Patents Examined by Samir Ahmed
-
Patent number: 11465453Abstract: A method of operation of a computer system comprising: receiving a tire image for a target tire; determining an analyzability for the target tire based on a wear model including the tire image; analyzing a wear level for the target tire based on the analyzability meets or exceeds a usable threshold; generating an augmented reality image for the wear level for the target tire; and communicating the augmented reality image for displaying the wear level for the target tire.Type: GrantFiled: February 21, 2020Date of Patent: October 11, 2022Assignee: MOJ.IO, Inc.Inventors: James Fulker, David Stelzer, Nicholas Butler, Anthony Hall
-
Patent number: 11468641Abstract: An augmented reality AR device may be communicatively connected to a remote network management platform configured to support a managed network. The AR device may capture an image of a real object in the field of view of an imaging component of the AR device. The real object may be recognized as a known managed object of the managed network. The AR device may also concurrently determine context information indicating a location or physical environment. The AR device may then transmit an identifier of the known managed object and the context information in a message to the management platform. In response, the AR device may receive data associated with the known managed. The AR device may then display a virtual object in a virtual space superimposed on the captured image of the real object, where the virtual object and the virtual space are based on the received management data.Type: GrantFiled: May 11, 2020Date of Patent: October 11, 2022Assignee: ServiceNow, Inc.Inventor: Darius Koohmarey
-
Patent number: 11468269Abstract: The performance of a discriminator is improved at low cost. An image quality parameter group in the development processing is obtained so that the discrimination success rate of a discriminator based on developed image data obtained by performing the development processing on captured image data is increased. For example, the discrimination success rate is obtained by comparing a discrimination result from the discriminator with the correct answer discrimination result in a ground truth database. Since the image quality parameter group in the development processing is optimized in accordance with a discriminator, a preprocessing unit for enhancing the discrimination performance of the discriminator is unnecessary. The performance of a discriminator can be improved at low cost.Type: GrantFiled: March 19, 2019Date of Patent: October 11, 2022Assignee: SONY CORPORATIONInventor: Daisuke Nakao
-
Patent number: 11460412Abstract: A system and method for inspecting a composite material structure for defects includes a) an inspection apparatus having a heating device for heating a surface of the structure, an infrared camera for receiving radiation from the surface in response to heating, a controller configured to generate thermal images from the infrared radiation, b) a training system includes an arrangement for obtaining thermal images from a known composite material sample including a plurality of heating elements positioned to apply heat to an entire surface of the sample, an infrared camera for capturing thermal images of the sample, and a processing system for recording the thermal images in a training database, and c) a computer system coupled to the training system and the inspection apparatus adapted to receive thermal images from the inspection apparatus and detect parameters of defects in the structure using the training database.Type: GrantFiled: October 9, 2019Date of Patent: October 4, 2022Assignee: Saudi Arabian Oil CompanyInventor: Ahmed S. Al-Omari
-
Patent number: 11462007Abstract: A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.Type: GrantFiled: October 13, 2020Date of Patent: October 4, 2022Assignee: DIGITALGLOBE, INC.Inventors: Adam Estrada, Kevin Green, Andrew Jenkins
-
Patent number: 11449733Abstract: The present disclosure provides a neural network training device for recognizing a class of an object included in an image based on an artificial intelligence (AI) system and an application thereof, the neural network training method including: acquiring, by using a first learning network model trained based on source training images respectively included in at least one class, feature information of a query image included in a class different from the at least one class; obtaining a generated image from the feature information of the query image by using a second learning network model acquiring feature information of the obtained generated image by using the first learning network model; and updating weights of layers respectively included in the first and second learning network models, based on a difference between the feature information of the query image and the feature information of the generated image and on a difference between the query image and the generated image.Type: GrantFiled: September 4, 2018Date of Patent: September 20, 2022Assignees: SAMSUNG ELECTRONICS CO., LTD., KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Jun-mo Kim, Byung-ju Kim, Joo-chang Kim, Ye-gang Lee, Min-seok Park, Ju-seung Yun, Jae-young Lee, Dong-gyu Joo
-
Patent number: 11436717Abstract: A first input unit receives an inspection image subject to inspection. A second input unit receives a normal reference image that should be referred to. A processing unit subjects the inspection image input to the first input unit and the reference image input to the second input unit to a process in a neural network. An output unit outputs information that results from the process in the processing unit and relates to an item of defect included in the inspection image.Type: GrantFiled: March 27, 2019Date of Patent: September 6, 2022Assignee: Panasonic Intellectual Property Management Co., Ltd.Inventors: Toshihide Horii, Shohei Kamada
-
Patent number: 11436736Abstract: The present invention relates to a pattern edge detection method applicable to a semiconductor inspection apparatus that performs a pattern inspection using pattern design data. This method includes: generating an image of a pattern; detecting an edge of the pattern on the image based on a reference pattern generated from design data for the pattern; repeating generating of an image of a pattern and detecting of an edge of the pattern on the image to produce training-data candidates including a plurality of images and corresponding pattern edges; determining training data by removing pattern edges and corresponding images from the training-data candidates, the pattern edges to be removed being pattern edges satisfying a predetermined disqualification condition; producing an edge detection model by machine learning using the training data; generating an image of other pattern; and detecting an edge of the other pattern on the image using the edge detection model.Type: GrantFiled: March 4, 2019Date of Patent: September 6, 2022Assignee: TASMIT, INC.Inventor: Masahiro Oya
-
Patent number: 11423302Abstract: An artificial intelligent laundry treatment apparatus according to an embodiment of the present invention includes: a door including an external cover and an internal glass and configured to open and close a laundry entrance; a gasket formed on an inner circumferential surface of the laundry entrance; a door imaging sensor disposed to face the internal glass and configured to acquire a door image; a gasket imaging sensor configured to acquire a gasket image including a region of the gasket; and a processor configured to classify a state of the door on the basis of the door image, to acquire a gasket contamination degree on the basis of the gasket image, and to determine whether inside cleansing is required for a region including an inside of a drum on the basis of at least one of the classification result of the state of the door or the acquired gasket contamination degree.Type: GrantFiled: June 13, 2019Date of Patent: August 23, 2022Assignee: LG ELECTRONICS INC.Inventors: Jinok Kim, Yunsik Park, Sungmok Hwang
-
Patent number: 11416981Abstract: A method for detecting damage and determining a type of damage and a degree or severity of damage to a component of a transmission. The method includes providing a first image of a portion of the component in a reference state and detecting a further image of the portion of the component after intended use. The further image of the portion of the component is detected in an installed state of the component. The method further includes determining, by comparing the further image with the first image, that the component is damaged, determining, by matching the further image against data of a damage database, a type of damage, and outputting the determined type of damage and a degree or severity of damage. The first image, the further image, and the data of the damage database are photographs.Type: GrantFiled: November 20, 2018Date of Patent: August 16, 2022Assignee: ZF FRIEDRICHSHAFEN AGInventors: Daniel Wolf, Johannes Schaefer, Jochen Abhau
-
Patent number: 11410290Abstract: Metrology methods, modules and systems are provided, for using machine learning algorithms to improve the metrology accuracy and the overall process throughput. Methods comprise calculating training data concerning metrology metric(s) from initial metrology measurements, applying machine learning algorithm(s) to the calculated training data to derive an estimation model of the metrology metric(s), deriving measurement data from images of sites on received wafers, and using the estimation model to provide estimations of the metrology metric(s) with respect to the measurement data. While the training data may use two images per site, in operation a single image per site may suffice—reducing the measurement time to less than half the current measurement time. Moreover, confidence score(s) may be derived as an additional metrology and process control, and deep learning may be used to enhance the accuracy and/or speed of the metrology module.Type: GrantFiled: December 23, 2019Date of Patent: August 9, 2022Assignee: KLA CORPORATIONInventors: Boaz Ophir, Yehuda Odes, Udi Shusterman
-
Patent number: 11393232Abstract: Techniques are described for extracting key values from a document without having to rely on finding corresponding labels for the target keys within the extracted text of the document. Further the techniques do not rely on knowledge of the correlation between (a) the location of labels within a document, and (b) the location of the key values that correspond to the labels. Key values are extracted from a document by, identifying candidate values within the document, establishing “joint-candidate” sets from those candidate values, and using a trained machine learning mechanism to score each joint-candidate set of values. The highest scoring joint-candidate set is deemed to reflect the correct mapping of candidate values to target keys for the document.Type: GrantFiled: December 27, 2019Date of Patent: July 19, 2022Assignee: LendingClub Bank, National AssociationInventor: Yifan Wu
-
Patent number: 11386546Abstract: A system for creating a learned model for component image recognition, the learned model being used when performing image recognition of a component that is picked up by a suction nozzle of a component mounter or a component that is mounted on a circuit board, serving as an imaging target, by imaging the imaging target with a camera, and the system includes a computer configured to acquire a reference-learned model to be used for image recognition of a reference component. The computer collects sample component images for each type of a component having a predetermined similarity with the reference component, and creates a component-by-component learned model to be used for image recognition of the component for each type of the component by adding the sample component image for each type of the component, as teacher data of the reference-learned model, and re-learning the added sample component image.Type: GrantFiled: February 9, 2018Date of Patent: July 12, 2022Assignee: FUJI CORPORATIONInventors: Takahiro Kobayashi, Shuichiro Kito, Yuta Yokoi
-
Patent number: 11386549Abstract: Included are: an image acquiring unit acquiring a determination target image in which a target object to be inspected is captured; a learning result acquiring unit acquiring a result of machine learning of forward domain conversion of an image or inverse domain conversion of an image performed using a normal image in which the target object in a normal state is captured as training data; a determination target image analysis unit obtaining a domain-converted image by sequentially performing forward domain conversion and inverse domain conversion on the determination target image using the result of the machine learning; and a determination unit determining whether or not an abnormality is occurring in the target object captured in the determination target image by comparing the determination target image and the domain-converted image.Type: GrantFiled: September 24, 2020Date of Patent: July 12, 2022Assignee: MITSUBISHI ELECTRIC CORPORATIONInventors: Kazuyuki Miyazawa, Kazuo Sugimoto
-
Patent number: 11386548Abstract: A method of storing images of a scene, including receiving an image of a scene, generating at least one image identifier of the image, which is indicative of content of the image, storing the at least one image identifier of the image in association with temporal information for that image in a first storage, determining a degree of similarity between content of the image and previous images which have been received based on a correspondence between the at least one image identifier of the image and the at least one images identifiers of the previous images in the first storage, and storing the at least one image identifier of subsequently received images in a second storage in association with temporal information corresponding to a first previous image when the determined degree of similarity between the image and the first previous image exceeds a predetermined threshold.Type: GrantFiled: March 23, 2020Date of Patent: July 12, 2022Assignees: Sony Corporation, Sony Europe B.V.Inventors: Edward Hawke, James Sharam
-
Patent number: 11385063Abstract: A distance-based score approximation having improved computational efficiency is provided. Responsive to receiving a score request, an observation point is identified based the score request. A geographic database is queried for map information corresponding to geometry elements located within a predetermined maximum distance of the observation point. A plurality of sections of the geometry elements are defined. Each section is associated with one of a plurality of groups of sections based on map information corresponding to a geometry element corresponding to the section. For each of the plurality of sections, an impact curtain area is determined. For each group of sections, the impact curtain area for each section associated with the group is aggregated to define a contribution for the group. The contribution for each group of sections is aggregated to determine the distance-based score. The distance-based score is provided for display via a display of a user computing entity.Type: GrantFiled: July 27, 2020Date of Patent: July 12, 2022Assignee: Liberty Mutual Insurance CompanyInventors: Justin Timmons, Spencer Aronstein, Scott Gorlin
-
Patent number: 11379992Abstract: Systems and methods for frame and scene segmentation are disclosed herein. One method includes associating a first primary element from a first frame with a background tag, associating a second primary element from the first frame with a subject tag, generating a background texture using the first primary element, generating a foreground texture using the second primary element, and combining the background texture and the foreground texture into a synthesized frame. The method also includes training a segmentation network using the background tag, the foreground tag, and the synthesized frame.Type: GrantFiled: May 14, 2019Date of Patent: July 5, 2022Assignee: Matterport, Inc.Inventors: Gary Bradski, Prasanna Krishnasamy, Mona Fathollahi, Michael Tetelman
-
Patent number: 11380118Abstract: A biometric sensor including: a transmitter configured to transmit electromagnetic waves between 1 GHz and 300 GHz; a receiver configured to receive the electromagnetic waves from the transmitter; and wherein the transmitter and receiver are positioned in relation to an object to be scanned such that the receiver receives reflected electromagnetic waves. A method for sensing including: transmitting electromagnetic waves between 1 GHz and 300 GHz to an object; receiving reflected electromagnetic waves from the object; analyzing the electromagnetic waves and reflected electromagnetic waves to determine a characteristic of interest associated with the object.Type: GrantFiled: November 21, 2017Date of Patent: July 5, 2022Inventor: George Shaker
-
Patent number: 11378522Abstract: An information processing apparatus includes a reception unit configured to receive an input specifying a position of a detection target included in an image, an acquisition unit configured to acquire a storage amount of training data including a pair of information indicating the image and information indicating the position specified by the input, a training unit configured to train a training model to detect the detection target from the image based on the stored training data, and a display control unit configured to control a display unit to display the storage amount, and a reference amount of the training data set as an amount of the training data necessary for the training unit to train the training model, in a comparable way.Type: GrantFiled: March 16, 2020Date of Patent: July 5, 2022Assignee: Canon Kabushiki KaishaInventors: Shoichi Hoshino, Masakazu Matsugu, Katsuhiko Mori, Yusuke Mitarai, Atsushi Nogami
-
Patent number: 11373295Abstract: A displacement measurement device includes: a first machine learning model trained to generate, from one image which contains a subject and has noise, at least one image which contains the subject and which has noise or has had noise removed; a first obtainer that obtains a first image which contains the subject and has noise and a second image which contains the subject and has noise; a first generator that, using the first machine learning model, generates M template images containing the subject from the first image and generates M target images containing the subject from the second image, M being an integer of 2 or higher; a hypothetical displacement calculator that calculates M hypothetical displacements of the subject from the M template images and the M target images; and a displacement calculator that calculates a displacement of the subject by performing statistical processing on the M hypothetical displacements.Type: GrantFiled: December 18, 2020Date of Patent: June 28, 2022Assignee: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.Inventors: Akihiro Noda, Taro Imagawa, Hiroya Kusaka, Yuki Maruyama