Abstract: A barcode detection device is disclosed which captures an image; examines the image in a plurality of grids; obtains a profile of the image along the sides of the grids; determines the number of transitions in the profile of each side; compares the number of transitions in each adjacent pair of sides with the number of transitions in the opposing adjacent pair of sides, respectively, and identifies a potential barcode data bearing grid when the count of transitions on one pair of adjacent sides matches the count of transitions on the opposing pair of adjacent sides.
Type:
Grant
Filed:
October 30, 2002
Date of Patent:
May 23, 2006
Assignee:
SICK Auto Ident, Inc.
Inventors:
Long Xiang Bian, Walter P. Sweeney, Jr.
Abstract: An image data processing device allowing both of user side and provider side to obtain benefits, leading to market expansion, is disclosed. When an image content is copied, an additional watermark is inserted into the copied image content. When an additional watermark is detected from input image content data, a further copy of the image content is prohibited.
Abstract: A method and digital camera are disclosed for capturing a complete set of image data for a three-dimensional target object by capturing image data from multiple images from different perspectives of the target object. The camera captures an image of the object from an initial perspective. Based on image data retrieved from the image, discontinuous edges of the object are identified for the initial perspective. The camera continues capturing image data for the object by capturing images from different perspectives, until complete image data is obtained. As each image is captured, the camera attempts to resolve discontinuous edges identified in any of the images. If all of the discontinuous edges cannot be resolved, then another image of the target object is captured from another perspective. When all of the discontinuous edges are resolved, the camera indicates that complete image data has been obtained, using an indicator.
Type:
Grant
Filed:
October 21, 2002
Date of Patent:
May 23, 2006
Assignee:
Hewlett-Packard Development Company, L.P.
Abstract: The regions of interest of images of both breasts of a patient are defined as regions of the image of minimal surface area and containing views of the breasts. These regions of interest are aligned for simultaneous display of the images. The display now allows simple and direct comparison of the images of both breasts, notably allowing immediate comparison of structural disorganizations within the two breasts.
Type:
Grant
Filed:
December 19, 2001
Date of Patent:
May 16, 2006
Assignee:
GE Medical Systems Global Technology Company, LLC
Inventors:
Elisabeth Soubelet, Sylvie Bothorel, Serge Louis Muller
Abstract: A technique for extracting a meaningful text block from a document where a table, an itemized list, a multiple column, etc., are arbitrarily laid out. A document is input which is laid out using blanks or the like, then a symbol is acquired which is associated with a spatial coordinate of the document. Consecutive characters of the same type are extracted from the symbol to generate a token and a space. A stream is generated from consecutive spaces in the column direction, while a text block is generated from streams and tokens. A link is generated between the text blocks to form a document graph. Validity of a connection (link) between the text blocks in the document graph is evaluated using a language model, then the text blocks are merged if the connection is valid.
Type:
Grant
Filed:
June 25, 2001
Date of Patent:
May 16, 2006
Assignee:
International Business Machines Corporation
Abstract: User attribute data, such as a retinal scan, is encoded into a media signal as it is captured in media capture device, such as a camera, video recorder, etc. The user attribute data uniquely associates the creator with the content he or she creates. By steganographically embedding the user attribute data into the content at or near the time of capture, the creator of the content can be authenticated at a subsequent time. In addition, alteration of the content can be detected.
Abstract: The resolution of an image is converted effectively using a simple process which needs a small amount of calculation. Local energy is determined from the differences between pixel values of N pixels lying at diagonal locations in an upper and lower rows. When the local energy is greater than a threshold value, a diagonal line given by two pixels having the smallest difference is employed as an edge direction. An image is interpolated between the two pixels in the edge direction by employing the mean value of the two pixel values of those two pixels. Thereafter, it is determined whether consistency is achieved between the interpolated image and the upper and lower pixels. If consistency is not achieved, linear interpolation is performed as in the case where the energy is lower than the threshold value.
Abstract: Methods and systems for document image decoding incorporating a Stack algorithm improve document image decoding. The application of the Stack algorithm is iterated to improve decoding. A provisional weight is determined for a partial path to reduce template matching. In addition, semantically equivalent hypotheses are identified to reduce redundant hypotheses.
Type:
Grant
Filed:
August 9, 2002
Date of Patent:
May 2, 2006
Assignee:
Xerox Corporation
Inventors:
Daniel H. Greene, Justin K Romberg, Tze-Lei Poo, Ashok C. Popat
Abstract: A biometric facial image verification system capable of recognizing human users which includes a smart-card having stored thereon encoded first human facial images, a video camera and video digitizer embedded within said smart-card for acquiring data representative of a second human facial image. A computer-based device with a docking station capable of receiving said smart-card and software resident within said computer-based device for facial recognition, which includes Principal Component Analysis, Neural Networks, or another equivalent algorithm for comparing said first human facial images with said second human facial image and producing an output signal therefrom for use in verifying the identity of said human users. The apparatus can further include software for fingerprint and speech recognition.
Type:
Grant
Filed:
April 7, 2000
Date of Patent:
May 2, 2006
Inventors:
David M. Tumey, Tianning Xu, Craig M. Arndt
Abstract: A method for processing segmentation tags to generate a block level tag representative of a group of segmentation tags includes identifying a block of the segmentation tags; compiling a block statistic from a plurality of segmentation tags within the block; determining a most predominant segmentation tag and a second most predominant segmentation tag in the plurality of segmentation tags; and generating a block level tag for the block based on the most predominant segmentation tag, the second most predominant segmentation tag and the block statistic.
Abstract: A data management system and method for processing, storing, and viewing the extremely large imagery data that is rapidly produced by a linear-array-based microscope slide scanner is provided. The system receives, processes, and stores imagery data produced by the linear-array-based microscope slide scanner at approximately 3 GB per minute. The data are received as a series of overlapping image stripes and combined into a seamless and contiguous baseline image. The baseline image is logically mapped into a plurality of regions that are individually addressed to facilitate viewing and manipulation of the baseline image. The data management system enables imagery data compression while scanning and capturing new image stripes. This advantageously eliminates the overhead associated with storing uncompressed image stripes. The image compression also creates intermediate level images, thereby organizing the baseline image into a variable level pyramid structure referred to as a virtual slide.
Type:
Grant
Filed:
February 21, 2003
Date of Patent:
April 25, 2006
Assignee:
Aperio Technologies, Inc.
Inventors:
Greg J. Crandall, Ole Eichhorn, Allen H. Olson, Dirk G. Soenksen
Abstract: The ability of the visual system to detect contrast in an image is a function of the frequency of the contrasting pattern and the distortion of the image. The visual system is more sensitive to contrasting patterns of lower frequency. When the image is significantly distorted, the visual system is even more sensitive to lower frequencies than higher frequencies. An image encoder employs lossy data compression processes producing a distorted reconstructed image. A method of quantizing image data including the step of varying the magnitude of a quantization step as a function of the distortion of an image is disclosed for further visually optimizing image quantization. Another method utilizes distortion adaptive weighting to vary the limit of code block truncation during embedded bitstream coding to visually optimize image compression by increasing relative lossiness of compression at higher frequencies.
Abstract: Systems and methods for deriving a cardiac cycle signal by selecting images of a portion of a cardiovascular system include receiving a plurality of images from a scanner that have been recorded over a period of time. The images represent one or more locations along the extent of the cardiovascular system. The images are then selected based on common criteria determined from the plurality of images and without reference to an external signal. The common criteria comprises changes in the size of a cross section of the aorta, changes in the volume of the heart, changes in the area of a cross section of the heart. In addition, the criteria can include the mean pixel difference between adjacent images.
Type:
Grant
Filed:
September 26, 2000
Date of Patent:
April 18, 2006
Assignee:
Vital Images, Inc.
Inventors:
Vincent J. Argiro, Marek Brejl, Renee Maheshwari Rashid, Todd Johnson, Milan Brejl
Abstract: A method and apparatus for specifying quantization based upon the human visual system is described. In one embodiment, the method comprises specifying scalar quantization for application to one or more bit planes of luminance information in image data using a human visual system (HVS) weighting and quantizing bit planes of the luminance information in the image data based on specified scalar quantization.
Type:
Grant
Filed:
October 4, 2004
Date of Patent:
April 18, 2006
Assignee:
Ricoh Co., Ltd.
Inventors:
Edward L. Schwartz, Michael J. Gormish, Martin Boliek, Kok Gi Wu
Abstract: A method and system for identifying multiple questionnaire pages. An embodiment of a method includes receiving a set of coordinates from a capture device, the set of coordinates indicating shapes made on multiple pages of a questionnaire without the use of a graphical user interface, and mapping each shape to a questionnaire answer on a different page. The method enables a processor to accurately and quickly determine which answers were entered on each questionnaire page attached to the capture device, without relying on the user to do so. Exemplary applications include a field survey and inventory.
Abstract: The present invention relates to an image search method capable of expressing one color feature related to a spatial color feature of a still image based on a multilevel image grid and similarity-based searching images using the thusly expressed multilevel image grid. In the present invention, hierarchical grids of different levels are generated with respect to one feature for thereby obtaining a data structure in which each cell corresponding to the grid is expressed based on a reliability on a region representative color and the region representative color, so that it is possible to fast and accurately search images with respect to a user's content-based query based on a cell matching of the same level as two image grids and different levels or a color local matching of the grid match.
Type:
Grant
Filed:
January 31, 2000
Date of Patent:
April 11, 2006
Assignee:
LG Electronics Inc.
Inventors:
Hyeon Jun Kim, Sung Bae Jun, Jin Soo Lee
Abstract: A method for locating face landmarks (e.g., eyes, nose, etc.) from an image is provided. The method comprises preprocessing an input image for alignment; comparing the aligned input image with a reference image located with face landmarks; calculating distances of pixels and pixel rows of the images; finding a correspondence between pixel rows of the reference image and that of the input image; and using the correspondence and the face landmarks of the reference image to find face landmarks of the aligned input image.
Type:
Grant
Filed:
October 31, 2002
Date of Patent:
April 11, 2006
Assignee:
Industrial Technology Research Institute
Abstract: A method of generating an image incorporating a microstructure includes the steps of obtaining an original image, generating a microstructure, and rendering a region or the whole said original image with said microstructure. The operation of generating the microstructure includes an automatic synthesis of microstructure elements from original microstructure shapes.
Type:
Grant
Filed:
July 5, 2002
Date of Patent:
April 11, 2006
Assignee:
Ecole Polytechnique Federale de Lausanne (EPFL)
Inventors:
Roger David Hersch, Bernard Wittwer, Edouard Forler, Patrick Emmel, Daniel Biemann, Daniel Gorostidi, Dominique Bongard
Abstract: Calibrating the dose response of an image acquisition device comprises comparing a first self-calibration curve to a second self-calibration curve to determine the relationship between the curves; modifying an acquired image based on the at least one difference; and applying an initial calibration to the acquired image, whereby the dose response of the image acquisition device is calibrated.
Type:
Grant
Filed:
January 20, 2005
Date of Patent:
April 4, 2006
Assignee:
Radiological Imaging Technology, Inc.
Inventors:
Daniel M. Ritt, Matthew L. Whitaker, Arthur J. Olch
Abstract: A method for blurring in signal processing, for example, in digital film processing, is performed with digital artifacts. The digital artifacts are derived, such as by scanning, and include a noisy artifact and a less noisy artifact. The artifacts are subdivided into a plurality of windows, with each window being subdivided into a plurality of squares. The squares of the noisy artifact and of the less noisy artifact have spatial correspondence, as do the respective windows.