossless coded motion vectors are also transmitted to the decoder unit.

Abstract: A method and apparatus for insertion of a secondary digital image, such as a digital image of a photograph or the like, into a base digital image without requiring the base document image data to be decompressed for purposes of locating the appropriate paste location or to perform the actual electronic pasting operation. The JPEG or otherwise compressed base digital image is segmented into information areas and background areas without decompressing the base digital image so that each background area is identified as a potential paste location for the compressed secondary digital image. The segmentation operation is performed on the basis of the encoding “cost” of each block and the DC coefficient of the block. Without decompressing the base digital image, a select background area is identified therein which is sufficiently large to receive the compressed secondary digital image.

Abstract: A method and system for real time converting a dynamic video to a set of static image frames includes segmenting the video into a plurality of frames. Significant parts of the frames are selected to comprise interest points. An operator estimates a motion trajectory of the interest points for real time computing of a global motion. Upon detection of global motion, selected key frames are selected from the set of static frames to represent the dynamic video. Interest points are identified as areas of high gradient and are further minimized by limiting interest points by imposing a grid on image frame and limiting the interest points to one point per grid cell.

Abstract: A method for processing compressed digital data derived from an original image sequence, the data being organized as a set of image frames, each image frame comprising a set of blocks, each block including a string of bits corresponding to an area of the original image frame in the original image sequence. A cost function is derived as a number related to the amount of bits spent to encode a block, sets of blocks, an image frame, or sets of image frames. A segmentation technique is applied to the map with cost functions. Temporal segmentation is performed by analyzing cost functions associated with each image frame. In both cases auxiliary functions can be used to improve the segmentation quality. The segmented regions of a image frame or sets of image frames can be identified, replaced, printed, or processed in special manners.

Abstract: A system and a method for motion-compensated de-interlacing of interlaced video frames that generates high quality progressive video frames, keeps computational complexity low and requires the use of only a single image frame is provided. The system and method of this invention determine if global motion (camera motion) is present in the scene. If global motion is detected, it is estimated and compensated. The globally-compensated image is then analyzed to determine whether local motion is present. If local motion is detected, the image pixels affected by the local motion are interpolated using motion-adaptive techniques. If no local motion and no global motion is detected, the image pixels are interleaved.

Abstract: In a temporal sequence of digitized image frames of video signals, the spatial and temporal image gradients and the pixel-to-pixel motion vectors (dense motion vectors) are obtained between two consecutive image frames. A shape-adaptive triangular patch mesh model overlay is provided on the first image frame such that the location of node points of each patch is determined by the spatial image gradients of the first frame and the pixel-to-pixel motion vectors. A priority ranking of patches is established before determining the node point motion vectors. The node point motion vectors, representing the motion of each of the node points of the triangular mesh patches, are estimated by a linear least-squares solution to an affine transformation of the mesh overlay on the first frame into the second frame. Failure regions are identified and are revised in accordance with a data bit budget. All data are coded prior to transmission at a constant data bit rate by a sending unit to a receiving unit over a data link.