Based On A Local Average, Mean, Or Median Patents (Class 382/272)
  • Patent number: 11809789
    Abstract: A method for implementing a component design model includes defining a component design specification, defining at least one variation mode parameter of a component manufacturing process, constructing a parametric model relating the at least one variation mode parameter to the component design specification, determining an expected component output based on the parametric model and comparing the expected component output to at least one as-manufactured component, and defining the parametric model as accurate in response to the expected output component matching the at least one as-manufactured component within a predefined degree of accuracy.
    Type: Grant
    Filed: November 6, 2019
    Date of Patent: November 7, 2023
    Assignee: RTX CORPORATION
    Inventors: Hoyt Y. Chang, David A. Burdette, Joshua D. Winn
  • Patent number: 11810374
    Abstract: In implementations of recognizing text in images, text recognition systems are trained using noisy images that have nuisance factors applied, and corresponding clean images (e.g., without nuisance factors). Clean images serve as supervision at both feature and pixel levels, so that text recognition systems are trained to be feature invariant (e.g., by requiring features extracted from a noisy image to match features extracted from a clean image), and feature complete (e.g., by requiring that features extracted from a noisy image be sufficient to generate a clean image). Accordingly, text recognition systems generalize to text not included in training images, and are robust to nuisance factors. Furthermore, since clean images are provided as supervision at feature and pixel levels, training requires fewer training images than text recognition systems that are not trained with a supervisory clean image, thus saving time and resources.
    Type: Grant
    Filed: April 26, 2021
    Date of Patent: November 7, 2023
    Assignee: Adobe Inc.
    Inventors: Zhaowen Wang, Hailin Jin, Yang Liu
  • Patent number: 11783623
    Abstract: A synthesizing apparatus comprises: an input part that inputs a plurality of feature point sets that are respectively extracted by a plurality of methods from an input image having a curved stripes pattern formed by ridges; and a synthesizing part that synthesizes the plurality of feature point sets by executing a logical operation on the plurality of feature point sets. The synthesizing part can execute a logical OR operation on the plurality of feature point sets. The synthesizing part can also execute a logical AND operation on the plurality of feature point sets.
    Type: Grant
    Filed: October 29, 2021
    Date of Patent: October 10, 2023
    Assignee: NEC CORPORATION
    Inventors: Hiroaki Toyama, Mamoru Inoue
  • Patent number: 11467128
    Abstract: A defect detection method and apparatus detecting a defect in an object. The method comprises: obtaining ultrasound scan data derived from an ultrasound scan of the object under consideration, the ultrasound scan data being in the form of a set of echo amplitude values representing the amplitude of echoes received from the object during ultrasound scanning at certain spatial and temporal points; processing the ultrasound scan data to remove echo amplitude values received after a predetermined threshold time; generating at least one image from the processed ultrasound scan data; subjecting each generated image to an automated defect recognition process to determine whether there is a defect in the portion of the object represented by the image; issuing a notification indicating whether or not a defect has been found; and, if a defect has been found, storing the result of the automated defect recognition process in a defect database.
    Type: Grant
    Filed: June 28, 2019
    Date of Patent: October 11, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Eduarda Mendes Rodrigues, Serban Georgescu
  • Patent number: 11330145
    Abstract: A device for removing a noise artifact from a document receives a scan of the document, where the document contains a noise artifact at least partially obstructing a portion of the document. The device generates an image of the document, and extracts a first set of features from the image. The device identifies noise artifact features from the first set of features, and generates a second set of features by removing the noise artifact features. The device generates a test clean image of the document based on the second set of features. The device determines whether a portion of the test clean image that previously displayed the noise artifact corresponds to a counterpart portion of the training clean image. If it is determined that the portion of the test clean image corresponds to the counterpart portion of the training clean image, the device outputs the test clean image.
    Type: Grant
    Filed: June 10, 2021
    Date of Patent: May 10, 2022
    Assignee: Bank of America Corporation
    Inventors: MadhuSudhanan Krishnamoorthy, Ramaswamy M
  • Patent number: 11188733
    Abstract: A synthesizing apparatus comprises: an input part that inputs a plurality of feature point sets that are respectively extracted by a plurality of methods from an input image having a curved stripes pattern formed by ridges; and a synthesizing part that synthesizes the plurality of feature point sets by executing a logical operation on the plurality of feature point sets. The synthesizing part can execute a logical OR operation on the plurality of feature point sets. The synthesizing part can also execute a logical AND operation on the plurality of feature point sets.
    Type: Grant
    Filed: October 20, 2017
    Date of Patent: November 30, 2021
    Assignee: NEC CORPORATION
    Inventors: Hiroaki Toyama, Mamoru Inoue
  • Patent number: 10573266
    Abstract: A display panel driving apparatus and method are provided. The display panel driving apparatus includes a timing control circuit, a memory, a compensation circuit and a data driving circuit. The memory provides at least one coupling-capacitance information between a current pixel and at least one adjacent pixel in a display panel. By using the coupling-capacitance information, the compensation circuit compensates the current pixel data to obtain the compensated pixel data for compensating the voltage offset of the current pixel caused by the coupling voltage of the adjacent pixel. The data driving circuit drives the current pixel according to the compensated pixel data.
    Type: Grant
    Filed: August 8, 2017
    Date of Patent: February 25, 2020
    Assignee: HIMAX TECHNOLOGIES LIMITED
    Inventors: Yih-Long Tseng, Ming-Cheng Chiu
  • Patent number: 9928417
    Abstract: A first image data, binarized with a first threshold, represent a first image corresponding to a first portion of a specific image. A second image data, binarized with a second threshold different from the first threshold, represent a second image corresponding to a second portion of the specific image. A first area, which is extracted from the first image, includes pixels with a first color. The first color corresponding to a color of an outline of a hole image in the specific image. A second area, which is extracted from the second image, includes pixels with the first color. The first area and the second area are determined as a specific area corresponding to the hole image.
    Type: Grant
    Filed: March 21, 2016
    Date of Patent: March 27, 2018
    Assignee: Brother Kogyo Kabushiki Kaisha
    Inventors: Toshiki Motoyama, Tomohiko Hasegawa, Akidi Yoshida
  • Patent number: 9619689
    Abstract: A biometric scanner having an electric field device and a method of using that scanner are disclosed. The electric field device (a) has no electric field generator or an electric field generator that is prevented from providing an electric field to a biometric object, such as a finger, and (b) has an electric field sensor array comprised of a plurality of electric field sensors. Capacitance readings from the sensor array are used to generate values that are attributed to locations corresponding to the sensors.
    Type: Grant
    Filed: February 6, 2013
    Date of Patent: April 11, 2017
    Assignee: QUALCOMM Incorporated
    Inventors: John K. Schneider, Jack C. Kitchens
  • Patent number: 9405953
    Abstract: A biometric scanner having an electric field device and a method of using that scanner are disclosed. The electric field device (a) has no electric field generator or an electric field generator that is prevented from providing an electric field to a biometric object, such as a finger, and (b) has an electric field sensor array comprised of a plurality of electric field sensors. Capacitance readings from the sensor array are used to generate values that are attributed to locations corresponding to the sensors.
    Type: Grant
    Filed: February 6, 2013
    Date of Patent: August 2, 2016
    Assignee: QUALCOMM Incorporated
    Inventors: John K. Schneider, Jack C. Kitchens
  • Patent number: 9330325
    Abstract: An apparatus for processing a fingerprint image, the apparatus includes a noise information estimation unit configured to estimate information for a noise removal from at least two or more images recognized for a first section before a point of time when a fingerprint contact is initiated. The apparatus includes a fingerprint image acquiring unit configured to correct at least one image recognized for a predetermined time period after the completion of the fingerprint contact using the estimated information to acquire the fingerprint image.
    Type: Grant
    Filed: July 1, 2013
    Date of Patent: May 3, 2016
    Assignee: SUPREMA INC.
    Inventors: Hochul Shin, BoGun Park, Kideok Lee, Jinwook Yi, Bong Seop Song, Jae Won Lee
  • Patent number: 9041834
    Abstract: Disclosed are apparatus and methods for denoising a video stream of a camera. A current frame of the video stream and a temporally adjacent frame of the video stream that has been previously spatially and temporally denoised are obtained. The current frame is first spatially denoised, while preserving edges in such current frame to generate a plurality of spatially denoised pixels for the current frame. A particular pixel of the current frame is then both spatially and temporally denoised based on a weighted averaging of the particular pixel's associated spatially denoised pixel from the current frame and a plurality of pixels from the temporally adjacent frame that have already been spatially and temporally denoised.
    Type: Grant
    Filed: September 19, 2012
    Date of Patent: May 26, 2015
    Assignee: ZiiLabs Inc., Ltd.
    Inventor: Aaron DeBattista
  • Patent number: 9014444
    Abstract: Certain aspects of an apparatus and method for method and apparatus for automatic HER2 scoring of tissue samples may include for determining a cancer diagnosis score comprising identifying one or more nuclei in a slide image of a tissue sample, determine one or more membrane strengths in the slide image surrounding each of the one or more nuclei, classifying one or more cells, each corresponding to the one or more nuclei, in a class among a plurality of classes according to the one or more membrane strengths and determining a cancer diagnosis score based on a percentage of cells classified in each of the plurality of classes.
    Type: Grant
    Filed: October 24, 2012
    Date of Patent: April 21, 2015
    Assignee: Sony Corporation
    Inventors: Ming-Chang Liu, Ximin Zhang
  • Patent number: 8988552
    Abstract: Image data may be color graded, distributed and viewed on target displays. Mappings that preserve mid-range points and mid-range contrast may be applied to view the image data for color grading and to prepare the image data for display on a target display. The image data may be expanded to exploit the dynamic range of the target display without affecting mid-tone values.
    Type: Grant
    Filed: September 25, 2012
    Date of Patent: March 24, 2015
    Assignee: Dolby Laboratories Licensing Corporation
    Inventor: Robin Atkins
  • Patent number: 8989514
    Abstract: A method is provided that includes identifying a plurality of data sets, each data set is associated with a distribution model and each data set is associated with an image having a first noise level. The method includes partitioning the data sets into a plurality of groups and generating a best representative estimate for each group, the estimate is associated with a second noise level that is less than the first noise level. The method further includes annotating each group and receiving an input data set. The method includes assigning the input data set to a group and annotating the input data set according to that group's annotation.
    Type: Grant
    Filed: February 3, 2012
    Date of Patent: March 24, 2015
    Assignee: Voxeleron LLC
    Inventors: Daniel Russakoff, Jonathan Oakley
  • Patent number: 8976257
    Abstract: An automatic process for calibrating the optical image exposure value to compensate for changes in machine vision systems to maintain optimal exposure of captured images and adjust for the different characteristics among cameras components, such as imaging sensor sensitivity, LED strength, external lighting, reflective functions of any background material, different external lighting conditions, possible changes or updates of the systems over the years, such as LED changes, and even the aging of camera sensor and LEDs over time. A series of images of a target are captured with a predetermined sequence of exposure values, the saturation exposure percentage of a region of interest is calculated in each of the images, and the saturation exposure percentages are compared to determine the exposure value that has a saturation exposure percentage that varies the least from the saturation exposure value of the preceding and following exposure values.
    Type: Grant
    Filed: July 31, 2012
    Date of Patent: March 10, 2015
    Assignee: Jadak, LLC
    Inventors: Mo Chen, Chun Jia
  • Patent number: 8948542
    Abstract: An image processing apparatus for processing image data by a plurality of pipeline-connected processing modules is provided. The apparatus includes a first pipeline processing unit configured to include a plurality of processing modules including a processing module which processes image data for every first size; and a second pipeline processing unit configured to be branched from the first pipeline processing unit and include a plurality of processing modules including a processing module which processes image data for every second size different from the first size. The second pipeline processing unit includes, at a start, a change unit configured to acquire partial image data of the first size from the first pipeline processing unit and change the partial image data of the first size into partial image data of the second size.
    Type: Grant
    Filed: June 3, 2011
    Date of Patent: February 3, 2015
    Assignee: Canon Kabushiki Kaisha
    Inventors: Michiaki Takasaka, Hisashi Ishikawa
  • Patent number: 8929678
    Abstract: A method is provided for automatic contour filter positioning for medical X-ray imaging in an X-ray apparatus comprising a collimator and at least one movable contour filter actuated by a motor based positioning subsystem, wherein a digital image in a frame of rows and columns of pixels is rendered for processing and obtaining control data for applying a contour filter. The method comprises identifying exposure of subareas, preparing for filter positioning, and defining filter position.
    Type: Grant
    Filed: August 31, 2012
    Date of Patent: January 6, 2015
    Assignee: General Electric Company
    Inventor: Tamás Újvári
  • Patent number: 8928485
    Abstract: The present invention relates to the acquisition of tilted series images of a minute sample in a short time. The present invention relates to: measuring in advance the relation between an amount of focus shift and a degree of coincidence at the time of acquiring tilted series images; calculating backwards a focus shift from the degree of coincidence on the basis of this relation; correcting the focus shift by controlling a stage, an objective lens, and the like; and thus acquiring the tilted series images. In addition, the present invention relates to: acquiring a reference image in advance at the time of photographing the tilted series images; obtaining the correlation between an acquired image and the reference image; and performing, if the degree of coincidence is equal to or smaller than a set value, processing such as the transmission of a warning message and the stop of an image acquisition sequence.
    Type: Grant
    Filed: June 15, 2009
    Date of Patent: January 6, 2015
    Assignee: Hitachi High-Technologies Corporation
    Inventors: Hideki Kikuchi, Isao Nagaoki, Katsuyuki Minakawa
  • Publication number: 20140340570
    Abstract: According to some embodiments, system and methods for image improvement comprise: receiving a plurality of frames of a given region of interest, the frames comprised of a plurality of pixels; determining, based on a quantum property of the frames, a normalized pixel intensity value for each pixel of each of the plurality of frames; and generating an improved image of the given region of interest based on the plurality of frames and the corresponding normalized pixel intensity values for the frames, the order of the image being two. Also embodiments for generating an image of a target illuminated by quantum entangled particles, such as, photons, are disclosed.
    Type: Application
    Filed: June 12, 2014
    Publication date: November 20, 2014
    Inventors: Ronald E. Meyers, Keith S. Deacon
  • Patent number: 8891812
    Abstract: A method to secure unique information about a handwritten document and to provide verification of document's authenticity, integrity and non-repudiation. The method includes the following steps: creating a document having an area of interest containing information, segmenting the area of interest on the document into a plurality of elements, obtaining the average gray scale of each element, inserting the average gray scale of each element into an identifier, and attaching the identifier to the document.
    Type: Grant
    Filed: November 9, 2006
    Date of Patent: November 18, 2014
    Assignee: Pitney Bowes Inc.
    Inventors: Andrei Obrea, Christian Crews
  • Patent number: 8873880
    Abstract: A method for obtaining and/or enhancing local contrast differences (LD) in digital image input data (in), wherein a local contrast measure (SADap) approximating a two-dimensional sum of absolute difference (SAD) measure is obtained by obtaining a first-dimension sum of absolute difference measure (energyVk(m, n)) representing a sum of absolute difference (SAD) in a first dimension of at least one image region, and obtaining the local contrast measure (SADap) as a second-dimension convoluted first-dimension sum of absolute difference measure by convoluting the first-dimension sum of absolute difference measure (energyVk(m, n)) in a second dimension of the at least one image region, is proposed, wherein the step of obtaining the local contrast measure (SADap) as the second-dimension convoluted first-dimension sum of absolute differences measure further includes an addition step wherein an energy term (?lpfk(j)) representing a first-order difference on a distance (J) of a low pass filtered signal used in obtaini
    Type: Grant
    Filed: April 26, 2010
    Date of Patent: October 28, 2014
    Assignee: Robert Bosch GmbH
    Inventors: Johan Schirris, Sasa Cvetkovic
  • Patent number: 8811768
    Abstract: A method and system for imaging information comprising at least one processor for processing information; a light source for illuminating first and second locations; a spatial receiver located at the second location for receiving the illuminating light comprising an array of pixel locations for detecting high resolution spatial information concerning the illuminating light; the spatial receiver being operatively connected, to the at least one processor and operating to transmit high resolution spatial information correlated to specific intervals of time to the processor; the at least one receiver operatively connected to the processor(s) and operative to receive light reflected from a subject and operating to transmit low resolution spatial information to the processor correlated to specific intervals of time; the processor operating to correlate a response by the at least one receiver with spatial information derived from the spatial receiver at correlating time intervals to create a high resolution image.
    Type: Grant
    Filed: May 22, 2012
    Date of Patent: August 19, 2014
    Assignee: The United States of America as Represented by the Secretary of the Army
    Inventors: Ronald Everett Meyers, Keith Scott Deacon
  • Patent number: 8787682
    Abstract: Systems and methods are disclosed to categorize images by detecting local features for each image; applying a tree structure to index local features in the images; and extracting a rank list of candidate images with category tags based on a tree indexing structure to estimate a label of a query image.
    Type: Grant
    Filed: December 28, 2011
    Date of Patent: July 22, 2014
    Assignee: NEC Laboratories America, Inc.
    Inventors: Ming Yang, Xiaoyu Wang, Yuanqing Lin, Kai Yu
  • Patent number: 8749580
    Abstract: A method and system for applying photo texture acquired from a video resource to a 3D model operates within a 3D modeling system. The modeling system includes a modeling application operating on a workstation and a storage device containing a video resource. A 3D model is created or edited within the 3D modeling system. For a selected surface, the method and system allow selection of a video resource, selection of a video frame of the video resource, and selection of an area of the video frame to use as a photo texture to apply to the selected surface. The selected area of the video frame is copied and mapped to the selected surface of the 3D model.
    Type: Grant
    Filed: August 12, 2011
    Date of Patent: June 10, 2014
    Assignee: Google Inc.
    Inventor: Scott Lininger
  • Patent number: 8744208
    Abstract: Briefly, in accordance with one aspect, a method of binarizing an image is provided. The method includes partitioning the image into a plurality of image segments, each image segment having a plurality of image pixels and partitioning each of the image segments into subsegments, each image subsegment having a plurality of image pixels. The method also includes estimating a grey membership parameter for each image pixel for each of the plurality of image segments and subsegments, combining the grey membership parameter for each of the plurality of image pixels from each of the plurality of image segments and subsegments to estimate a net grey membership parameter for each image pixel and assigning black or white color to each of the plurality of image pixels based on the estimated net grey membership parameter of the respective pixel.
    Type: Grant
    Filed: March 7, 2013
    Date of Patent: June 3, 2014
    Assignee: Jadavpur University
    Inventors: Satadal Saha, Subhadip Basu, Mita Nasipuri, Dipak Kumar Basu
  • Patent number: 8737758
    Abstract: An apparatus of reducing noise includes: an edge determining module determining whether each pixel of an image corresponds to an edge; a low pass filter module performing low pass filtering of the image in two directions and performing low pass filtering only for the pixel determined not to be the edge; a filter selecting module selecting a filter having a flexible size to be applied to a mask region for each of the images low pass filtered based on the average brightness of the entire region and the average brightness of the mask region having a predetermined size; a sigma filter module sigma filtering the mask region using the selected filter for each of the images low pass filtered; and an averaging module averaging the image sigma filtered in the two directions.
    Type: Grant
    Filed: May 31, 2011
    Date of Patent: May 27, 2014
    Assignee: Samsung Electro-Mechanics Co., Ltd.
    Inventors: Gyu Won Kim, Ho Seop Jeong, In Taek Song, Kyoung Joong Min, Tae Hyeon Kwon
  • Patent number: 8682095
    Abstract: A method for recognizing markers printed on a learning material, includes sampling an image of the learning material; grouping the sampled image of pixels into a first image group and a second image group based on a threshold; and calculating medians of the first image group and the second image group to update the threshold with a first average value of the calculated medians. Further, the method for recognizing markers printed on the learning material includes repeating the above until a difference between a previous threshold and an updated threshold is equal to or smaller than a reference value; binarizing an image captured by a camera based on the updated threshold; and detecting the markers based on the binary image.
    Type: Grant
    Filed: July 1, 2009
    Date of Patent: March 25, 2014
    Assignee: Electronics and Telecommunications Research Institute
    Inventors: Su Woong Lee, Junsuk Lee, Yong Hun Kim, Seokjae Lee, Sangwon Um, Shihua Ming
  • Patent number: 8655097
    Abstract: A system and method for a blur brush performing adaptive bilateral filtering is disclosed. The method may include receiving user input selecting an area of an image to be filtered, such as by pointing to the image area using the blur brush. The selected image may comprise an edge and a plurality of pixels. The method may operate to the blur brush identifying the edge in the selected image area. The method may operate to apply a filter tool (e.g., a bilateral filter) to the selected image area, while preserving the edge. The methods may be implemented by program instructions executing in parallel on CPU(s) or GPUs.
    Type: Grant
    Filed: November 26, 2008
    Date of Patent: February 18, 2014
    Assignee: Adobe Systems Incorporated
    Inventors: Jen-Chan Chien, Michael W. Tao, Sylvain Paris
  • Patent number: 8644639
    Abstract: A block noise reduction system and method which may determine a feature value of a local texture at each location of input pixel, may selectively determine 1D filtering mode or 2D filtering mode as a filtering mode based on the determined feature value, and may perform filtering to preserve an edge according to the determined filtering mode.
    Type: Grant
    Filed: May 7, 2009
    Date of Patent: February 4, 2014
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Seung Sin Lee, Young Ran Han, Du-Sik Park
  • Patent number: 8594455
    Abstract: A method and system for improving picture quality of images by providing a series of frames of a given region of interest.
    Type: Grant
    Filed: March 15, 2013
    Date of Patent: November 26, 2013
    Assignee: The United States of America as represented by the Secretary of the Army
    Inventors: Ronald E. Meyers, Keith S. Deacon
  • Patent number: 8577183
    Abstract: A method samples a first spectral band to obtain an initial image frame, determines at least one region of interest of the scene from the initial image frame, each of the at least one region of interest associated with a mean signal level, illuminates the at least one region of interest with at least one illuminator when the mean signal level of the at least one region of interest is at or below a respective threshold of a first plurality of thresholds, the at least one region of interest being illuminated in accordance with a power threshold indicating a minimum illuminator power and agility necessary to illuminate the at least one region of interest, collects at least one image frame in at least one sub-band of a second spectral band, and generates at least one image to be displayed from at least the at least one image frame.
    Type: Grant
    Filed: August 5, 2009
    Date of Patent: November 5, 2013
    Assignee: Raytheon Company
    Inventor: Ian S. Robinson
  • Patent number: 8571344
    Abstract: An image processing method performed by a processor for processing a plurality of pixel values in an image data representing a two-dimensional image, the image processing method including defining a block representing a part of the two-dimensional image corresponding to a predetermined number of pixels in rows and columns, obtaining an average of a gradient of pixel value on the basis of the pixel values of adjacent pixels in the block along each of at least one of rows and at least one of columns, generating a product of the average of the gradient pixel value along each of at least one of the rows and the average of the gradient pixel value along each of at least one of the columns, and generating a double summation of the products of the gradient pixel values of each of the rows and the columns.
    Type: Grant
    Filed: February 24, 2010
    Date of Patent: October 29, 2013
    Assignee: Fujitsu Semiconductor Limited
    Inventors: Hiroshi Iwabuchi, Hiroaki Taniguchi, Atsushi Matsuzaka
  • Patent number: 8571271
    Abstract: A dual-phase approach to red eye correction may prevent overly aggressive or overly conservative red eye reduction. The dual-phase approach may include detecting an eye portion in a digital image. Once the eye portion is detected, the dual-phase approach may include the performance of a strong red eye correction for the eye portion when the eye portion includes a strong red eye. Otherwise, the dual-phase approach may include the performance of a weak red eye correction for the eye portion when the eye portion includes a weak red eye. The weak red eye may be distinguished from the strong red eye based a redness threshold that shows the weak red eye as having less redness hue than the strong red eye.
    Type: Grant
    Filed: May 26, 2011
    Date of Patent: October 29, 2013
    Assignee: Microsoft Corporation
    Inventors: Lu Yuan, Fang Wen, Jian Sun
  • Patent number: 8565549
    Abstract: A contrast enhancement method for an image includes extracting at least one sub-band image from the image, comprising detail information at a predetermined spatial scale; determining a first gain value for each pixel, based on pixel values of the image or the at least one sub-band image; determining a second gain value for each pixel; modifying the first gain value for each pixel using the respective second gain value; and generating an enhanced image by applying the modified first gain values to respective pixels of one or more sub-band images and combining the result with the image. Determining the first gain value for each pixel comprises: estimating a dynamic range of the pixel values in a neighbourhood of that pixel; and setting the first gain value in inverse relation to the dynamic range.
    Type: Grant
    Filed: September 21, 2010
    Date of Patent: October 22, 2013
    Assignee: NXP B.V.
    Inventor: Andre Leitao
  • Patent number: 8532427
    Abstract: A method and system for forming an improved image from a series of frames comprising inputting a pixel value array for each image frame; summing the pixel values in each frame to obtain the frame intensity for each frame; multiplying the pixels in pixel value array by the frame intensity; summing the frame intensity multiplied pixel value arrays together and dividing by the number of frames to obtain an average of the frame intensity multiplied pixel value arrays; then, using the inputted pixel value arrays, creating an array of average pixel values; multiplying the array of average pixel values by the average frame intensity for all of the inputted frames; and subtracting the array of average pixel values multiplied by average frame intensity from the average of the frame intensity multiplied pixel value arrays to provide an array of modified pixel values to form an improved image.
    Type: Grant
    Filed: September 28, 2011
    Date of Patent: September 10, 2013
    Assignee: The United States of America as represented by the Secretary of the Army
    Inventors: Ronald Everett Meyers, Keith Scott Deacon
  • Patent number: 8477149
    Abstract: A method, system and computer readable media for real-time chromakey matting using image statistics. To identify the chroma key spectrum, the system/method executes in three stages. In an off-line training stage, the system performs semi-automatic calibration of the chroma key parameterization. In the real-time classification stage, the system estimates the alpha matte on a GPU. Finally, an optional error minimization stage improves the estimated matte, accounting for misclassifications and signal noise. Given the resulting matte, standard alpha blending composites the virtual scene with the video feed to create the illusion that both worlds coexist.
    Type: Grant
    Filed: April 1, 2010
    Date of Patent: July 2, 2013
    Assignee: University of Central Florida Research Foundation, Inc.
    Inventors: Nicholas Beato, Charles E. Hughes, Mark Colbert, Yunjun Zhang, Kazumasa Yamazawa
  • Patent number: 8478065
    Abstract: A method of processing pixels of an image comprises determining the most homogenous region of the image, calculating a threshold (th) according to the content of the determined region, selecting pixels in the image according to the calculated threshold (th), and applying a gain to the selected pixels. The method can also further comprise calculating the gain according to the content of the image.
    Type: Grant
    Filed: October 1, 2008
    Date of Patent: July 2, 2013
    Assignee: Entropic Communications, Inc.
    Inventors: Mohammed Elhassani, Marc André Georges Duranton, Stephanie Jehan-Besson
  • Patent number: 8442350
    Abstract: An edge parameter computing method for an image, wherein the image includes a plurality of pixels forming a Bayer pattern. The edge parameter computing method comprises: (a) computing an average grey level of at least one specific type pixels in a specific region of the image; (b) computing each grey level difference value between the average grey level and the specific type pixels in the specific region to generate a plurality of grey level difference values; (c) finding a specific pixel with a maximum grey level difference value according to the grey level difference values; and (d) computing a ratio value between the average grey level and the maximum grey level difference value as the edge parameter.
    Type: Grant
    Filed: October 7, 2009
    Date of Patent: May 14, 2013
    Assignees: Silicon Motion Inc., Silicon Motion Inc.
    Inventor: Chun-Wen Chang
  • Patent number: 8437031
    Abstract: An image processor includes a reduced image forming unit, a first reflectance value calculating unit, a normalizing parameter determining unit, a second reflectance value calculating unit, a normalizing unit, a correcting unit, and a reducing information determining unit. The reduced image forming unit reduces an original image to form a reduced image. The first reflectance value calculating unit calculates a first reflectance value for each reduced pixel. The normalizing parameter determining unit determines a normalizing parameter based on a distribution of the first reflectance values. The second reflectance value calculating unit calculates a second reflectance value for each original pixel. The normalizing unit normalizes the second reflectance values based on the normalizing parameter to obtain normalized Retinex values. The correcting unit corrects the original pixel values based on the normalized Retinex values.
    Type: Grant
    Filed: August 31, 2007
    Date of Patent: May 7, 2013
    Assignee: Brother Kogyo Kabushiki Kaisha
    Inventor: Tomohiko Hasegawa
  • Patent number: 8433155
    Abstract: The noise reduction filter is intensity adaptive and incorporates directional variances of input images.
    Type: Grant
    Filed: December 28, 2006
    Date of Patent: April 30, 2013
    Assignee: Texas Instruments Incorporated
    Inventors: Jeffrey Matthew Kempf, Rajeev Ramanath
  • Patent number: 8422818
    Abstract: A method and apparatus for image processing are provided. The method may include generating a first restoration image by removing distortion components from an original image; determining a mixing ratio between the original image and the first restoration image based on distortion information of a region of interest in the original image; and generating a second restoration image by mixing the original image and the first restoration image according to the mixing ratio.
    Type: Grant
    Filed: February 19, 2010
    Date of Patent: April 16, 2013
    Assignee: Samsung Electronics Co., Ltd.
    Inventor: Hee-chul Han
  • Patent number: 8406459
    Abstract: Guilloches (preventing modification) and watermarking (preventing substitution) technologies are combined to protect a medium, such as a card or a passport. The major idea stems from their dual role for medium authentication: the presence of one is needed to check the validity of the other one. By nature, the guilloche network is visible in the image and easily detectable by image processing. This network is therefore used to generate reference points as elements of synchronization to retrieve watermark information originally embedded in the medium that has submitted an RST transformation. These reference points are by nature stronger than any other means involving invisible templates in the spatial or Fourier space.
    Type: Grant
    Filed: November 28, 2008
    Date of Patent: March 26, 2013
    Assignees: Gemalto SA, Gemalto Oy
    Inventors: Frederic Ros, Christophe Mourtel, Teemu Pohjola
  • Patent number: 8363975
    Abstract: There is provided an image determining device including a frequency band signal detecting unit for dividing an image into a plurality of local regions and detecting for each local region signals of a plurality of frequency bands from the image signal; an average value calculating unit for calculating an average value of a characteristic value corresponding to an amplitude, for each local region and for each signal of the plurality of frequency bands; a local region selecting unit for selecting at least one local region based on image information; an average value selecting unit for selecting the average value corresponding to the selected local region; a relative value calculating unit for calculating a relative value of one average value with respect to another average value both of the average values being of the selected average values; and an image determining unit for determining an image based on the relative value.
    Type: Grant
    Filed: August 6, 2008
    Date of Patent: January 29, 2013
    Assignee: Sony Corporation
    Inventors: Masaru Suzuki, Masami Ogata, Kazuhiko Ueda
  • Patent number: 8363889
    Abstract: An image data processing system includes an image input module, a bit map generation module and an encoding module. The image input module receives an image and secret information and obtains at least one gray-level image according to image. The bit map generation module generates a bit map image according to gray-level image and generates an ordered dithering block truncation coding (ODBTC) image according to bit map image and gray-level image. The encoding module generates an encoded gray-level image according to bit map image and secret information, wherein the encoding module divides gray-level image into image blocks, finds candidate blocks with close black and white pixel numbers among the image blocks, selects high frequency blocks belong to the high frequency region of the image from candidate blocks, and randomly embeds secret information into high frequency blocks to generate encoded gray-level image with secret information embedded therein.
    Type: Grant
    Filed: June 22, 2010
    Date of Patent: January 29, 2013
    Assignee: National Taiwan University of Science and Technology
    Inventors: Jing-Ming Guo, Jia-Jin Tsai
  • Patent number: 8311328
    Abstract: An electronic visual aid is provided that includes an evaluating unit, which is supplied with a recording of an information carrier on which information standing out visibly from the background is displayed. The evaluating unit determines a brightness distribution of the recording and derives from the brightness distribution a brightness threshold value lying in the transition zone between a zone of the brightness distribution associated with the background and a zone of the brightness distribution associated with the information. The visual aid also includes an image processing unit which generates from the recording a binary image having only two different, predetermined brightness values, by respectively assigning to the pixels of the binary image the first of the two brightness values when the brightness of the corresponding pixel of the recording is below the brightness threshold value, and otherwise assigning the second brightness value.
    Type: Grant
    Filed: January 8, 2007
    Date of Patent: November 13, 2012
    Assignee: Carl Zeiss AG
    Inventor: Bernd Spruck
  • Patent number: 8310732
    Abstract: An image processing device includes a displaying unit that reads and displays an image; a base color region designator that designates a base color region of the image displayed on the displaying unit; a non-base color region designator that designates a non-base color region of the image displayed on the displaying unit; and a base eliminator that executes a base elimination of the image based on the base color region designated by the base color region designator and the non-base color region designated by the non-base color region designator.
    Type: Grant
    Filed: February 26, 2009
    Date of Patent: November 13, 2012
    Assignee: Oki Data Corporation
    Inventor: Norihide Miyamura
  • Patent number: 8305458
    Abstract: There is a problem in that when magnification chromatic aberration correction is carried out, the difference in reproducibility of high-frequency components, depending on the spatial position, between a color for which position shift correction is not performed and a color for which position shift correction is performed may influence the image quality of an output image. In order to perform magnification chromatic aberration correction, high-frequency components, which are lost due to the position shift correction of a color for which position shift correction is carried out, are extracted from a color for which position shift correction is not carried out, and are added to the color for which position shift correction is carried out. Therefore, the high-frequency components are restored in a pseudo manner.
    Type: Grant
    Filed: August 2, 2010
    Date of Patent: November 6, 2012
    Assignee: Canon Kabushiki Kaisha
    Inventor: Takayuki Hara
  • Patent number: 8306352
    Abstract: Disclosed is an edge sharpening method using maximum and minimum filters. In an embodiment of the present invention, the edge region of an input image signal is detected, minimum and maximum signals are generated for the detected edge region, the input signal of the detected edge region is compared with the average signal of the minimum and maximum signals, and the average of the input signal and the maximum signal is output if the input signal is larger than the average signal, the average of the input signal and the minimum signal is output if the input signal is smaller than the average signal, and the input signal is output if the input signal is equal to the average signal. Meanwhile, median filtering, using a window perpendicular to the direction in which the edge sharpening is performed, is performed on the region on which the edge sharpening has been performed.
    Type: Grant
    Filed: November 21, 2006
    Date of Patent: November 6, 2012
    Assignee: HUMAX Co., Ltd.
    Inventors: Jung Hun Jung, Yong Seok Cho
  • Patent number: 8300092
    Abstract: An in-vivo image acquiring apparatus includes an operation control unit which controls a black image acquiring operation, in which the operation control unit controls an imaging unit and an illuminating unit in such a manner the imaging unit conducts an image acquiring operation in a state the illuminating unit does not conduct an illuminating operation. The in-vivo image acquiring apparatus also includes an average calculating unit which calculates the average value of pixel value in a predetermined determining area, and a black image determining unit, which determines whether the image information acquired by the image acquiring operation is the black image by comparing the average value with a predetermined threshold value. The image information determined as the black image by the black image determining unit is transmitted, as the black image information, to an external apparatus by radio.
    Type: Grant
    Filed: March 5, 2009
    Date of Patent: October 30, 2012
    Assignee: Olympus Medical Systems Corp.
    Inventor: Seiichiro Kimoto