Pattern Boundary And Edge Measurements Patents (Class 382/199)
  • Patent number: 11132579
    Abstract: A contour recognition device includes: a projecting unit which projects pattern light; a light quantity adjustment unit which adjusts a light quantity of the pattern light; two photographing units which capture, from different viewpoints, the target and the placement surface; a distance calculation unit which calculates a distance at every two-dimensional position; an image generation unit which generates a distance image which gradient expresses a distance from a maximum distance until a minimum distance at every two-dimensional position; and a contour extraction unit which extracts a contour of the target, in which the light quantity adjustment unit adjusts the light quantity so that the distance of at least the contour of the target cannot be calculated, and the distance of the placement surface can be calculated, and the image generation unit generates an image so that a maximum distance becomes a distance greater than the distance of the placement surface.
    Type: Grant
    Filed: January 6, 2020
    Date of Patent: September 28, 2021
    Assignee: FANUC CORPORATION
    Inventor: Yuuji Taira
  • Patent number: 11132487
    Abstract: A layout of original pattern is rotated in a rotational direction to form a layout of rotation pattern. Vertices and segment points of the layout of rotation pattern are matched with ones of the reference points closest thereto, and the matched reference points are connected to form a layout of first modification pattern. A region of the layout of first modification pattern is enlarged to form a layout of second modification pattern. A layout of reference pattern having the same direction as the layout of rotation pattern is formed. A layout of target pattern is formed based on a region where the layouts of reference pattern and second modification pattern overlap. An optical proximity correction is performed on the layout of target pattern to form a layout of third modification pattern, which is rotated in a reverse rotational direction to form a layout of final pattern.
    Type: Grant
    Filed: April 23, 2020
    Date of Patent: September 28, 2021
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: Kyubin Han, Sangwook Kim
  • Patent number: 11126860
    Abstract: An abnormality detection device calculates high-dimensional feature values from real world data; projects, by using a matrix generated from real world data collected for learning so as to project the feature values onto an abnormality discriminant space, feature values calculated from real world data which is input for inspection onto an abnormality discriminant space, the abnormality discriminant space being used for determining presence or absence of an abnormality; judges the presence or absence of an abnormality from a distribution in the abnormality discriminant space; identifies, if an abnormality is found and if the abnormality is a known abnormality, the content of the abnormality from a trend of a distribution in the abnormality discriminant space and presenting the content of the abnormality; and visually displays a distribution in the abnormality discriminant space as a detection result of an abnormality.
    Type: Grant
    Filed: August 1, 2018
    Date of Patent: September 21, 2021
    Assignee: ADACOTECH INCORPORATED
    Inventors: Keiichi Ito, Takahide Ibe, Nobuyuki Otsu
  • Patent number: 11094212
    Abstract: The sharing of signal segments using a semantic understanding of what is included within the signal segment. Upon selection of a physical entity (or portion thereof) that is rendered within a signal segment, the system then extracts portion(s) of signal segment(s) in which that selected physical entity appears. A representation of the extracted signal segment portion are then dispatched to recipients. Thus, portions of signal segments may be shared at the granularity of the content of what the signal segment depicts. There is wide flexibility in what representations of those signal segment portion(s) are shared.
    Type: Grant
    Filed: February 17, 2017
    Date of Patent: August 17, 2021
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
    Inventors: Vijay Mital, Suraj T. Poozhiyil, Nizam Anuar, Olivier Colle
  • Patent number: 11068740
    Abstract: A method of characterising particles (140) by using a processor (301) to identify a particle boundary (165) of at least one particle (140) in an image (135, 171). The method comprises processing the image (135, 171) using a thresholding method to determine a first boundary (160a) corresponding with the at least one particle (140) and processing the image (135, 171) using an edge detection method to determine a second boundary (160b) corresponding with at the least one particle (140). The first boundary (160a) and second boundary (160b) are combined to create a combined boundary (160). A particle boundary (165) of the at least one particle (140) is determined using the combined boundary. A parameter used by the edge detection method is adaptive, and determined with reference to the image (135, 171).
    Type: Grant
    Filed: September 1, 2017
    Date of Patent: July 20, 2021
    Assignee: Malvern Panalytical Limited
    Inventors: James Hyland, Chris Jones
  • Patent number: 11070819
    Abstract: A method of de-blocking filtering a processed video is provided. The processed video includes a plurality of blocks and each block includes a plurality of sub-blocks. A current block of the plurality of blocks includes vertical edges and horizontal edges. The processed video further includes a set of control parameters and reconstructed pixels corresponding to the current block. A boundary strength index is estimated at the vertical edges and at the horizontal edges of the current block. The set of control parameters, the reconstructed pixels corresponding to the current block and partially filtered pixels corresponding to a set of adjacent sub-blocks are loaded. The vertical edges and the horizontal edges of the current block are filtered based on the boundary strength index and the set of control parameters such that a vertical edge of the current block is filtered before filtering at least one horizontal edge of the current block.
    Type: Grant
    Filed: September 9, 2019
    Date of Patent: July 20, 2021
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Mihir Narendra Mody, Niraj Nandan, Hideo Tamama
  • Patent number: 11049175
    Abstract: A method and system displaying and managing images of consumer products with audio commands and responses. One or more consumer products are selected with target network device with a target audio interface. An N-layer digital image is created that includes an M-layer hierarchy of vector images and/or visual overlays in progressive resolution format and allows progressive resolution display without loss of image quality on the selected plural consumer products that appear in the N-layer digital image. Consumer products are selected with audio commands and audio responses from the target network device via audio commands sent and received on the target audio interface. Consumer products selected with audio commands are placed in a graphical shopping cart/bag that provides progressive resolution display directly from the graphical shopping cart/bag and allows new or different consumer products to be selected directly from the graphical shopping cart/bag via audio commands and responses.
    Type: Grant
    Filed: April 6, 2020
    Date of Patent: June 29, 2021
    Inventor: Joseph R. Dollens
  • Patent number: 11048253
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle and, for only those agents which are high priority agents, generating data characterizing the agents using a first prediction model. In a first aspect, a system identifies multiple agents in an environment in a vicinity of a vehicle. The system generates a respective importance score for each of the agents by processing a feature representation of each agent using an importance scoring model. The importance score for an agent characterizes an estimated impact of the agent on planning decisions generated by a planning system of the vehicle which plans a future trajectory of the vehicle. The system identifies, as high-priority agents, a proper subset of the plurality of agents with the highest importance scores.
    Type: Grant
    Filed: November 21, 2018
    Date of Patent: June 29, 2021
    Assignee: Waymo LLC
    Inventors: Kai Ding, Khaled Refaat, Stephane Ross
  • Patent number: 11034348
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. In one aspect, a method comprises processing an input that characterizes a trajectory of the vehicle in an environment using an importance scoring model to generate an output that defines a respective importance score for each of a plurality of agents in the environment in the vicinity of the vehicle. The importance score for an agent characterizes an estimated impact of the agent on planning decisions generated by a planning system of the vehicle which plans a future trajectory of the vehicle. The high-priority agents are identified as a proper subset of the plurality of agents with the highest importance scores.
    Type: Grant
    Filed: January 31, 2019
    Date of Patent: June 15, 2021
    Assignee: Waymo LLC
    Inventors: Kai Ding, Khaled Refaat, Stephane Ross
  • Patent number: 11006900
    Abstract: The present disclosure relates to a method and a system for standardizing a hemodynamics measurement result and a non-transitory computer-readable recording medium. According to one aspect of the present disclosure, provided is a method for standardizing a measurement result obtained from a device for monitoring hemodynamics, the method comprising the steps of: capturing an image of a subject wearing a monitoring device; defining a photogrammetric coordinate system on the captured image, and converting a preset local coordinate system on the monitoring device into the photogrammetric coordinate system; and converting the photogrammetric coordinate system into a standard coordinate system which is based on a standard space.
    Type: Grant
    Filed: July 5, 2017
    Date of Patent: May 18, 2021
    Assignee: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
    Inventors: Hyeon Min Bae, Gun Pil Hwang, Min Gyu Choi, Jong Kwan Choi, Jae Myoung Kim, Min Su Ji
  • Patent number: 10983215
    Abstract: An advanced driver assistance system (ADAS) and method for a vehicle utilize a light detection and ranging (LIDAR) system configured to emit laser light pulses and capture reflected laser light pulses collectively forming three-dimensional (3D) LIDAR point cloud data and a controller configured to receive the 3D LIDAR point cloud data, convert the 3D LIDAR point cloud data to a two-dimensional (2D) birdview projection, obtain a template image for object detection, the template image being representative of a specific object, blur the 2D birdview projection and the template image to obtain a blurred 2D birdview projection and a blurred template image, and detect the specific object by matching a portion of the blurred 2D birdview projection to the blurred template image.
    Type: Grant
    Filed: December 19, 2018
    Date of Patent: April 20, 2021
    Assignee: FCA US LLC
    Inventors: Dalong Li, Alex M Smith, Stephen Horton
  • Patent number: 10984581
    Abstract: Embodiments provide for cut-aware UV transfer. Embodiments include receiving a surface correspondence map that maps points of a source mesh to points of a target mesh. Embodiments include generating a set of functions encoding locations of seam curves and wrap curves from a source UV map of the source mesh. Embodiments include using the set of functions and the surface correspondence map to determine a target UV map that maps a plurality of target seam curves and a plurality of target wrap curves to the target mesh. Embodiments include transferring a two-dimensional parametrization of the source UV map to the target UV map.
    Type: Grant
    Filed: July 17, 2019
    Date of Patent: April 20, 2021
    Assignee: Pixar
    Inventor: Fernando Ferrari De Goes
  • Patent number: 10984169
    Abstract: A method for providing a dynamic loupe in a window of an electronic device. The method includes displaying a document in the window of the electronic device, displaying, using at least dimensions associated with a first sub-region of the document being displayed, the dynamic loupe for the first sub-region, receiving an instruction to associate the dynamic loupe with a second sub-region of the document being displayed, determining one or more dimensions of the second sub-region, and displaying, using at least the identified one or more dimensions, the dynamic loupe for the second sub-region.
    Type: Grant
    Filed: June 7, 2018
    Date of Patent: April 20, 2021
    Assignee: Apple Inc.
    Inventors: Nils Beck, Conrad Carlen
  • Patent number: 10977797
    Abstract: A method of detecting an edge within digitized images, said method comprising steps of: (a) obtaining said image in a digital form; (b) building a 3D graph of intensity distribution within said image; (c) finding Regions of Interest ROI in the image and subtracting out the background; (d) establishing edge lines within said image; establishing a resultant edge line for each ROI by averaging or maximizing the set of independently obtained edge lines corresponding to said plurality of criteria but that differ from each other by a margin increasing with a predetermined increment; and (f) generating at least one report presenting the quantitative and/or qualitative parameters in a form of accurate quantitative measurements and qualitative inferences regarding medical and general diagnosis of the images and patients utilizing one or more output modules.
    Type: Grant
    Filed: December 13, 2017
    Date of Patent: April 13, 2021
    Assignee: EYES LTD.
    Inventor: Benjamin H. Chadi
  • Patent number: 10957056
    Abstract: An image processing technique uses requirements for a geospatial distribution of image tie points for a triangulation of images. The images are correlated, thereby generating candidate tie points across the images. Statistical consistency checks are applied to the images to identify and dispose of the candidate tie points that are local outliers, and a geometric identification technique is applied to the images to identify and dispose of the candidate tie points that are global outliers. The candidate tie points that are not local outliers or global outliers are spatially down-selected such that the spatially down-selected candidate tie points satisfy the one or more requirements for the geospatial distribution.
    Type: Grant
    Filed: August 30, 2019
    Date of Patent: March 23, 2021
    Assignee: Raytheon Company
    Inventors: Grant B. Boroughs, Stephen J. Raif, Jody D. Verret
  • Patent number: 10949976
    Abstract: A method for determining a contour of an organ in an ultrasound image is performed by a processor in a base unit. The method includes detecting an organ within the ultrasound image; obtaining a centroid position for the organ; extending a set of radial lines from the centroid position beyond an expected organ boundary; determining cost values at candidate nodes on each radial line, of the set of radial lines, by applying costs along gradient vectors that are normal to a contour between adjacent nodes on different radial lines; and selecting a final organ boundary contour based on a cost function analysis of paths through the candidate nodes.
    Type: Grant
    Filed: June 12, 2018
    Date of Patent: March 16, 2021
    Assignee: Verathon Inc.
    Inventors: Joon Hwan Choi, Fuxing Yang
  • Patent number: 10949610
    Abstract: A computing machine managing a template manages a document format, a template, and a cluster generated on the basis of a classification result based on a position of the document in a feature space in such a manner that they correspond to one another; determines whether a cluster to which a target document can belong is present on the basis of a position, in the feature space, of the target document in a case of detecting an opportunity of generating a template of the target document; registers the template of the target document in a case of determining that the cluster to which the target document can belong is not present; generates a cluster corresponding to the registered template; and manages a document format of the target document, the registered template, and the generated cluster in such a manner that they correspond to one another.
    Type: Grant
    Filed: February 8, 2019
    Date of Patent: March 16, 2021
    Assignee: HITACHI, LTD.
    Inventors: Ryosuke Odate, Hiroshi Shinjo, Yasufumi Suzuki, Masahiro Motobayashi
  • Patent number: 10948354
    Abstract: A method of measuring people flow through a doorway using a low-resolution, low-cost infrared array is disclosed. The method includes reading a sequence of sensor data frames from the infrared array; determining a background temperature frame; determining whether sensor data frames include at least one person using noise filtering techniques; identifying at least one group of adjacent pixels corresponding to the at least one person; determining at least one location corresponding to the at least one person; and determining whether the at least one person is a same person as a person in a previous sensor data frame. Based on the matching of a same person through multiple sensor data frames, direction of movement and entry/exit events can be determined. The entry/exit events can advantageously be used to operate and HVAC system, security system, or other such system more efficiently and effectively.
    Type: Grant
    Filed: June 5, 2018
    Date of Patent: March 16, 2021
    Assignee: Robert Bosch GmbH
    Inventors: Sirajum Munir, SeyyedHessamAldin Mohammadmoradi, Omprakash Gnawali, Charles P. Shelton
  • Patent number: 10943140
    Abstract: In some implementations, a device may detect edges in an image, and may identify, based on the edges, a rectangle that bounds a document in the image. The device may detect lines in the image, and may identify edge candidate lines by discarding one or more of the lines. The device may identify intersection points where lines, included in the edge candidate lines, intersect with one another. The device may identify corner candidate points by discarding one or more points included in the intersection points, and may identify a corner point included in the corner candidate points. The corner point may be a point, included in the corner candidate points, that is closest to one corner of the bounding rectangle. The device may perform perspective correction on the image of the document based on identifying the corner point.
    Type: Grant
    Filed: June 17, 2019
    Date of Patent: March 9, 2021
    Assignee: Capital One Services, LLC
    Inventors: Jason Pribble, Nicholas Capurso, Daniel Alan Jarvis
  • Patent number: 10937201
    Abstract: A method for generating a vehicle environment view involves: capturing camera images with vehicle cameras on a vehicle body of a vehicle; and calculating of the vehicle environment view based on the camera images. In the vehicle environment view, a texture of a non-visible region of a ground surface located under the vehicle body and not visible to the vehicle cameras is calculated based on texture data of a visible region of the ground surface that is visible to vehicles cameras and surrounds the non-visible region.
    Type: Grant
    Filed: September 15, 2017
    Date of Patent: March 2, 2021
    Assignee: Conti Temic microelectronic GmbH
    Inventors: Georg Arbeiter, Rodrigo Garcia Marques, Martin Simon, Johannes Petzold, Joerg Schrepfer, Markus Friebe
  • Patent number: 10933931
    Abstract: An image processing method and system, a storage medium and a moving system are provided, and the image processing method includes: obtaining a 2D depth array Dp having depth information of a target object; calculating to obtain a depth vector D=[d1, d2, d3, . . . , di, . . . , dn], in which an element di is an average value of elements of the ith row in the 2D depth array; calculating to obtain an edge determination vector ?D=[?d1, ?d2, ?d3, . . . , ?di, . . . , ?dn?1], in which an element ?di=|di?di+1|; calculating an average value d0=(|?d2??d1|+|?d3??d2|+ . . . +|?dn?1??dn?2|)/(n?2); and comparing an absolute value |?di??di+1| with d0 to identify an edge of the target object, in which in a situation where |?di??di+1| is greater than d0, it is determined that the elements of the ith row in the 2D depth array Dp correspond to the edge of the target object.
    Type: Grant
    Filed: February 2, 2018
    Date of Patent: March 2, 2021
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventors: Li Zhou, Xuan He, Kailiang Zhang, Jingang Kang
  • Patent number: 10922535
    Abstract: The present disclosure provides a method and a device for identifying a wrist, a method for identifying a gesture, electronic equipment and a computer-readable storage medium. The method includes: obtaining a first image, the first image including a hand and the wrist; binarizing the first image to obtain a binary image; extracting a partial image from the binary image, where the partial image is obtained by removing at least of finger information from the binary image; identifying a principal direction of the binary image based on the partial image, and determining a target direction perpendicular to the principal direction; and determining a target position in the binary image where the binary image matches a first wrist feature as a wrist position in the binary image according to the target direction.
    Type: Grant
    Filed: November 29, 2018
    Date of Patent: February 16, 2021
    Assignee: BOE TECHNOLOGY GROUP CO., LTD.
    Inventor: Zhenkun Song
  • Patent number: 10909313
    Abstract: Various embodiments are generally directed to systems for summarizing data visualizations (i.e., images of data visualizations), such as a graph image, for instance. Some embodiments are particularly directed to a personalized graph summarizer that analyzes a data visualization, or image, to detect pre-defined patterns within the data visualization, and produces a textual summary of the data visualization based on the pre-defined patterns detected within the data visualization. In various embodiments, the personalized graph summarizer may include features to adapt to the preferences of a user for generating an automated, personalized computer-generated narrative. For instance, additional pre-defined patterns may be created for detection and/or the textual summary may be tailored based on user preferences. In some such instances, one or more of the user preferences may be automatically determined by the personalized graph summarizer without requiring the user to explicitly indicate them.
    Type: Grant
    Filed: June 22, 2017
    Date of Patent: February 2, 2021
    Assignee: SAS INSTITUTE INC.
    Inventors: Ethem F. Can, Richard W. Crowell, James Tetterton, Jared Peterson, Saratendu Sethi
  • Patent number: 10902592
    Abstract: A method for analysis of a digital image in order to determine a value relating to an amount of a substance shown in the image includes using a threshold to identify all pixels of the digital image above or below a certain intensity value in order to produce a first binary image. Texture filtering is used to identify regions of high texture in the digital image to produce a second binary image in which all regions of high texture are pixels with a first state. The first and second binary images are overlayed to produce a combined binary image. A value relating to the amount of the substance is determined based on the area of the combined binary image with pixels having the first state.
    Type: Grant
    Filed: June 15, 2017
    Date of Patent: January 26, 2021
    Assignee: Q-Linea AB
    Inventors: Caroline Johansson, Amin Allalou, Ylva Molin, Magnus Sandow, Carolina Wahlby
  • Patent number: 10902271
    Abstract: The invention relates to a method for recognizing a raised object on the basis of images in an environmental region of a motor vehicle, comprising: capturing a first image from a first camera and a second image from a second camera, transforming the first and second images into a common reference system, forming gradients over pixel values of pixels along gradient lines in the transformed first and second images, summing gradients along parallel summation lines to form a gradient sum, determining a first pair of the maxima of the gradient sum in the transformed first image and a second pair of the maxima of the gradient sum in the transformed second image, recognizing the raised object, if at least one distance between the maxima of the first pair in the transformed first image deviates from a distance of the maxima of the corresponding second pair in the transformed second image.
    Type: Grant
    Filed: December 19, 2017
    Date of Patent: January 26, 2021
    Assignees: Connaught Electronics Ltd., Bayerische Motoren Werke Aktiengesellschaft
    Inventors: Pantelis Ermilios, Jonathan Horgan, Ciaran Hughes, Guenter Bauer
  • Patent number: 10902053
    Abstract: Approaches are described for shape-based graphics search. Each graphics object of a set of graphics objects is analyzed. The analyzing includes determining an outline of the graphics object from graphics data that forms the graphics object. The outline of the graphics object is sampled resulting in sampled points that capture the outline of the graphics object. A shape descriptor of the graphics object is determined which captures local and global geometric properties of the sampled points. Search results of a search query are determined based on a comparison between a shape descriptor of a user identified graphics object and the shape descriptor of at least one graphics object of the set of graphics objects. At least one of the search results can be presented on a user device associated with the search query.
    Type: Grant
    Filed: December 21, 2017
    Date of Patent: January 26, 2021
    Assignee: ADOBE INC.
    Inventor: Sanjeev Kumar Biswas
  • Patent number: 10894364
    Abstract: A method of controlling an additive manufacturing process in which a directed energy source is used to selectively melt material to form a workpiece, forming a melt pool in the process of melting, the method comprising: using an imaging apparatus to generate an image of the melt pool comprising an array of individual image elements, the image including a measurement of at least one physical property for each of the individual image elements; from the measurements, mapping a melt pool boundary of the melt pool; computing a geometric length of the melt pool boundary; and controlling at least one aspect of the additive manufacturing process with reference to the geometric length.
    Type: Grant
    Filed: December 13, 2018
    Date of Patent: January 19, 2021
    Assignee: General Electric Company
    Inventor: Thomas Graham Spears
  • Patent number: 10853636
    Abstract: An information processing apparatus includes a memory, and a processor coupled to the memory and configured to obtain a plurality of images of a subject captured at different timings, detect a feature point of the subject from each of the plurality of images, identify a movement locus of the feature point between the plurality of images, identify a center position of a circle having the movement locus as an arc, and determine a posture of the subject based on the identified center position.
    Type: Grant
    Filed: May 16, 2018
    Date of Patent: December 1, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Shanshan Yu, Norihiro Kakuko, Takeshi Otani
  • Patent number: 10846568
    Abstract: Deep learning-based automatic gesture recognition method and system are provided. The training method according to an embodiment includes: extracting a plurality of contours from an input image; generating training data by normalizing pieces of contour information forming each of the contours; and training an AI model for gesture recognition by using the generated training data. Accordingly, robust and high-performance automatic gesture recognition can be performed, without being influenced by an environment and a condition even while using less training data.
    Type: Grant
    Filed: October 1, 2018
    Date of Patent: November 24, 2020
    Assignee: Korea Electronics Technology Institute
    Inventors: Sang Ki Ko, Choong Sang Cho, Hye Dong Jung, Young Han Lee
  • Patent number: 10846498
    Abstract: Systems and methods illustrated herein disclose error correction of a two-dimensional (2D) symbol. The systems and methods include reading, by a hardware processor, a plurality of codewords in the 2D symbol. Further, the systems and methods include identifying, by the hardware processor of, an optically ambiguous codeword of the plurality of codewords in the 2D symbol. The optically ambiguous codeword corresponds to a codeword with a minimum interior contrast level below a predefined minimum interior contrast level. Further, the systems and methods include correcting, by the hardware processor, errors in the optically ambiguous codeword based on, a location of the optically ambiguous codeword and an erroneous decoded value associated with the optically ambiguous codeword.
    Type: Grant
    Filed: February 6, 2019
    Date of Patent: November 24, 2020
    Assignee: HAND HELD PRODUCTS, INC.
    Inventor: H. Sprague Ackley
  • Patent number: 10839518
    Abstract: An image edge extraction device for an automated driving system is capable of extracting an image edge in a rapid manner. The device employs an image edge extraction method that includes: acquiring a grayscale image of a target image; calculating an edge magnitude and an edge angle of the grayscale image, so as to generate an edge magnitude image and an edge angle image; detecting an edge peak of the edge magnitude image in accordance with the edge angle image, so as to acquire each edge point of the edge magnitude image and acquire an edge peak detection result; and performing double-thresholding segmentation on the edge peak detection result through a flooding method, so as to acquire an image edge of the target image.
    Type: Grant
    Filed: January 17, 2019
    Date of Patent: November 17, 2020
    Assignee: Beijing Smarter Eye Technology Co. Ltd.
    Inventors: Ran Meng, Feng Cui, Haitao Zhu, An Jiang, Hua Chai, Zunying Pang
  • Patent number: 10837630
    Abstract: A system for detecting misalignment of a light fixture uses a gateway controller device to receive images captured by an aerial drone. The gateway controller will select a group of the images and, for each image in the group: identify a segment of an illuminated surface that is contained in the image; identify a light fixture that is configured to direct light to the segment; and determine whether the image contains content indicating that the light fixture improperly aligned. For any image that indicating that the light fixture is improperly aligned, the system will output a signal indicating that the light fixture requires recalibration.
    Type: Grant
    Filed: March 4, 2019
    Date of Patent: November 17, 2020
    Assignee: SIGNIFY HOLDING B.V.
    Inventors: Daniel S. Foster, Brian M. Wilson, Christopher D. Nolan, Joseph R. Casper
  • Patent number: 10832444
    Abstract: A system for estimating a plurality of device poses in a space, comprising: at least one device, comprising at least one hardware processor connected to at least one sensor and adapted to: in at least one of a plurality of iterations: using at least one model to compute a first estimated device pose in a first identified region of the space in response to at least one input signal captured by the at least one sensor, where the at least one model is one of a plurality of region specific models, each trained to compute an estimated device pose in one of a plurality of regions of the space; providing the first estimated device pose to at least one software object executed by the at least one hardware processor to perform a pose-oriented task; receiving at least one other model trained to compute another estimated device pose in a second.
    Type: Grant
    Filed: February 18, 2019
    Date of Patent: November 10, 2020
    Assignee: NEC Corporation Of America
    Inventor: Tsvi Lev
  • Patent number: 10825185
    Abstract: The present invention relates to a method and apparatus for performing object segmentation in an image. More particularly, the present invention divides a screen of an input image into at least two sub-images, and generates one image by combining the at least two sub-images to which an image segmentation algorithm is respectively applied.
    Type: Grant
    Filed: November 28, 2018
    Date of Patent: November 3, 2020
    Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
    Inventors: Kwang Yong Kim, Sang Joon Park, Gi Mun Um, Chang Eun Lee
  • Patent number: 10817728
    Abstract: A method of updating an identification algorithm of a vehicle includes sensing an image and drawing boundary boxes in the image. The algorithm attempts to identify an object-of-interest within each respective boundary box. The algorithm also attempts to identify a component of the object-of-interest within each respective boundary box, and if component is identified, calculates an excluded amount of a component boundary that is outside an object boundary. When the excluded amount is greater than a coverage threshold, the algorithm communicates the image to a processing center, which may identify a previously un-identified the object-of-interest in the image. The processing center may add the image to a training set of images to define a revised training set of images, and retrain the identification algorithm using the revised training set of images. The updated identification algorithm may then be uploaded onto the vehicle.
    Type: Grant
    Filed: January 23, 2019
    Date of Patent: October 27, 2020
    Assignee: GM Global Technology Operations LLC
    Inventors: Syed B. Mehdi, Yasen Hu, Upali P. Mudalige
  • Patent number: 10796435
    Abstract: An image processing method includes calculating a first feature-quantity that includes feature-quantities for indicating features of individual pixel values of pixels located in a first direction perpendicular to a first line segment out of line segments and feature-quantities for indicating features of individual pixel values of pixels located in a second direction opposite to the first direction with respect to the first line segment, and calculating, based on pixel values of pixels located for each predetermined distance in a third direction perpendicular to a second line segment out of the line segments and pixel values of pixels located for each of the predetermined distance in a fourth direction opposite to the third direction with respect to the second line segment, a second feature-quantity that includes feature-quantities for indicating individual features of the pixels located for each of the predetermined distance from the second line segment.
    Type: Grant
    Filed: September 25, 2018
    Date of Patent: October 6, 2020
    Assignee: FUJITSU LIMITED
    Inventor: Nobuyasu Yamaguchi
  • Patent number: 10769429
    Abstract: Examples of present disclosure relate to method and system to extract text from engineering drawing for performing accurate OCR. Initially, for the extraction, image of engineering drawing is received with a plurality of components. Each of the plurality of components in the image is classified to be one of a textual component and a non-textual component. At least one word element for textual components from the plurality of components is identified based on segmentation of the plurality of components. The segmentation is performed by drawing a plurality of horizontal edge projections of a predefined length for each of the textual components. Further, the textual components is identified to be associated with the at least one word element when horizontal edge projection of each of the textual components overlaps with adjacent textual component. The at least one word element is provided as extracted text for performing OCR on the engineering drawing.
    Type: Grant
    Filed: October 24, 2018
    Date of Patent: September 8, 2020
    Assignee: Wipro Limited
    Inventors: Aniket Anand Gurav, Rupesh Bapuji Wadibhasme, Swapnil Dnyaneshwar Belhe
  • Patent number: 10762372
    Abstract: An image processing apparatus inputs a first and a second captured videos; extracts attribute values of image regions of background objects commonly included in the first and the second captured videos respectively; extracts attribute values of image regions of objects respectively included in the first and the second captured videos; derives a relative index of an attribute value of the image region of the object with reference to the attribute value of the image region of the background object with respect to the object included in each of the first and the second captured videos; and detects the same object included in the first and the second captured videos based on the index derived with respect to the object included in each of the first and the second captured videos.
    Type: Grant
    Filed: July 23, 2018
    Date of Patent: September 1, 2020
    Assignee: Canon Kabushiki Kaisha
    Inventors: Hiroshi Tojo, Kotaro Yano
  • Patent number: 10755135
    Abstract: A computational imaging device and method are described, wherein the computational imaging device is operable to perform corner detection and other computer vision tasks more efficiently and/or more robustly than traditional imaging devices. In addition, methods are described operable to jointly optimize the computational imaging device and the corner detection task.
    Type: Grant
    Filed: September 23, 2018
    Date of Patent: August 25, 2020
    Inventor: Paulo Eduardo Xavier da Silveira
  • Patent number: 10757386
    Abstract: Disclosed are a white balance calibration method based on skin color data and an image processing apparatus using the same. By using the method and the image processing apparatus, weight allocation of the skin color data in an input image may be adaptively performed to avoid white balance calibration errors due to excessive skin color data. Therefore, the present disclosure can further solve an issue that in video applications, the white balance calibration is easily interfered by a large amount of the skin color data. Moreover, the present disclosure may be adapted to different color temperatures and may output images having colors closer to actual colors.
    Type: Grant
    Filed: October 26, 2018
    Date of Patent: August 25, 2020
    Assignee: REALTEK SEMICONDUCTOR CORP.
    Inventors: Ching-Ju Hsiao, Wen-Tsung Huang
  • Patent number: 10748317
    Abstract: A logo controller includes: a logo area detector for detecting a logo area commonly included in a plurality of first image frames, based on the plurality of first image frames; a logo peripheral area setting unit for setting a logo peripheral area expanded based on the logo area; a display load determiner for calculating a display load value, based on grayscale values of at least one first image frame, and determining the difference between a logo peripheral area representative value based on grayscale values of the logo peripheral area and the display load value exceeds a first reference value; and a logo peripheral area corrector for generating a second image frame.
    Type: Grant
    Filed: July 26, 2019
    Date of Patent: August 18, 2020
    Assignee: Samsung Display Co., Ltd.
    Inventor: Geun Jeong Park
  • Patent number: 10746542
    Abstract: Embodiments disclosed herein relate generally to methods for measuring a characteristic of a substrate. In an embodiment, the method includes scanning over the substrate with a scanning probe microscope, the substrate having fins thereon, the scanning obtaining images showing respective fin top regions of the fins, the scanning probe microscope interacting with respective portions of sidewalls of the fins by a scanning probe oscillated during the scanning, selecting images obtained at a predetermined depth below the fin top regions to obtain a line edge profile of the fins, by a processor-based system, analyzing the line edge profile of the fins using power spectral density (PSD) method to obtain spatial frequency data of the line edge profile of the fins, and by the processor-based system, calculating line edge roughness of the fins based on the spatial frequency data.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: August 18, 2020
    Assignee: TAIWAN SEMICONDUCTOR MANUFACTURING CO., LTD.
    Inventors: Wei-Shan Hu, Dong Gui, Jang Jung Lee, Che-Liang Li, Duen-Huei Hou, Wen-Chung Liu
  • Patent number: 10740903
    Abstract: Techniques of detecting edges of objects in images include applying an adaptive threshold to a sigmoidal membership function of a fuzzy gradient of the image brightness. For example, when a computer configured to detect edges of an object of an image receives a grayscale image, the computer computes gradients of the image brightness at each pixel to form a gradient matrix. The computer then creates a fuzzy gradient matrix by applying a sigmoidal membership function to each element of the gradient matrix to form a smoothed gradient matrix. The computer then performs an adaptive threshold operation on the smoothed gradient matrix to produce the edges of the object of the image.
    Type: Grant
    Filed: July 18, 2018
    Date of Patent: August 11, 2020
    Assignee: ADOBE INC.
    Inventor: Somya Jain
  • Patent number: 10740591
    Abstract: Systems and methods provide adapted content to a visitor to a physical environment. An example method receives an image of a visitor to an environment. A visitor portion of the image is distinct from an environment portion of the image. The method detects one or more shapes in the visitor portion of the image using an automatic shape detection technique and defines an approximate boundary of the one or more shapes using a mask. The one or more shapes can be shapes of the visitor's clothing items. The method then calculates an attribute for an area of the image within the mask and identifies electronic content based on the attribute for the area of the image within the mask. The attribute can be a color attribute for the area such as a median color or a dominant color. The method provides the identified electronic content for display in the environment.
    Type: Grant
    Filed: August 23, 2016
    Date of Patent: August 11, 2020
    Assignee: Adobe Inc.
    Inventors: Damien Antipa, Alexandre Capt
  • Patent number: 10713792
    Abstract: A system for processing a seller provided input image depicting an object. The system may process the input images to be in compliance with an online shopping website's image requirements. The image processing service may execute multiple modules on the input image. An edge detection module may detect one or more edges of the image of the object and determine border data indicative of a border around the object. An object of interest module may extract the image of the object within the border to generate an object of interest image. A background extraction module may create one or more closed shapes to separate the image of the object from background pixels. A hole detection module may traverse the one or more closed shapes to determine a presence of background pixels, remove the background pixels, and generate a resulting image.
    Type: Grant
    Filed: January 13, 2017
    Date of Patent: July 14, 2020
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Risto Fermin Rangel Kuoppa, Sergio Damo De Lemos, Munir Mahmood, Mohammed Nazeeruddin
  • Patent number: 10706315
    Abstract: An image processing device includes a memory, and a processor coupled to the memory, wherein the processor is configured to execute acquiring a captured image including an original document region, detecting a color component value of a predetermined area in the captured image, detecting an edge in the predetermined area to acquire an edge amount indicating any one or both of a density of the edge and an edge intensity, and identifying, based on the color component value and the edge amount, a difference between a background of the original document region and a background of a background region obtained by removing the original document region from the captured image.
    Type: Grant
    Filed: October 24, 2018
    Date of Patent: July 7, 2020
    Assignee: PFU LIMITED
    Inventors: Masayoshi Hayashi, Kiyoto Kosaka
  • Patent number: 10692291
    Abstract: An information processing apparatus comprises a determination unit configured to analyze a captured image of a finger and determine whether the captured image is a captured image appropriate to measure a dimension of a part of the finger; a measuring unit configured to measure a dimension of the finger using the captured image determined to be appropriate by the determination unit; and a generation unit configured to generate a model of a three-dimensional shape of the finger using information of the dimension.
    Type: Grant
    Filed: May 21, 2018
    Date of Patent: June 23, 2020
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Kazuhiro Koga
  • Patent number: 10690988
    Abstract: An apparatus can include a control device configured to select a scene from a collection of scenes for a window including electrochromic devices in response to receiving an input corresponding to state information. In another aspect, a method of operating an apparatus can include receiving an input corresponding to state information; and at a control device, in response to receiving the input, selecting a scene from a collection of scenes. The collection of scenes may be validated before using the scenes. The scenes may be validated based on physical configuration of the controlled space, preferences of the occupant, or the like. Still further, scenes can be changed to allow for the passage of time or an illusion of changing sky conditions when sky conditions are not changing. The apparatus and method can be simpler to understand and implement as compared to complex control strategies.
    Type: Grant
    Filed: August 8, 2019
    Date of Patent: June 23, 2020
    Assignee: SAGE ELECTROCHROMICS, INC.
    Inventors: Louis J. Podbelski, Joshua M. Battles, Bryan D. Greer, Helen E. Sanders
  • Patent number: 10685223
    Abstract: Systems and methods are provided for processing and extracting content from an image captured using a mobile device. In one embodiment, an image is captured by a mobile device and corrected to improve the quality of the image. The corrected image is then further processed by adjusting the image, identifying the format and layout of the document, binarizing the image and extracting the content using optical character recognition (OCR). Multiple methods of image adjusting may be implemented to accurately assess features of the document, and a secondary layout identification process may be performed to ensure that the content being extracted is properly classified.
    Type: Grant
    Filed: May 24, 2019
    Date of Patent: June 16, 2020
    Assignee: Mitek Systems, Inc.
    Inventors: Grigori Nepomniachtchi, Mike Strange
  • Patent number: 10685452
    Abstract: The invention relates to a registration apparatus (14) for registering images comprising a unit (11) for providing a first and a second image of an object, such that an image element of the first image at a respective position has been reconstructed by multiplying projection data values of rays traversing the image element with weights and by backprojecting the weighted projection data values, a unit (12) for providing a confidence map comprising for different positions in the first image confidence values being indicative of a likelihood that an image feature is caused by a structure of the object, the confidence value being calculated as a sum of a function, which depends on the respective weight, over the rays traversing the respective image element, and a unit (13) for determining a transformation for registering the first and second image to each other under consideration of the confidence map.
    Type: Grant
    Filed: June 17, 2016
    Date of Patent: June 16, 2020
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Rolf Dieter Bippus, Sven Kabus, Michael Grass