Patents Examined by Michelle Entezari
-
Patent number: 9055217Abstract: A moving region information calculation unit calculates moving region information from a global motion vector and a local motion vector. An image correction unit generates a corrected reference image obtained by correcting a reference image based on the global motion vector and a corrected reference image obtained by correcting the reference image based on the local motion vector. A composition unit composites a base image with the corrected reference images with composition ratios determined based on the moving region information. The composition ratio of the corrected reference image corrected based on the global motion vector is higher than the composition ratio of the corrected reference image corrected based on the local motion vector in a region having the moving region information indicative of a moving region.Type: GrantFiled: April 20, 2012Date of Patent: June 9, 2015Assignee: OLYMPUS CORPORATIONInventor: Yukihiro Naito
-
Patent number: 9053551Abstract: Embodiments of the invention relate to a method, system, and computer program product to automate image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.Type: GrantFiled: May 23, 2012Date of Patent: June 9, 2015Assignee: International Business Machines CorporationInventors: David J. Beymer, Hayit Greenspan, Tanveer Syeda-Mahmood, Fei Wang, Yong Zhang
-
Patent number: 9053556Abstract: An image processing apparatus synthesizing a plurality of sub-images in a panoramic way to create a panoramic image includes a face recognizing unit recognizing a person's face from a plurality of the sub-images, a sampling image selecting unit selecting a sub-image which has a face recognized by the face recognizing unit, out of a plurality of the sub-images as a sampling image, a sampling unit sampling a plurality of pixels from the selected sampling image.Type: GrantFiled: October 29, 2009Date of Patent: June 9, 2015Assignee: Seiko Epson CorporationInventors: Masatoshi Matsuhira, Kosuke Shingai, Makoto Oyanagi
-
Patent number: 9025903Abstract: An image processing device includes: a first edge strength calculation part that calculates a first edge strength for a focus pixel based on pixel values in a first region that includes the focus pixel in an input image; a second edge strength calculation part that calculates a second edge strength for the focus pixel based on pixel values in a second region that is smaller than the first region and that includes the focus pixel; and a filter processing part that determines a filter coefficient such that a first smoothing strength is higher than a second smoothing strength and that filters the input image using the filter coefficient. The first smoothing strength is obtained where the first edge strength is higher than a first reference value and where the second edge strength is lower than a second reference value, and the second smoothing strength is obtained in other cases.Type: GrantFiled: August 31, 2011Date of Patent: May 5, 2015Assignee: Kabushiki Kaisha ToshibaInventors: Yasuaki Wada, Yasunori Taguchi
-
Patent number: 9008464Abstract: Techniques and systems for media data customization system are provided. In one embodiment, a media data customization system includes a resource allocator that receives media data and a media data customization request and that allocates customization resources for a service of the media data customization request, a pipe repository that stores pipe filter modules, and a pipe manager that retrieves pipe filter modules stored in the pipe repository based on the media data customization request, that integrates the retrieved pipe filter modules to form a pipe group, and that applies the pipe group to the media data using the customization resources to generate customized media data.Type: GrantFiled: June 16, 2009Date of Patent: April 14, 2015Assignee: University-Industry Cooperation Group of Kyung Hee UniversityInventor: Eui-Nam Huh
-
Patent number: 9008393Abstract: Embodiments of the invention relate to automating image classification with respect to coronary vessels in an angiography sequence. Two primary elements are employed, including training and recognition. Training pertains to the pre-processing images and extracting salient features that characterize the appearance of coronary arteries under different viewpoints. Recognition pertains to extraction of features from a new image sequence and determining a classification boundary for the new image from previously classified and labeled image sequences.Type: GrantFiled: August 23, 2012Date of Patent: April 14, 2015Assignee: International Business Machines CorporationInventors: David J. Beymer, Hayit Greenspan, Tanveer Syeda-Mahmood, Fei Wang, Yong Zhang
-
Patent number: 8995750Abstract: There is provided an image composition apparatus including a parallax deriving unit configured to derive a parallax of one area in a background image, the one area corresponding to one object in the background image, an image selection unit configured to select an image which has a parallax different from the parallax of the one area in the background image, as a material image, from a plurality of three-dimensional images, each of which is viewed as a specific object in a three-dimensional manner, and an image composition unit configured to superpose the material image selected by the image selection unit on the background image.Type: GrantFiled: September 28, 2011Date of Patent: March 31, 2015Assignee: Casio Computer Co., Ltd.Inventors: Kiyoshi Ogishima, Yoshihisa Matsumoto
-
Patent number: 8983228Abstract: In one aspect, a method for automatically adjusting temporal creation data for a plurality of images is disclosed. The method may generally include receiving a plurality of image files associated with the plurality of images, wherein each of the plurality of image files includes an initial creation time. In addition, the method may include determining a baseline creation time by analyzing the plurality of image files based on their association with at least one of daytime hours or nighttime hours and adjusting the initial creation time for at least one of the plurality of image files based on the baseline creation time.Type: GrantFiled: May 31, 2012Date of Patent: March 17, 2015Assignee: Google Inc.Inventors: Michael Shynar, Asaf Zomet, Gal Chechik
-
Patent number: 8977072Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.Type: GrantFiled: December 13, 2012Date of Patent: March 10, 2015Assignee: A9.com, Inc.Inventors: Raghavan Manmatha, Mark A. Ruzon
-
Patent number: 8953901Abstract: A computer-implemented method for applying a filter to an image comprising: receiving a filter setting, selecting a selected filter from a family of filters stored on a computer-readable storage medium, based at least on the filter setting, wherein the family of filters comprises a plurality of filters each being an approximation of a function on different orders, and applying the selected filter to a stored image with a processor.Type: GrantFiled: January 12, 2012Date of Patent: February 10, 2015Assignee: Sony CorporationInventors: Dennis Adams, Nikolaos Georgis, Zhenglu Wu
-
Patent number: 8948539Abstract: System and method for image improvement comprising providing a series of frames; summing pixel values to obtain frame intensity; computing average frame intensity; determining frame intensity deviation for each frame by subtracting average frame intensity from frame intensity; determining an array of average pixel values (AAPV) and subtracting AAPV from the pixel value arrays to determine positive or negative pixel deviation values; grouping frames in first or second groups depending positive or negative frame intensity deviation; selecting all pixel values having a positive or negative deviation value and creating subgroups of positive or negative pixel deviation value frames, multiplying the pixel deviation value frames in each subgroup by frame intensity deviation to create first product arrays, which are summed together and divided by total number of frames to obtain second product arrays for each subgroup; selecting one or more of second product arrays to generate an image.Type: GrantFiled: September 9, 2013Date of Patent: February 3, 2015Assignee: The United States of America as represented by the Secretary of the ArmyInventors: Ronald E Meyers, Keith S Deacon
-
Patent number: 8929684Abstract: When an area in a first image is specified, an amounts of characteristics of image data included in the area and a neighboring area are detected and it is determined based on the amount of the characteristics whether or not a notification display indicating that the area is likely not to be a target area needs to be presented. If it is determined that the notification display needs to be displayed, a notification image that enables the area to be identified is generated for the first image and is combined with a second image to generate a composite image and the composite image is displayed on a display unit. On the other hand, if it is determined that the specified area is likely to be a target area, the second image based on the image data included in the area is displayed over the full screen of the display unit.Type: GrantFiled: October 26, 2012Date of Patent: January 6, 2015Assignee: Canon Kabushiki KaishaInventor: Hirofumi Takei
-
Patent number: 8913805Abstract: Methods provided for forward and back-projection, which are referred to as separable footprint (SF) projectors: exemplified by the SF-TR and SF-TT projectors. These methods approximate the voxel footprint functions as 2D separable functions. Because of the separability of these footprint functions, calculating their integrals over a detector cell is greatly simplified and can be implemented efficiently. In some embodiments, the SF-TR projector uses trapezoid functions in the transaxial direction and rectangular functions in the axial direction. In some embodiments, the SF-TT projector uses trapezoid functions in both the axial and transaxial directions. Simulations and experiments showed that both SF projector methods are more accurate than conventional distance-driven (DD) projectors. Moreover, the SF-TT projector is more accurate than the SF-TR projector for rays associated with large cone angles.Type: GrantFiled: August 29, 2011Date of Patent: December 16, 2014Assignee: The Regents of The University of MichiganInventors: Yong Long, Jeffrey A. Fessler, James M. Balter
-
Patent number: 8913844Abstract: An improved method for correcting for noise in the digital domain is disclosed. Reference pixel fast-varying components are extracted using a Hilbert-Huang Transform Real-Time Data Processing System (HHT-DPS-RT). The reference pixels are non-photon-detecting pixels in a sensor array. The fast-varying components of the reference pixels are processed in addition to the average over the remaining trend, facilitating additional noise correction for active pixels.Type: GrantFiled: June 5, 2012Date of Patent: December 16, 2014Assignee: The United States of America as represented by the Administrator of the National Aeronautics Space AdministrationInventors: Katherine R. Heinzen, Semion Kizhner, Maxime Pinchinat, Thomas P. Flatley, Dominic J. Benford
-
Patent number: 8913784Abstract: A method, in accordance with particular embodiments, includes receiving voxel data for a plurality of voxels. Each voxel is associated with a unique volume of space associated with a geographic area. The voxel data for each respective voxel includes one or more values based on one or more reflections from one or more light pulses from a LIDAR system. The method further includes identifying noise values from among the one or more values for each respective voxel. The method additionally includes determining a baseline threshold comprising a static value that is uniform for each of the voxels. The method additionally includes determining a dynamic threshold that varies between the voxels and is based on the identified noise values. The method further includes applying the baseline and dynamic thresholds to the voxel data to generate filtered voxel data. The method also includes generating a three-dimensional image based on the filtered voxel data.Type: GrantFiled: August 29, 2011Date of Patent: December 16, 2014Assignee: Raytheon CompanyInventors: Corey J. Collard, Vernon R. Goodman
-
Patent number: 8903191Abstract: In some embodiments, a method of processing a video sequence may include receiving an input video sequence having an input video sequence resolution, aligning images from the input video sequence, reducing noise in the aligned images, and producing an output video sequence from the reduced noise images, wherein the output video sequence has the same resolution as the input video sequence resolution. Other embodiments are disclosed and claimed.Type: GrantFiled: December 30, 2008Date of Patent: December 2, 2014Assignee: Intel CorporationInventors: Oscar Nestares, Horst W. Haussecker, Scott M. Ettinger, Yoram Gat, Sreenath Kurupati
-
Patent number: 8897605Abstract: Embodiments include a method, a manual device, a handheld manual device, a handheld writing device, a system, and an apparatus. An embodiment provides a device. The device includes an imaging circuit operable to acquire digital information encoded in a hand-formed analog expression marked on a surface by a handheld writing device. The device also includes a translator circuit operable to decode the digital information. The device further includes a correlation circuit operable to generate a signal indicative of the decoded digital information.Type: GrantFiled: January 17, 2011Date of Patent: November 25, 2014Assignee: The Invention Science Fund I, LLCInventors: Alexander J. Cohen, B. Isaac Cohen, Ed Harlow, Eric C. Leuthardt, Royce A. Levien, Robert W. Lord, Mark A. Malamud
-
Patent number: 8861890Abstract: A system for continuously displaying individual images to present a visual narrative is provided. The system includes a storage module that stores multiple digital images. The images include image data that corresponds to a portion of a least one panel of narrative artwork. At least one of the images includes image data that corresponds to a transition that conforms to a visual grammar. An image processor retrieves the images from the storage module and arranges the image data of the images in an ordered configuration according to a predetermined sequence. The predetermined sequence specifies an order for the images. A display module accesses the ordered image data for display as a continuous image.Type: GrantFiled: November 24, 2010Date of Patent: October 14, 2014Inventor: Douglas Alan Lefler
-
Patent number: 8861893Abstract: A method and apparatus for processing images. A portion of a selected image in which a moving object is present is identified. The selected image is one of a sequence of images. Pixels in a region of interest are identified in the selected image. First values are identified for a first portion of the pixels using the images and first transformations. The first portion of the pixels corresponds to the background in the selected image. A first transformation is configured to align features of the background between one image in the images and the selected image. Second values are identified for a second portion of the pixels using the images and second transformations. The second portion of the pixels corresponds to the moving object in the selected image. A second transformation is configured to align features of the moving object between one image in the images and the selected image.Type: GrantFiled: September 27, 2011Date of Patent: October 14, 2014Assignee: The Boeing CompanyInventors: Yang Chen, David R. Gerwe, Deying Zhang
-
Patent number: 8842939Abstract: A direction-adaptive image upsampling system and method using double interpolation is disclosed. Each of double interpolation (DI) units with different interpolation functions receives an input image and generates a corresponding double-interpolated image and an associated double-interpolated difference. A decision unit receives the double-interpolated differences from the DI units for deciding the DI unit that has an optimal interpolation around a pixel under process. An adaptive selector selects the double-interpolated image associated with the DI unit having the optimal interpolation as an output image.Type: GrantFiled: August 23, 2011Date of Patent: September 23, 2014Assignees: National Taiwan University, Himax Technologies LimitedInventors: Shao-Yi Chien, Yi-Nung Liu, Yi-Chun Lin, Ling-Hsiu Huang