Patents Examined by Stephen R Koziol
-
Patent number: 9731500Abstract: A method for testing the reliability of an error detection of an image inspection method by using a computer includes producing a defective test image by superposing specific error elements on an error-free reference image, carrying out the image inspection method with the defective test image, comparing the errors found by the image inspection method with the error set to be expected with the aid of the known errors added to the test image, and evaluating the reliability of the image inspection method with the aid of the difference between found and expected errors.Type: GrantFiled: March 31, 2015Date of Patent: August 15, 2017Assignee: Heidelberger Druckmaschinen AGInventors: Frank Schumann, Frank Soltwedel, Daniel Blatt
-
Patent number: 9734621Abstract: An ultrasonic diagnostic apparatus according to an embodiment includes a rendering controller, a detector, and a voxel data generator. The rendering controller divides three-dimensional data constituted by voxel data into a plurality of slice regions, rearranges the slice regions based on a sight line direction in which the voxel data is observed, and performs volume rendering on the voxel data in which the slice regions have been rearranged so as to generate image data. The detector detects image quality information indicating image quality of image data that is generated by the rendering controller. The voxel data generator rearranges the voxel data constituting the three-dimensional data based on the image quality information detected by the detector based on the sight line direction.Type: GrantFiled: January 28, 2015Date of Patent: August 15, 2017Assignee: Toshiba Medical Systems CorporationInventor: Itsuki Kuga
-
Patent number: 9734415Abstract: An object detection system including multiple detecting means identifies other-vehicle information data acquired by using the multiple detecting means, determines whether or not the other-vehicle information data acquired by using the multiple detecting means 105 and 107 are of the same vehicle to output the other-vehicle information data that can be applied to various control applications when the other-vehicle information data determined to be of the same vehicle are switched, selects either of the multiple other-vehicle information data determined to be of the same vehicle according to the other-vehicle information detecting accuracies of the detecting means 105 and 107, and switches the selected other-vehicle information data to another other-vehicle information in a transition period based on the relative speed and the relative position from the other vehicle.Type: GrantFiled: November 5, 2012Date of Patent: August 15, 2017Assignee: HITACHI AUTOMOTIVE SYSTEMS, LTD.Inventors: Hiroto Mitoma, Seiya Kato
-
Patent number: 9715736Abstract: The present invention generally relates to automatic detection of video artifacts. The present invention relates to automatically detect out the images with visible artifacts due to STB decoding error based on a generated artificial edge map. In particular, the application teaches a method to detect out the images with the visible artifacts and how to identify artificial edges from texture (natural) edges. The present system identifies that artificial edges are most significant in local area, while texture edges are often together with some other texture edges.Type: GrantFiled: August 9, 2012Date of Patent: July 25, 2017Assignee: Thomson LicensingInventors: Debing Liu, Zhibo Chen, Xiaodong Gu
-
Patent number: 9710690Abstract: A fingerprint sensing system comprising a device connection interface, and a sensing arrangement including sensing structures, a read-out circuitry connected the sensing structures, and a sensing arrangement controller for controlling the sensing arrangement between at least a first sensing arrangement operational mode and a second sensing arrangement operational mode. The system further comprising supply circuitry connected to the sensing arrangement, and comprising a supply circuitry controller for controlling the supply circuitry between a first supply circuitry operational mode and a second supply circuitry operational mode in which modes different supply power is provided to the sensing arrangement. The supply circuitry controller transitions the supply circuitry between its modes in response to a power state signal indicative of a future transition of the sensing arrangement from the first operational mode to the second operational mode.Type: GrantFiled: January 17, 2017Date of Patent: July 18, 2017Assignee: Fingerprint Cards ABInventors: David Carling, Robert Hägglund, Emil Hjalmarson, Peter Nygren, Erik Säll
-
Patent number: 9704225Abstract: An image enhancement method calculates a central response value of a target pixel based on an original pixel value of the target pixel. The method includes calculating a first total suppression value of the target pixel, where the values of suppression to the target pixel from the neighborhood pixels refer to values representing suppression effects imposed by the neighborhood pixels on the target pixel. When the central response value is greater than the first total suppression value, the first total suppression value is subtracted from the central response value, and the difference is used as a pixel value of the target pixel after image enhancement. When the central response value is less than the first total suppression value, a value 0 is used as a pixel value of the target pixel after image enhancement.Type: GrantFiled: October 22, 2015Date of Patent: July 11, 2017Assignee: Huawei Technologies Co., Ltd.Inventors: Xinyu Du, Dong Wang
-
Patent number: 9690974Abstract: Platelets or blood cells are detected in a fluid sample by adjusting a focal depth of a microscope through a range of values, the microscope having a mounted sample and an objective lens adapted with one or both of (a) a spherical aberration correction unmatched to a utilized cover plate for the sample, or (2) a numerical aperture unmatched to a utilized illumination source for the sample. Images are recorded at different specific focal depths and in multiple z planes of a fluid bearing the platelets, where the position of platelets may overlap on different of the multiple z planes that are recorded, the images recorded through the cover plate, thus causing the generation of a specific light-dark pattern indicative of platelets at particular positions and at multiple depths in the fluid media. The images are analyzed for the specific light-dark pattern.Type: GrantFiled: March 24, 2014Date of Patent: June 27, 2017Assignee: 2M Engineering LimitedInventors: Thomas Obrien, Hendrik Dijkstra, Marcel F Schemmann
-
Patent number: 9576201Abstract: The present disclosure relates to a method and apparatus for classifying pixels in an input image and image processing system. The apparatus includes a first confidence determination unit configured for determining a first confidence of each of the pixels in the input image belonging to each of a plurality of predetermined classes; a detection unit configured for acquiring, by using a detector for detecting a particular class among the plurality of predetermined classes, detection results used to indicate pixels which belong to the particular class; an updating unit configured for updating the first confidences according to the detection results; and a class determination unit configured for determining the class to which each of the pixels in the input image belongs among the plurality of predetermined classes, according to the updated first confidences.Type: GrantFiled: July 22, 2014Date of Patent: February 21, 2017Assignee: Canon Kabushiki KaishaInventors: Bo Wu, Yong Jiang, You Lv, Xingwei Xu
-
Patent number: 9576187Abstract: A photo sharing system with a face recognition function includes a photo browser and a photo sharing platform. The photo browser allows a user to browse plural photos, and includes a user interface that shows the plural photos; a photo classification module that is activated to automatically classify the plural photos into groups according to face images contained in the plural photos and identified by the face recognition function while showing the groups of photos on the user interface for selection; and a photo transmission module that is activated to automatically pack and transmit a selected one of the groups of photos to a photo sharing platform in the cloud. The photo sharing platform includes a photo file management module that manages at least a photo folder that stores the selected group of photos.Type: GrantFiled: December 4, 2013Date of Patent: February 21, 2017Assignee: PRIMAX ELECTRONICS LTD.Inventor: Chen-Ning Hsi
-
Patent number: 9576359Abstract: The subject invention provides a method for detecting and analyzing the hair follicles on a scalp to assist with hair follicle transplantation. The methods of the subject invention are able to count the number of hair follicle groups and the number of follicles within each group based upon a microscopic image of a sample from a human scalp. An algorithm is then used to cluster the follicles and generate a neighboring connected graph to calculate the inter object distances. A report can then be generated that provides information regarding the density, placement, and percentage of hair follicle type in different areas of the scalp. This report can be used to generate a hair follicle transplant strategy to assist a physician or robotic system.Type: GrantFiled: November 3, 2014Date of Patent: February 21, 2017Assignees: The Florida International University Board of Trustees, NRG Medical, LLCInventors: Md Mahbubur Rahman, S. S. Iyengar, Wei Zeng, Frank Hernandez, Bernard Nusbaum, Paul Rose
-
Patent number: 9569665Abstract: In accordance with one embodiment, a commodity recognition apparatus detects, from a captured image, an object imaged in the captured image and extracts an appearance feature amount of the object from the image of the object; compares the extracted appearance feature amount with feature amount data of a dictionary file in which feature amount data indicating the surface information of a commodity is stored for each recognition target commodity to calculate a similarity degree indicating how similar the appearance feature amount is to the feature amount data for each recognition target commodity; recognizes whether or not the object is a commodity based on the calculated similarity degree; and specifies and notifies the reason in a case in which the object is not recognized as a commodity.Type: GrantFiled: November 11, 2014Date of Patent: February 14, 2017Assignee: TOSHIBA TEC KABUSHIKI KAISHAInventor: Yuishi Takeno
-
Patent number: 9563186Abstract: A method for controlling a medical apparatus includes identifying at least one object and at least one part of a user's body; capturing the position, movement and/or alignment of the identified part of the body and the identified object; and controlling at least one apparatus using a corresponding predetermined command, if predetermined criteria for the identity of the object and/or part of the body and its position, movement and/or alignment are fulfilled. A device for controlling a medical apparatus includes an identifying device which identifies parts of a user's body and objects; a capture device which captures the position, movement and/or alignment of the identified parts of the body and objects; and a control device which controls at least one apparatus using a corresponding predetermined command, if predetermined criteria for the identity of the object and/or part of the body and its position, movement and/or alignment are fulfilled.Type: GrantFiled: March 15, 2013Date of Patent: February 7, 2017Assignee: Brainlab AGInventors: Wolfgang Steinle, Nils Frielinghaus, Christoffer Hamilton
-
Patent number: 9558421Abstract: Systems, devices, and methods disclosed herein may apply a computational spatial-temporal analysis to assess pixels between temporal and/or perspective view imagery to determine imaging details that may be used to generate image data with increased signal-to-noise ratio.Type: GrantFiled: September 26, 2014Date of Patent: January 31, 2017Assignee: RealD Inc.Inventors: Jon Karafin, Mrityunjay Kumar
-
Patent number: 9552645Abstract: Representations of an object (110) in an image generated by an imaging apparatus (100) can comprise two or more separate sub-objects, producing a compound object (500). Compound objects can negatively affect the quality of object visualization and threat identification performance. As provided herein, a compound object (500) can be separated into sub-objects. Three-dimensional image data of a potential compound object (500) is projected into a two-dimensional manifold projection (504), and segmentation is performed on the two-dimensional manifold projection of the compound object to identify sub-objects. Once sub-objects are identified, the two-dimensional, segmented manifold projection (900) is projected into three-dimensional space (1104). A three-dimensional segmentation may then be performed to identify additional sub-objects of the compound object that were not identified by the two-dimensional segmentation.Type: GrantFiled: June 30, 2009Date of Patent: January 24, 2017Assignee: Analogic CorporationInventors: Zhengrong Ying, Baoming Hong, Ram Naidu
-
Patent number: 9547793Abstract: Disclosed are a method and system for dividing a plant organ point cloud. According to information about lamina point cloud blocks and stem point cloud blocks in a previous adjacent point cloud frame of a point cloud frame to be divided and a flatness feature of a data point of the point cloud frame to be divided, a point cloud of the point cloud frame to be divided is divided into lamina point cloud blocks and stem point cloud blocks; taking the adjacent point cloud frame as a reference to divide the point cloud frame facilitates the divided organ in maintaining the consistency of time and space between adjacent point cloud frames, and improves the accuracy of plant organ division.Type: GrantFiled: September 13, 2013Date of Patent: January 17, 2017Assignee: Shenzhen Institutes of Advanced TechnologyInventors: Yangyan Li, Baoquan Chen, Xiaochen Fan
-
Patent number: 9547897Abstract: There is described a system, method, and computer-readable medium having stored thereon executable program code for generating a final Cobb angle prediction for idiopathic scoliosis, the method comprising: receiving patient-specific 3D morphological spine parameters, a selected curve type, and a selected skeletal maturity; applying the patient-specific 3D morphological spine parameters, a selected curve type, and a selected skeletal maturity to a predictive model based on 3D morphological spine parameters, curve type, and skeletal maturity, and generating the final Cobb angle prediction by modeling a progression curve of the idiopathic scoliosis.Type: GrantFiled: October 15, 2013Date of Patent: January 17, 2017Assignees: ECOLE DE TECHNOLOGIE SUPERIEURE, VALORISATION HSJ, LIMITED PARTNERSHIPInventors: Stefan Parent, Marie-Lyne Nault, Jean-Marc Mac-Thiong, Hubert Labelle, Jacques De Guise
-
Patent number: 9547907Abstract: Image segmentation utilizing 3D image data. A plurality of pixels of an image frame may be segmented based at least on a function of pixel color and a pixel depth over the spatial positions within the image frame. A graph-cut technique may be utilized to optimize a data cost and smoothness cost in which at least the data cost function includes a component that is a dependent on a depth associated with a given pixel in the frame. In further embodiments, both the data cost and smoothness functions are dependent on a color and a depth associated with each pixel. Components of at least the data cost function may be weighted for each pixel to arrive at most likely segments. Segmentation may be further predicated on a pre-segmentation label assigned based at least on a 3D spatial position clusters.Type: GrantFiled: December 15, 2014Date of Patent: January 17, 2017Assignee: Intel CorporationInventor: Gowri Somanath
-
Patent number: 9547913Abstract: An information processing device, apparatus, method and non-transitory computer-readable storage medium are disclosed.Type: GrantFiled: September 4, 2015Date of Patent: January 17, 2017Assignee: NEC CorporationInventor: Takashi Shibata
-
Patent number: 9542610Abstract: An image associated with a poll may be acquired via a camera. One or more symbols indicating responses may be found by analyzing the image. The responses specified by the symbols may be determined and saved. The responses may also be displayed to the operator and/or to the respondents.Type: GrantFiled: June 29, 2015Date of Patent: January 10, 2017Assignee: Plickers Inc.Inventors: Nolan R. Amy, Stan R. Amy
-
Patent number: 9536180Abstract: Methods and systems for grapheme splitting of text input for recognition are provided. A method may include receiving a text input in a script and segmenting the text input into one or more graphemes. Each of the one or more graphemes may be split into one or more recognition units based on one or more recognition unit identification criteria associated with the script. Next, a text recognition system may be trained using the recognition units. Text input may be handwritten text input received from a user or a scanned image of text.Type: GrantFiled: December 30, 2013Date of Patent: January 3, 2017Assignee: Google Inc.Inventors: Thomas Deselaers, Daniel Martin Keysers, Dmitriy Genzel, Ashok Chhabedia Popat