Morphological Operations (i.e., Local Neighborhood Operations) Patents (Class 382/308)
-
Patent number: 7570794Abstract: A method and system are provided for non-contact evaluation of a machined surface of a cast-metal part, including a vision-based porosity inspection station. A digital image of the machined surface is acquired, oriented and scaled to an XY coordinate system, filtered, and inverted. A second image is generated with known design surface features eliminated. Each pixel of the inverted digital image is XOR-compared with a corresponding pixel of the second image. Identified common surface features common to both images is analyzed statistically for conformance to a threshold. A defect is identified as any identified surface feature common to both images which exceeds the threshold. The system moves the part for further processing if a statistical analysis of defects indicates an acceptable component, and alternatively, removes the part from further processing if the analysis indicates a flawed component.Type: GrantFiled: September 2, 2005Date of Patent: August 4, 2009Assignee: GM Global Technology Operations, Inc.Inventors: Michael E. Swanger, John S. Agapiou, Robert J. Hogarth
-
Patent number: 7529397Abstract: The present invention discloses methods for automatically generating regions of seeding points for fiber tracking in diffusion tensor images. These methods are based on connected region grow. Seeding point selection criteria involving Fractional Anisotropy thresholding and Dominant Eigen Vector similarity are also disclosed.Type: GrantFiled: January 17, 2006Date of Patent: May 5, 2009Assignee: Siemens Medical Solutions USA, Inc.Inventors: Zhizhou Wang, Yuanhsi (Tony) Chen, Mariappan S. Nadar
-
Patent number: 7515764Abstract: An image processing apparatus which uses morphology is provided. A masked image is provided to a morphological processing section of the image processing apparatus. The morphological processing section calculates the opening gap of the masked image, calculates the minimum number N of iterations of dilations required for filling the opening gap and, after performing N dilations, executes N erosions to remove a mesh pattern. Then, an edge detecting section detects the edges of a wiring pattern in the image and a measuring section calculates the distance between the edges, which is the width of the wiring.Type: GrantFiled: April 25, 2005Date of Patent: April 7, 2009Assignee: Mitutoyo CorporationInventors: Naoki Mitsutani, Masaki Kurihara
-
Patent number: 7496231Abstract: Disclosed is a color interpolation method. The present invention decides a precise position of an edge with use of a G value in a unit pixel structure with a size of 3×3, thereby using different color interpolations according to the position of the edge. Also, the present invention provides an effect of emphasizing an edge by emphasizing a brightness and lowering colors when the edge is placed in the vertical center or the horizontal center of the unit pixel structure of 3×3 with use of a property that the edge has stronger brightness than the colors and prevents an incorrect color.Type: GrantFiled: March 28, 2005Date of Patent: February 24, 2009Assignee: MagnaChip Semiconductor, Ltd.Inventor: Byung-Geun Jung
-
Patent number: 7493340Abstract: An improved image retrieval process based on relevance feedback uses a hierarchical (per-feature) approach in comparing images. Multiple query vectors are generated for an initial image by extracting multiple low-level features from the initial image. When determining how closely a particular image in an image collection matches the initial image, a distance is calculated between the query vectors and corresponding low-level feature vectors extracted from the particular image. Once these individual distances are calculated, they are combined to generate an overall distance that represents how closely the two images match. According to other aspects, relevancy feedback received regarding previously retrieved images is used during the query vector generation and the distance determination to influence which images are subsequently retrieved.Type: GrantFiled: October 21, 2004Date of Patent: February 17, 2009Assignee: Microsoft CorporationInventor: Yong Rui
-
Patent number: 7486838Abstract: A noise reduction apparatus is disclosed. A noise amount estimating unit estimates a noise amount in a focused pixel. A smoothing unit smoothes the focused pixel. A control unit controls the smoothing unit on the basis of the noise amount and information on the focused pixel and neighboring pixels thereof.Type: GrantFiled: September 13, 2005Date of Patent: February 3, 2009Assignee: Olympus CorporationInventor: Yamato Kanda
-
Patent number: 7471835Abstract: The invention relates to a method and an apparatus for encoding images, more particularly to an encoding unit in conjunction with a library of pictorial entities and image qualifiers. The method and apparatus provide encoding an image by using a code factor table in conjunction with a set of element codes. The resulting image code allows the set pictorial elements of an image and their associated image qualifiers to be represented by a compact code uniquely representing a given configuration of pictorial elements. The use of the resulting image code facilitates the transmission and storage of images requiring only the code to be sent or stored. The invention further provides a computer readable medium comprising a program element that direct a computer to implement the encoding process.Type: GrantFiled: January 22, 2004Date of Patent: December 30, 2008Assignee: IQ Biometrix Corp.Inventor: Pierre Côté
-
Publication number: 20080181535Abstract: An imaging processing system adapted for use with a vehicle is provided in one aspect of the present invention. The system generally includes an image capturing device and an image processing device. The image capturing device is operable to capture an original image of a scene exterior to the vehicle. The captured original image is generally defined by a group of pixels. The image processing device is operable to receive the captured original image and morphologically process the captured original image to remove distortion from the captured original image to produce a final filtered image.Type: ApplicationFiled: January 29, 2007Publication date: July 31, 2008Applicant: Ford Global Technologies, LLCInventor: Reid Steiger
-
Patent number: 7382941Abstract: An apparatus to compress a dynamic range of an image, and a method of compressing the dynamic range. The apparatus includes a periphery value production unit to calculate periphery information about peripheral pixels on a polyhedron-by-polyhedron basis using summed area tables produced form an analog pixel stream of a previous frame of the image, multiply the periphery information by predetermined weight values, sum results of the multiplications, and output the sum as a periphery value; and a pixel value correction unit to correct a pixel value of a target pixel included in an analog pixel stream of a current frame using the periphery value; wherein the peripheral pixels are located around the target pixel and included in the previous frame, and a kernel distribution expressed in a kernel function, which is a distribution of weight values dependent on locations of pixels included in the image, is approximated to a sum of the polyhedrons.Type: GrantFiled: March 25, 2005Date of Patent: June 3, 2008Assignee: Samsung Electronics Co., Ltd.Inventor: Euihyeon Hwang
-
Patent number: 7359536Abstract: An automated method for evaluating the amount of residual protein levels following treatment of cellular specimens. Particular methods include the measurement of maternal neutrophil alkaline phosphatase after treatment with or without urea or heat, measurement of leukocyte acid phosphatase after treatment with or without tartrate, and measurement of leukocyte esterase after treatment with ?-naphthol butyrate with or without fluoride.Type: GrantFiled: December 5, 2003Date of Patent: April 15, 2008Assignee: Carl Zeiss MicroImaging AIS, Inc.Inventors: Presley Hays, Michal L. Peri, Douglas Harrington
-
Patent number: 7359542Abstract: A method and apparatus for accurately detecting the anomalous shadows occurring within an interimage image based on two or more images obtained of the same subject, wherein the artifacts occurring in the interimage image are reduced, is provided. A temporal subtraction image formed by an interimage processing means is subjected to a morphology process wherein the artifacts occurring in the interimage image are suppressed relative to the actual difference between the two images on which the temporal subtraction image is based. A detecting means detects the suspected anomalous shadows occurring within the temporal subtraction image that has been subjected to an artifact-suppressing morphology process.Type: GrantFiled: November 20, 2001Date of Patent: April 15, 2008Assignee: FUJIFILM CorporationInventor: Akira Oosawa
-
Patent number: 7359567Abstract: Image quality degrading components can be eliminated from a contour correction signal of high frequency region that is used for contour correction. A filtering section extracts a high frequency region signal from a signal inputted from a VLPF. A mask generating section generates a mask by masking image quality degrading components (e.g., ringing components) contained in the extracted signal. A gain factor generating section generates a gain factor that eliminates image quality degrading components on the basis of the mask. A multiplier multiplies the extracted signal by the gain factor, and outputs an adder a resultant signal (horizontal contour correction signal free from the image quality degrading components). Since the horizontal contour correction signal is generated by eliminating the image quality degrading components from the high frequency region signal, the occurrence of ringing and the like can be suppressed to ensure excellent image quality.Type: GrantFiled: January 16, 2004Date of Patent: April 15, 2008Assignee: Sony CorporationInventors: Shinichiro Gomi, Kazuhiko Ueda
-
Patent number: 7330609Abstract: A method of measuring a modulation transfer function (MTF) includes detecting the center of a line spread function (LSF) image in order to calculate an MTF. For this purpose, an enlarged image of a portion of an image containing the LSF image is created, and binary-coded based on a threshold. A morphological operation is performed on the binary-coded image. Coordinates representing points that define the contour of the resultant image are sampled, and used to work out coordinates representing the center of a circle through Hough transform. The coordinates representing the center are transformed into coordinates representing a point in an original image.Type: GrantFiled: November 4, 2004Date of Patent: February 12, 2008Assignee: GE Medical Systems Global Technology Company, LLCInventors: Xueli Wang, Xiongwei Yan, Wei Ding, Makoto Gohno
-
Patent number: 7321676Abstract: A diagnostic imaging apparatus generates a three-dimensional diagnostic image representation. The image representation is converted into an image representation of the patient's heart. A left lower posterior point of the heart image representation is selected as a first approximation of a left ventricle apex and a line of preselected orientation is drawn through the first approximation apex as a first approximation ventricle axis. The ventricle axis is redefined by generating short axis slices across the approximated ventricle axis, isolating a selected one of the ventricles, determining a centroid of each short axis slice of the selected ventricle, and fitting the axis to the apex approximation and the centroids. The apex location is redefined by looking for the lowermost short axis slice orthogonal to the redefined axis which intersects the ventricle volume and selecting the intersection point as the next approximation of the apex.Type: GrantFiled: June 2, 2004Date of Patent: January 22, 2008Assignee: Koninklijke Philips Electronics N.V.Inventors: Guy A. Lavi, Jonathan Lessick
-
Patent number: 7305089Abstract: The camera includes a sensor for sensing the photographer's iris image and registering the image in advance. The iris image is recorded in the image of a subject by a digital MCU at a timing different from that at which the image of the subject is captured. The recording timing is that at which the camera power supply is turned off, that at which a recording medium is ejected from the camera or that at which the iris image to be recorded is changed to the registered iris image of another photographer. The recording of the iris image is achieved by embedding it as a watermark or by appending it to metadata.Type: GrantFiled: June 13, 2003Date of Patent: December 4, 2007Assignee: Canon Kabushiki KaishaInventors: Goichi Morikawa, Go Tokura
-
Patent number: 7277600Abstract: Skew angle in a document image is estimated using operators known from mathematical morphology. Skew angle in a document image (A) is estimated by run-length smoothing the image and then producing a plurality of eroded run-length-smoothed images. The run-length-smoothed image (RLSA(A)) is eroded using a linear structuring element (k2L?) oriented at each of a plurality of different angles (?). The angle of the linear structuring element which produces an eroded image having the greatest surface area is designated as the skew angle. A plurality of run-length-smoothed images (RLSA?(A)) may be produced, each generated by smoothing the document image using a linear structuring element (k1L?) oriented at a respective different angle (?i). Then each run-length smoothed image (RLSA?(A)) is eroded using a linear structuring element oriented at the corresponding angle (?i).Type: GrantFiled: August 27, 2003Date of Patent: October 2, 2007Assignee: OCE Print Logic Technologies S.A.Inventor: Laurent Alain Najman
-
Patent number: 7269294Abstract: A foreground erosion method is used to meet thin (but unbroken) text requirements using linear YCC segmentation. The method uses a fixed value subtracted from a gray selector signal, thereby thinning/eroding the foreground. In cases where the pixel would be converted from foreground to background, this is only done if a neighborhood test verifies that the thinning won't result in broken lines. The foreground erosion method attempts to match a couple of templates wherein if a match is found, then the adjustment is performed.Type: GrantFiled: July 1, 2003Date of Patent: September 11, 2007Assignee: Xerox CorporationInventors: Donald J. Curry, Doron Kletter, Asghar Nafarieh
-
Publication number: 20070177825Abstract: An image processing method extracts line segment elements from grayscale captured images, so that line segments are extracted at high-speed without being influenced by contrast ratio, even if morphology processing is used. A selection processing select an area where continuous line segments possibly exist from the captured image and a morphology processing detect line segment elements in the selected area by scanning an operator. Line segments can be extracted in a plurality of directions at high-speed. Also by an extraction target area selection processing, an area of which contrast ratio is low, continuing from an area of which contrast ratio is high in the line segment growth direction is also extracted as one line segment.Type: ApplicationFiled: August 25, 2006Publication date: August 2, 2007Applicants: FUJITSU LIMITED, FUJITSU FRONTECH LIMITEDInventors: Tomoharu Suzuki, Shinichi Eguchi
-
Patent number: 7142732Abstract: A method of segmenting objects in an image is described. The method applies a Top Hat algorithm to the image then constructs inner and outer markers for application to the original image in a Watershed algorithm. The inner marker is constructed using binary erosion. The outer marker is constructed using binary dilation and perimeterisation. The method finds particular application for first level segmentation of a cell nucleus prior to detailed analysis.Type: GrantFiled: June 28, 2001Date of Patent: November 28, 2006Assignee: Co-Operative Research Centre for Sensor Signal and information ProcessingInventors: Pascal Bamford, Paul Jackway
-
Patent number: 7123783Abstract: An image classification system uses curvature-based multi-scale morphology to classify an image by its most distinguishing features. The image is recorded in digital form. Curvature features associated with the image are determined. A structuring element is modulated based on the curvature features. The shape of the structuring element is controlled by making it a function of both the scaling factor and the principal curvatures of the intensity surface of the face image. The structuring element modulated with the curvature features is superimposed on the image to determine a feature vector of the image using mathematical morphology. When this Curvature-based Multi-scale Morphology (CMM) technique is applied to face images, a high-dimensional feature vector is obtained. The dimensionality of this feature vector is reduced by using the PCA technique, and the low-dimensional feature vectors are analyzed using an Enhanced FLD Model (EFM) for superior classification performance.Type: GrantFiled: January 21, 2003Date of Patent: October 17, 2006Assignee: Arizona State UniversityInventors: Madhusudhana Gargesha, Sethuraman Panchanathan
-
Patent number: 7102793Abstract: A method of filtering an input image is provided. In a creating action, a boolean tone map is created based on the input image and an array of tone nodes. In a determining action, it is determined whether or not a target pixel is in a tone region by examining the target pixel and a neighboring region of pixels. If the target pixel is in a tone region, in a selecting action, a first base-filter is selected for the tone region. A method of resolution dependent filtering is also provided.Type: GrantFiled: April 30, 2003Date of Patent: September 5, 2006Assignee: Hewlett-Packard Development Company, L.P.Inventors: Je-Ho Lee, Jay S. Gondek
-
Patent number: 7091995Abstract: The present invention provides a method for morphing different geometric shapes while not using algebraic characteristics and overcoming inefficiency of Minkowski sum computation. The method for geometric shape morphing by using direction map so as to smoothly morph more than two different geometric shapes includes the steps of: a) extracting each direction map of the geometric shape; b) merging the direction maps; c) scaling the merged direction map by group; and d) generating a polygon by using an inverse function of a direction map.Type: GrantFiled: December 10, 2003Date of Patent: August 15, 2006Assignee: Electronics and Telecommunications Research InstituteInventors: Joo-Haeng Lee, Hyun Kim, Duk-Joo Son
-
Patent number: 7062100Abstract: In an image-data processing system, as would be found in a digital copier or scanner, a relatively quick calculation is performed to estimate a compression ratio or compression time resulting from applying a compression algorithm to an image data set. If the estimated compression ratio or compression time is determined to be unfavorable, the system is advised not to apply the compression algorithm. The method can also be used to select a type of compression algorithm, such as CCITT G4 or JBIG2, according to the requirements of the larger system.Type: GrantFiled: December 16, 2002Date of Patent: June 13, 2006Assignee: Xerox CorporationInventors: Fritz F. Ebner, Daniel Davies, Edward E. Ewer, Ramesh Nagarajan
-
Patent number: 7043066Abstract: A method, system and computer readable medium for computerized processing of chest images including obtaining a digital first image of a chest (S100); producing a second image which is a mirror image (S300) of the first image; performing image warping on one of the first and second images to produce a warped image (S400) which is registered to the other of the first and second images; and subtracting the warped image from the other image to generate a subtraction image (S600).Type: GrantFiled: November 5, 1999Date of Patent: May 9, 2006Assignee: Arch Development CorporationInventors: Kunio Doi, Qiang Li, Shigehiko Katsuragawa, Takayuki Ishida
-
Patent number: 7027660Abstract: 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: GrantFiled: July 5, 2002Date of Patent: April 11, 2006Assignee: Ecole Polytechnique Federale de Lausanne (EPFL)Inventors: Roger David Hersch, Bernard Wittwer, Edouard Forler, Patrick Emmel, Daniel Biemann, Daniel Gorostidi, Dominique Bongard
-
Patent number: 6993203Abstract: An original image is subjected to an opening processing and to a closing processing to obtain a blurred image by using an average value between the result of the opening processing and the result of the closing processing as a reference for correcting the brightness. The brightness of the original image is corrected by multiplying a difference between the blurred image and the original image, by a ratio of an upper limit value of brightness to a difference between the upper limit value of brightness and the blurred image. Then, the brightness of the original image is corrected based on the blurred image which enhances the contrast of a highly bright portion of a predetermined area or more while lowering the brightness of that portion. Contrast and brightness of the whole image can be adapted to the sensitivity of human eyes.Type: GrantFiled: July 29, 2002Date of Patent: January 31, 2006Assignee: Fujitsu LimitedInventors: Akio Ozawa, Kohei Murao
-
Patent number: 6978053Abstract: A system and method of adding hyperlinked information to a television broadcast. The broadcast material is analyzed and one or more regions within a frame are identified. Additional information can be associated with a region, and can be transmitted in encoded form, using timing information to identify the frame with which the information is associated. The system comprising a video source and an encoder that produces a transport stream in communication with the video source, an annotation source, a data packet stream generator that produces encoded annotation data packets in communication with the annotation source and the encoder, and a multiplexer system in communication with the encoder and the data packet stream generator. The encoder provides timestamp information to the data packet stream generator and the data packet stream generator synchronizes annotation data from the annotation source with a video signal from the video source in response to the timestamp information.Type: GrantFiled: October 26, 2000Date of Patent: December 20, 2005Assignee: Goldpocket Interactive, Inc.Inventors: Karen Sarachik, Jon Dakss, V. Michael Bove, Jr.
-
Patent number: 6970579Abstract: A system and method for detecting features in video from business meetings and video teleconferencing systems can use color, motion, morphological (shape) filtering and a set of heuristic rules to determine possible features in the scene. One embodiment includes obtaining a first video frame of images and a second video frame of images, performing a luminance conversion on the first video frame of images and the second video frame of images, performing a motion filter operation on the converted first and second frames of images, performing a chrominance normalization on the second video frame of images, performing a color filter operation on the normalized second video frame of images, and processing the first and second frames of video images after the motion filter and color filter operations.Type: GrantFiled: April 15, 2002Date of Patent: November 29, 2005Assignee: Sonic Foundry, Inc.Inventor: Susan M. Thornton
-
Patent number: 6959119Abstract: A method kit is provided for demonstrating the effects of a cosmetic product on a consumer's body, especially effects over a period of time. The method includes applying a cosmetic product to the body, capturing an image of the consumer, displaying the image on a monitor and digitally transforming the image to reflect the effect of using the selected cosmetic over the period of time. Among transformed attributes of the body are those of glow/color, sags/wrinkles, pores and combinations thereof. The original and transformed images are juxtaposed on a screen. Consumers are required to select between transformed and displayed images, preferably repetitively, until the consumer has chosen their most appealing transformation.Type: GrantFiled: May 4, 2001Date of Patent: October 25, 2005Assignee: Unilever Home & Personal Care USAInventors: Stacy Susan Hawkins, Jeremy James Andrew, Richard Iwao Murahata
-
Patent number: 6956669Abstract: An effects processor for an effects module. The effects processor comprises a RISC processor, a DSP for fast integer multiplication and a small memory. The processor uses VARK language and a lookup table of VARK scripts to apply a variety of effects to images stored outside the effects module. The effects processor includes a serial bus interface which communicates with the Serial Bus of a compact printer system comprising one or more further modules. The Serial Bus communicates power and data between the effects module and one or more of the further modules. Methods of compositing, convolving, warping and color substitution are described.Type: GrantFiled: May 23, 2000Date of Patent: October 18, 2005Assignee: Silverbrook Research Pty LTDInventors: Kia Silverbrook, Simon Robert Walmsley, Paul Lapstun
-
Patent number: 6952502Abstract: Data filtering apparatus comprising: an input for receiving a stream of data, each data item taking a range of at least two values ranging between a low value to a high value, a segmentation device for dividing the stream into segments, a segment midpoint definer for defining a midpoint of each segment, a segment orderer for ordering the segment in a first direction from low to high on a first side of the midpoint and in a second direction from low to high on a second side of the midpoint, an extremity filter unit for comparing the ordered data on either side of the midpoint to create a temporary output per segment, for each segment, each data item on either side of the midpoint being given an extremity filter value, the filter unit being operable to utilize the ordering to find the extremity value via a minimal number of comparisons, the extremity filter for initially comparing a single end of each segment, and being operable to alternate between ends per segment, the extremity filter being further operableType: GrantFiled: June 25, 2001Date of Patent: October 4, 2005Assignee: Technion Research & Development Foundation Ltd.Inventors: Joseph Gil, Ron Kimmel
-
Patent number: 6922201Abstract: A chronological age altering lenticular image is comprised of a first photograph (62) of an individual at a first age (64). A second photograph (66) of the individual at a second age (68) and a third photograph (70) of the individual at a third age (72) are included in the composite which comprise the lenticular image. The first, second, and third photographs show the individual at progressively older stages in the individuals life. In another embodiment the first, second, and third photographs show the individual at progressively younger stages in that individuals life.Type: GrantFiled: December 5, 2001Date of Patent: July 26, 2005Assignee: Eastman Kodak CompanyInventors: Nelson A. Blish, Jeffery R. Hawver, Timothy J. Tredwell
-
Patent number: 6901168Abstract: The object of the invention is a method of processing information contained in an image, including: a first processing (1-4), for defining an area of interest of the image (8), effecting an adaptive thresholding (1-8) of this area of interest in order to obtain a threshold image (10) of this area of interest, referred to as the first thresholded image, the segmentation (1-12) of the thresholded image, in order to obtain a first set of morphological layers (14-1, 14-2, 14-3, . . . ) of the thresholded image.Type: GrantFiled: May 6, 1999Date of Patent: May 31, 2005Assignee: France TelecomInventors: Joël Gardes, Rémy Mullot, Yves Lecourtier, Jean-Marc Ogier, Alain Lassaulzais
-
Patent number: 6879731Abstract: A system and process for generating High Dynamic Range (HDR) video is presented which involves first capturing a video image sequence while varying the exposure so as to alternate between frames having a shorter and longer exposure. The exposure for each frame is set prior to it being captured as a function of the pixel brightness distribution in preceding frames. Next, for each frame of the video, the corresponding pixels between the frame under consideration and both preceding and subsequent frames are identified. For each corresponding pixel set, at least one pixel is identified as representing a trustworthy pixel. The pixel color information associated with the trustworthy pixels is then employed to compute a radiance value for each pixel set to form a radiance map. A tone mapping procedure can then be performed to convert the radiance map into an 8-bit representation of the HDR frame.Type: GrantFiled: April 29, 2003Date of Patent: April 12, 2005Assignee: Microsoft CorporationInventors: Sing Bing Kang, Matthew T. Uyttendaele, Simon Winder, Richard Szeliski
-
Patent number: 6879720Abstract: A system and method of adding hyperlinked information to a television broadcast. The broadcast material is analyzed and one or more regions within a frame are identified. Additional information can be associated with a region, and can be transmitted in encoded form, using timing information to identify the frame with which the information is associated. The system comprising a video source and an encoder that produces a transport stream in communication with the video source, an annotation source, a data packet stream generator that produces encoded annotation data packets in communication with the annotation source and the encoder, and a multiplexer system in communication with the encoder and the data packet stream generator. The encoder provides timestamp information to the data packet stream generator and the data packet stream generator synchronizes annotation data from the annotation source with a video signal from the video source in response to the timestamp information.Type: GrantFiled: April 8, 2004Date of Patent: April 12, 2005Assignee: GoldPocket Interactive, Inc.Inventors: Karen Sarachik, Jon Dakss, V. Michael Bove, Jr., Josh Wachman
-
Patent number: 6879713Abstract: The developmental potential of a mammalian oocyte for successful implantation is evaluated by producing a plurality of intensity images of the oocyte using polarized light optics, and calculating a retardance image with a sensitivity of 3 nm or less. The presence, location and morphological characteristics of a meiotic spindle in the oocyte can then be determined based on the spindle structure in the retardance image, and the developmental potential of the oocyte can be evaluated.Type: GrantFiled: June 25, 2001Date of Patent: April 12, 2005Assignee: Women & Infants Hospital of Rhode IslandInventor: David L. Keefe
-
Patent number: 6834288Abstract: An image retrieval system for retrieving image similarities from a database is proposed. The image retrieval system uses a universal query mechanism (UQM) to locate statistically silent common features among sample query images from different feature sets. The UQM also adjusts the weight factor for each feature to meet a user's query demand.Type: GrantFiled: April 13, 2001Date of Patent: December 21, 2004Assignee: Industrial Technology Research InstituteInventors: Jiann-Jone Chen, Chen-Chin Chiang
-
Patent number: 6816627Abstract: A system capable of efficiently fusing image information from multiple sensors operating in different formats into a single composite image and simultaneously display all of the pertinent information of the original images as a single image.Type: GrantFiled: April 12, 2001Date of Patent: November 9, 2004Assignee: Lockheed Martin CorporationInventor: Norman Ockman
-
Patent number: 6813373Abstract: An imaging system and method enables 3-D direct segmentation from a series of spatially offset 2-D image slices in a volume scan. The algorithm first smoothes and preserves the interface edges of the image volume using Bottom-Hat gray scale morphological transform followed by 3-D segmentation using fast 3-D level sets by preserving topology constraints, for example, cortical thickness in a brain volume. The method inputs opposite polarity spheres (contracting and expanding spheres) which morph into shapes within the volume using a surface propagation technique. The speed of propagation is controlled by the likelihood statistical component derived under constraints. During the propagation polygonalization extracts the zero-level surface set. The field distribution is computed using the improved shortest distance method or polyline distance method. The morphing algorithm then morphs the input concentric spheres into interface surfaces such as WM-GM and GM-CSF with cortical constraint.Type: GrantFiled: April 3, 2001Date of Patent: November 2, 2004Assignee: Koninklijke Philips Electronics, N.V.Inventors: Jasjit S. Suri, Kecheng Liu, Laura M. Reden
-
Patent number: 6804375Abstract: 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.Type: GrantFiled: June 27, 2001Date of Patent: October 12, 2004Assignee: Kabushiki Kaisha ToshibaInventor: Hirofumi Muratani
-
Patent number: 6801661Abstract: A method for representing an image in terms of the shape properties of its identified segments of interest involves analyzing each segment of interest to automatically identify one or more of its perceptually significant components and then representing each perceptually significant component in terms of its shape properties, e.g., by means of Fourier descriptors. The image segment is then characterized as a composition of the shape properties of its perceptually significant components. By repeating the foregoing steps, the image is represented as a composition of its characterized segments. This technique can then be used to archive and retrieve images based on the shape properties of identified segments.Type: GrantFiled: February 15, 2001Date of Patent: October 5, 2004Assignee: Eastman Kodak CompanyInventors: George E. Sotak, Rajiv Mehrotra
-
Patent number: 6785409Abstract: 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.Type: GrantFiled: October 24, 2000Date of Patent: August 31, 2004Assignee: Koninklijke Philips Electronics, N.V.Inventor: Jasjit S. Suri
-
Patent number: 6771834Abstract: Briefly, in accordance with one embodiment of the invention, a method of segmenting an initial digital image includes the following. The initial digital image is processed to produce a first digital image with defined edges corresponding to the initial digital image and to produce a second digital image with at least two dominant contiguous regions corresponding to the initial digital image. Distinct non-overlapping regions of the first digital image formed by the defined edges are identified. The distinct non-overlapping regions of the first digital are combined based, at least in part, on a correspondence with the at least two dominant contiguous regions in the second digital image. Based, at least in part, on the remaining regions after combining the distinct non-overlapping regions of the first digital image, the initial digital image is segmented.Type: GrantFiled: July 2, 1999Date of Patent: August 3, 2004Assignee: Intel CorporationInventors: Fernando C. M. Martins, Rajeeb Hazra
-
Patent number: 6757442Abstract: A technique is disclosed for enhancing discrete pixel images. Image enhancement is first performed by separating structural regions from non-structural regions and performing separate smoothing and sharpening functions on the two regions. Non-uniform equalization is then performed to reduce differences between high and low intensity values, while maintaining the overall appearance of light and dark regions of the reconstructed image. Contrast enhancement is then performed on the equalized values to bring out details by enhancing local contrast.Type: GrantFiled: November 22, 2000Date of Patent: June 29, 2004Assignee: GE Medical Systems Global Technology Company, LLCInventor: Gopal B. Avinash
-
Patent number: 6741255Abstract: Apparatus, methods, systems and computer program products are disclosed that optimize the application of deferred image operations on a tiled source image. The invention dynamically creates a data structure (such as a directed acyclic graph (DAG)) representing the operations performed on various instances of one or more images to create a final image. The invention analyzes the data structure to determine which source image tiles are needed when the actual image data comprising the final image is required. Each of these tiles are then separately processed by all of the deferred operations to create the final image data. This approach reduces the number of times a tile is read into memory for processing and improves the performance of deferred image operations on a tiled source image.Type: GrantFiled: August 14, 1997Date of Patent: May 25, 2004Assignee: Sun Microsystems, Inc.Inventors: John L. Furlani, Alexandra R. Ohlson, Richard T. Inman
-
Publication number: 20040096124Abstract: An image apparatus and method is disclosed for extending the dynamic range of an image sensor. A first linear pixel circuit produces a first pixel output signal based on charge integration by a first photo-conversion device over a first integration period. A second linear pixel circuit produces a second pixel output signal based on charge integration by a second photo-conversion device over a second integration period, where the second integration period is shorter than the first integration period. A sample-and-hold circuit captures signals representing the first and second pixel output signals.Type: ApplicationFiled: November 15, 2002Publication date: May 20, 2004Inventor: Junichi Nakamura
-
Patent number: 6731414Abstract: For preventing the occurrence of disjunction among a plurality of images in the magnification index in the main scanning direction, image data delivered from an external device through an input image data connector are converted by a P/S converter into serial data from parallel data, and then stored into a memory by a write controller. When the image data are cached, a read controller starts reading the image data. At the same time, a computation means starts counting time based on information set at a setting means by an external central processing unit. As soon as it reaches the initial insert interval, the read controller suspends reading of image data out of the memory to insert virtual data pixel. In the same procedure, the read controller inserts virtual data pixel at each of the insert intervals counted by the computation means.Type: GrantFiled: March 1, 2000Date of Patent: May 4, 2004Assignee: Matsushita Electric Industrial Co., Ltd.Inventor: Akira Ito
-
Patent number: 6728427Abstract: The present invention provides the method of extracting temporal and spatial combination markers including the steps of: (1) simplifying inputted current image frames, quantizing the simplified images, and then extracting spatial markers from the simplified and quantized image frames using spatial information; (2) extracting temporal markers from inputted current image frames and previous image frames using temporal information, and (3) combining the extracted spatial marker and the extracted temporal marker to extract temporal and spatial markers.Type: GrantFiled: August 2, 2000Date of Patent: April 27, 2004Assignee: Electronics and Telecommunications Research InstituteInventors: Jae Gark Choi, Mun Churl Kim, Myoung Ho Lee, Chie Teuk Ahn
-
Patent number: 6728004Abstract: A method for processing digital images to be displayed, stored, or printed, to eliminate blooming and other artifacts. The system utilizes morphological processes to isolate and modify image structures susceptible to marking process artifacts and then combines the modified image structures with the input image to produce a printable image that may be rendered on a given printer.Type: GrantFiled: May 30, 2001Date of Patent: April 27, 2004Assignee: Xerox CorporationInventors: Robert P. Loce, Michael Branciforte, Ying-wei Lin
-
Publication number: 20040057080Abstract: Selective edge softening and selective edge dithering is introduced into an image representation to improve local control where halo problems are expected. Selective areas of dilation are isolated and separately dithered or halftoned, the result of which is then swapped back into or substituted for the stored original image. In this manner misregistration and color plane-to-plane interactions can be compensated for in plural image forming station architecture systems. The same technique is also valuable in monochrome systems as an aid to overcoming edge displacement and slow toner problems when the selective edge softening is selectively applied to edges which are in particular perpendicular to the fast scan direction.Type: ApplicationFiled: October 27, 2003Publication date: March 25, 2004Applicant: Xerox CorporationInventors: Robert P. Loce, Clara Cuciurean-Zapan