Abstract: The present invention relates to a technique for optimizing off-line facial feature tracking. Facial features in a sequence of image frames are automatically tracked while a visual indication is presented of the plurality of tracking node locations on the respective image frames. The sequence of image frames may be manually paused at a particular image frame in the sequence of image frames if the visual indication of the tracking node locations indicates that at least one location of a tracking node for a respective facial feature is not adequately tracking the respective facial feature. The location of the tracking node may be reinitialized by manually placing the tracking node location at a position on the particular image frame in the monitor window that corresponds to the respective facial feature. Automatic tracking of the facial feature may be continued based on the reinitialized tracking node location.

Abstract: A device is provided to support and position a limb extremity in a desired steady position to enable acquisition of morphological data from the underside and the upper portion of the limb extremity in a substantially non-weight-bearing attitude. The device comprises a stretchable envelope, made of a thin elastomeric membrane, and a support provided with adjustable positioning members such as hooks, pegs or clips comprising a proximal end and a distal end. The envelope is provided with laterally extending positioning member engaging portions disposed on opposite sides along the longitudinal axis of said envelope. Said positioning member engaging portions receive the distal end of said adjustable positioning members and thereby enable adjustable support and positioning of the envelope and, in turn, of the limb extremity inserted therein.

Abstract: Systems and method for organizing information relating to the design of polymer probe array chips including oligonucleotide array chips. A database model is provided which organizes information interrelating probes on a chip, genomic items investigated by the chip, and sequence information relating to the design of the chip. The model is readily translatable into database languages such as SQL. The database model scales to permit storage of information about large numbers of chips having complex designs.

Abstract: Preferred data compression and decompression processes (500, 600) of this invention speed transmission of a color XGA image (502). A first compression step employs an RGB-to-YCrCb color conversion compression process (504), and a second step employs an Lempel-Ziv-Oberhumer (“LZO”) compression process (506) for generating compressed image data for transmission through a wireless transmission medium. A preferred data decompression process receives the compressed image data from the LZO compression process. A first decompression step employs an LZO decompression process (602), and a second decompression step employs a YCrCb-to-RGB color conversion decompression process (604) for generating decompressed data suitable for rendering an image (606) that is substantially the same as the original XGA image.

Abstract: A point of sale terminal includes an input device, for reading information to be stored as part of a financial transaction, and a storage device in which data derived from the information is stored, with the amount of data stored being determined by the financial value of the transaction. The terminal may include a document scanner providing an image of a check or of another form of identification associated with a check, and a digitizing tablet, which provides an indication of movement of a pen or stylus to form a signature. The terminal may also include optical character recognition, which is used to obtain a name and address from the check, which is also stored according to the value of the check.

Abstract: Video image data is received in the form of a sequence of images representative of a subject performing one or more predetermined tasks within a new environment (FIG. 3 element 31). A plurality of silhouettes is generated from the video image data and combined to provide a motion portrait (FIG. 6). Motion characteristics are then calculated based on the motion portrait and may be compared with normal or previous motion characteristics as part of diagnostic analysis (38).

Abstract: Methods, apparatus, and computer readable medium for compressing connected component objects (300) of bi-level images. The compression apparatus (204) can take various forms including apparatus for coding a stroke of an object (300) or for coding the entirety of the object (300), including plural strokes. The compression apparatus (204) typically includes a referencing module (205) for identifying at least one reference node (310), a coding module (206) for successively coding pixel runs (311-314) such that at least one run (311) is coded relative to the reference node (310) and other runs (312-314) are coded relative to previously coded runs, and a closing module (207) for terminating the process. Certain forms of the apparatus operate in a horizontal or a vertical mode only, never operate in horizontal mode during two consecutive coding operations, code each run using two code-words, and/or utilize modified Huffman coding techniques.

Abstract: Electronic watermarks in digital documents can be detected, even if the content of the digital documents has been subjected to distortion or other attempts to hide or destroy the watermarks. A method involves inputting the distorted image and comparison information, the comparison information including at least one of the original image or information used for embedding the electronic watermark; dividing a domain of the original image into a plurality of patches, based on the comparison information; inputting affine parameters of a predetermined patch from among the patches in the original image; extracting a patch candidate from the distorted image; using a predetermined electronic watermark detection method, judging whether the patch candidate in the distorted image adequately correlates with a neighboring patch in the original image; when the judging indicates an adequate correlation, outputting a part of the electronic watermark.

Abstract: An image processing apparatus and method for deriving a digital watermark embedded in an image is provided which has a recognizing unit for recognizing a predetermined characteristic area in the image and a deriving unit for extracting the digital watermark from the image data in the recognized characteristic area.

Abstract: The present invention relates to a method and an apparatus capable of severing or damaging unwanted plants without using herbicides. The present invention relates in particular to an apparatus and a method for differentiating between different types of plants to allow identification of, and thus selective elimination or treatment of, individual plants. According to the present invention, the positioning of and the output power of at least one light generating means is controlled on the basis of information from an image recognition system which is capable of differentiating beween different plants.

Abstract: A method of detecting a block-based watermark is provided. The method detects the location of the watermark within a frame of content data regardless of whether the watermark has been shifted or resized.

Abstract: A method and apparatus for searching, browsing and summarizing moving image data using the fidelity of a tree-structured moving image hierarchy, which can partition or divide the moving image data into predetermined units, extract a key frame or representative frame from each of the partitioned or divided units, create a tree-structured key frame hierarchy on the basis of the extracted key frames, store a fidelity value of each of the key frames, which is a sub-tree information representative degree of each key frame, at an edge between adjacent ones of the key frames and effectively and efficiently search, browse and summarize the moving image data using the stored fidelity values. Therefore, a query image or video clip desired by a user can more rapidly and accurately be searched for.

Abstract: By automatically compensating for unwanted lighting effects caused by varying ambient light sources, digital still images and video are made to appear more naturally realistic. A set of correction factors based upon an ascertained ambient lighting conditions, such as color temperature, provides for selectively color correcting only those pixels requiring correction. In this way, only those portions of a digital image having excessive color due to ambient light conditions are improved without affecting those portions of the digital image not requiring correction.

Abstract: An image positional relation apparatus is provided, in which coordinate data of a real targed photographed by a CCD camera and coordinate data of a virtual target logically calculated from the predetermined position of the real target are transmitted to a superimpose circuit, and the real target and the virtual target are superimposed to be displayed on a monitor screen. A user operates a controller so that the real target coincides with the virtual target. An amount of such operation is transmitted to the superimpose circuit as a correction amount, and the positional relation between the real target and the virtual target, i.e., the positional relation between the real image and the virtual image can be properly corrected.

Abstract: To provide an electronic watermark method and system for which the detection reliability of embedded information does not depend on the strength of signals that are measured in frames. To achieve the above object, information is prepared for embedding as a bit stream, the sign of the bit stream being changed in accordance with a sign inversion cycle, and the bit stream being embedded in a frame. As for detection of information, values obtained through observation of frames are accumulated, and the accumulated values are compared with threshold values that are varied in accordance with the accumulated values obtained by observation. The comparison results are then employed to detect the embedded information.

Abstract: A method of digital imaging includes receiving image data and fitting a curve to boundaries within the image data. The curve is fit to the boundaries within the image data by extracting a region of interest from the image data and computing a signed distance transform in a narrow band within the region of interest. Finite difference equations including various variables are solved to determine a rate at which the distance transform changes. The distance transform is then diffused at that rate. The technique is based on region-based diffusion propagation, pixel classification, and mathematical morphology. The method is implemented to run in the narrow band of the region of interest specified by the user and the computations are implemented using a fast marching method in the narrow band. While idealized for distinguishing segments of white matter, gray matter, and cerebral spinal fluid in the brain, the algorithm can applied to find contours in any digital image.

Abstract: Systems and methods for non-intrusive analysis and display of internal features of wooden objects are provided. In embodiments of the system, a log is passed through a CT scanner in one continuous motion. One or more x-ray sources revolve around the log generating x-ray beams that traverse contiguous cross-sections of the log. An array of x-ray detectors detects x-rays that traverse the log for variations in the attenuation of rays. The detected attenuation is converted into spiral scan data that corresponds to projections in different contiguous cross-sections traversed by the x-rays. An image processor reconstructs spiral scan data into two dimensional cross-sectional images of the log by processing and formatting scan data using a planar reconstruction technique. The system renders three-dimensional views based on two-dimensional images.

Abstract: In a situation where a data portion is considered as of higher importance in the course of preparation of original data, the designer is enabled to set the electronic watermark in a position that is judged appropriate by the designer. There are provided input means for setting and entering information to be added as the electronic watermark, area data preparation means for setting and preparing the area data of the electronic watermark, first display/reproduction means for displaying or reproducing the digital data in which the electronic watermark is to be applied, electronic watermark addition means for adding the electronic watermark to the digital data, and second display/reproduction means for displaying or reproducing the digital data to which the electronic watermark is added, thereby setting the electronic watermark in a specified area in the digital data and satisfactorily preventing the infringement of the copyright by tampering of the work.

Abstract: Colored images are divided into color planes and watermarks are inserted into the individual color planes. One or more watermarks can be inserted into one or more of the color planes. In order to print a color image the image is divided into color planes corresponding to the colors of ink used for printing. A separate plate is used to print each color. The different plates must be precisely aligned. Any misalignment will cause blurring in the image and may make it difficult or impossible to read a watermark in the image. Misalignment of the plates can cause the watermark data in one color plane to, in effect, cancel out the watermark data in a different color plane. With the present invention a watermark is inserted into a selected color plane only, thus there is no cancellation due to misalignment of color plates. The watermark detection and reading can be done after the image is divided into color planes.

Abstract: In an image recognition apparatus, a left camera and a right camera are provided so as to produce a parallax. A road surface indication recognizing section recognizes road surface indications contained in a left input image that is supplied from the left camera. An edge detecting section detects remaining edges other than the edges of the recognized road surface indications among all the edges in the left input image. A matching section extracts a reference pattern in the left input image that includes a detected edge, and conducts matching between the reference pattern and a right input image that is supplied from the right camera using a pattern matching method. Based on each matching result with the reference pattern, an object recognizing section recognizes an object in the visual fields and determines a distance from the recognized object to the image recognition apparatus.