Patents Examined by Michael J Vanchy, Jr.
-
Patent number: 11188728Abstract: A display device includes a display panel having a display area including pixels in a emitting area, a layer disposed on the display panel and including photo sensors to generate sensing signals upon activation thereof, a panel driving unit to supply a first signal, during a first mode, to display an image in the display area, and supply a second signal, during a second mode, to increase the luminance of the emitting area, a detecting unit to perform a fingerprint sensing operation to detect a fingerprint, during the second mode, based on sensing signals received from the photo sensors, and a setting unit to change a characteristic of the emitting area in response to the fingerprint sensing operation.Type: GrantFiled: September 18, 2018Date of Patent: November 30, 2021Assignee: Samsung Display Co., Ltd.Inventor: Jong Woong Park
-
Patent number: 11182586Abstract: A background subtraction method includes: obtaining a first background image corresponding to a first object, wherein the first object has a first reflectivity; obtaining a second background image corresponding to a second object, wherein the second object has a second reflectivity, and the first reflectivity is different from the second reflectivity; calculating a plurality of relative values of the first background image relative to the second background image so as to obtain a mask image; obtaining a target image; subtracting the second background image from the target image so as to obtain a first background-removed image; and calculating and outputting a second background-removed image according to the first background image, the second background image, the first background-removed image and the mask image.Type: GrantFiled: October 18, 2019Date of Patent: November 23, 2021Assignee: SHENZHEN GOODIX TECHNOLOGY CO., LTD.Inventors: Chung-Te Li, Chieh-Wei Lo, Chih-Long Hsu
-
Patent number: 11176660Abstract: A method and system for sorting pistons with flaws is disclosed. In an embodiment, a piston with flaws is three dimensionally scanned and compared to a reference image to detect the location and geometry of the flaws. The location and geometry of the flaws are recorded and used to generate a surface condition score. The pistons are sorted based on the surface condition score being higher or lower than a set threshold value.Type: GrantFiled: July 25, 2019Date of Patent: November 16, 2021Assignee: Caterpillar Inc.Inventors: Kegan Luick, Kevin P. Reardon, Allison Karen White, Jason Robert Mrkonich, William Ryan McDermith
-
Patent number: 11170261Abstract: Systems and methods of generating a compact visual vocabulary are provided. Descriptor sets related to digital representations of objects are obtained, clustered and partitioned into cells of a descriptor space, and a representative descriptor and index are associated with each cell. Generated visual vocabularies could be stored in client-side devices and used to obtain content information related to objects of interest that are captured.Type: GrantFiled: December 31, 2019Date of Patent: November 9, 2021Assignee: Nant Holdings IP, LLCInventors: Bing Song, David McKinnon
-
Patent number: 11164026Abstract: A computer-implemented method of generating a graphical user interface based on image analysis is disclosed, the method including cognitively analyzing, by a data processing system, an image, which may be associated with a user, to identify item(s) in the image, obtaining, by the data processing system, available image filter(s) based on the identified item(s), presenting, by the data processing system, the available image filter(s) to the user, receiving, by the data processing system, a selection of an image filter from the one or more of the at image filter(s) from the user, and applying, by the data processing system, an image overlay to the image, the image overlay including the selection of an image filter as a selectable option. The available image filter(s) can be obtained by searching for them based on a relationship, by searching based on image filters associated with the identified item(s) or by using a cognitive suggestion service.Type: GrantFiled: October 16, 2018Date of Patent: November 2, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Jeremy Adam Greenberger, Lisa Seacat DeLuca
-
Patent number: 11126879Abstract: Technology described herein includes a method that includes obtaining a set of color-coded sequences, each of which includes a sequence of colors. Each color-coded sequence has auto-correlation properties characterized by a merit factor larger than a first predetermined threshold, and cross-correlation properties among the color-coded sequences characterized by a demerit factor lower than a second predetermined threshold. A color-coded sequence is randomly selected from the set of color-coded sequences. A subject is illuminated in accordance with the sequence of colors in the selected color-coded sequence. A sequence of images of the subject are captured, and are temporally synchronized with illumination by the color-coded sequence. A filtered response image is generated from the sequence of images by a matched filtering process. Based on the filtered response image, it is determined that the subject is an alternative representation of a live person. In response, access to a secure system is prevented.Type: GrantFiled: April 8, 2021Date of Patent: September 21, 2021Assignee: EyeVerify, Inc.Inventors: Spandana Vemulapalli, David Hirvonen
-
Patent number: 11127154Abstract: A method includes obtaining an image of a composite material part, each pixel of the image representing material density at a point of the part represented by that pixel; extracting from the image, for at least one fiber element of the part, a line that is representative of that element along its length; for each extracted line extending this line in width at reference points in compliance with the width of the fiber element, this extension resulting, for each reference point, in extended points; and associating an orientation with each extended point associated with a reference point, which orientation is parallel to the direction of the line at that reference point; evaluating, for a plurality of extended points, a mean orientation of the fiber elements at those points; and determining, for a plurality of orientations, a proportion of elements having those orientations from among the evaluate mean orientations.Type: GrantFiled: December 8, 2017Date of Patent: September 21, 2021Assignee: SAFRANInventors: Robin Mandel, Bastien Tranquart
-
Patent number: 11120530Abstract: An image processing apparatus includes an acquisition unit configured to acquire an image, an image processing unit configured to perform image processing on the acquired image, and an output unit configured to output the image having undergone the image processing to an output destination. The image processing unit is able to perform replacement processing for replacing colors of predetermined image portions in the acquired image with a color selected from a plurality of predetermined different colors based on the colors of the predetermined image portions. The output unit is able to output the acquired image having undergone the replacement processing to the output destination, and to output the image not having undergone the replacement processing to the output destination.Type: GrantFiled: May 11, 2018Date of Patent: September 14, 2021Assignee: Canon Kabushiki KaishaInventor: Takashi Miyauchi
-
Patent number: 11113574Abstract: A method of self-supervised learning for detection network using deep Q-network includes steps of: performing object detection on first unlabeled image through the detection network trained with training database to generate first object detection information and performing learning operation on a first state set corresponding to the first object detection information to generate a Q-value, if an action of the Q-value accepts the first unlabeled image, testing the detection network, retrained with the training database additionally containing a labeled image of the first unlabeled image, to generate a first accuracy, and if the action rejects the first unlabeled image, testing the detection network without retraining, to generate a second accuracy, and storing the first state set, the action, a reward of the first or the second accuracy, and a second state set of a second unlabeled image as transition vector, and training the deep Q-network by using the transition vector.Type: GrantFiled: March 26, 2021Date of Patent: September 7, 2021Assignee: Stradvision, Inc.Inventors: Wooju Ryu, Bongnam Kang, Hongmo Je
-
Patent number: 11100321Abstract: An information processing method including the following executed using a computer: obtaining a neural network model that solves a regression problem; obtaining input data and label data corresponding to the input data; compressing a network of the neural network model to obtain a compressed model; and changing the label data and the number of nodes in the neural network model, based on information indicating performance of the compressed model, the number of nodes being assigned to the regression problem, the information being calculated using the label data and output data which is obtained by inputting the input data to the compressed model.Type: GrantFiled: January 25, 2019Date of Patent: August 24, 2021Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICAInventors: Yohei Nakata, Yasunori Ishii
-
Patent number: 11100160Abstract: Embodiments for intelligent image note processing by a processor. One or more images associated with a user equipment (UE) may be determined to have notation data. The notation data may be extracted from the one or more images to create one or more actions in relation to the notation data.Type: GrantFiled: July 31, 2018Date of Patent: August 24, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Paul A. R. Frank, Martin G. Keen, Adam Smye-Rumsby, Hernan A. Cunico
-
Patent number: 11100310Abstract: Disclosed in embodiments of the present disclosure are an object three-dimensional detection method and apparatus, an intelligent driving control method and apparatus, a medium, and a device. The object three-dimensional detection method comprises: obtaining two-dimensional coordinates of a key point of a target object in an image to be processed; constructing a pseudo three-dimensional detection body of the target object according to the two-dimensional coordinates of the key point; obtaining depth information of the key point; and determining a three-dimensional detection body of the target object according to the depth information of the key point and the pseudo three-dimensional detection body.Type: GrantFiled: July 16, 2019Date of Patent: August 24, 2021Assignee: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.Inventors: Yingjie Cai, Xingyu Zeng, Junjie Yan, Xiaogang Wang
-
Patent number: 11098455Abstract: This disclosure relates generally to systems and methods for data acquisition and asset inspection in presence of magnetic interference. Data acquisition and assets inspection systems in many infrastructures such as railway, power line, and bridges provide inaccurate results in presence of magnetic interference. The proposed system and method proposes UAV based navigation through a dynamic correction path to inspect one or more assets in one or more infrastructures. A plurality of sensors are integrated with the UAV to acquire images of the one or more assets in presence of magnetic field. The acquired images are further processed to segment and detect anomalies in one or more parts of the one or more assets. The detected anomalies are further classified as potential anomalies and non-potential anomalies. The proposed method provides accurate results with reduced processing time.Type: GrantFiled: June 5, 2019Date of Patent: August 24, 2021Assignee: Tata Consultancy Services LimitedInventors: Sunil Dattatraya Joshi, Mayank Mishra, Vaibhav Vyawahare, Shripad Salsingikar, Jayavardhana Rama Gubbi Lakshminarasimha, Srinivas Kotamraju, Sreehari Kumar Bhogineni, Rishin Raj, Vishnu Hariharan Anand, Vishal Bajpai, Jegan Mohan Ponraj, Mahesh Rangarajan, Balamuralidhar Purushothaman, Gopi Kandaswamy
-
Patent number: 11085913Abstract: A biological sample analyzer includes: a camera 201a imaging a blood collection tube 209 containing a biological sample; an image processing section 201b and a comparative analysis section 206 that analyze the image imaged by the camera in order to extract an existence region of the biological sample; a light source 203a1, a photo sensor 203a2 and a liquid-level position detection section 203b that detect the amount of transmitted light in the blood collection tube 209 in order to detect a liquid-level position of the biological sample; and the comparative analysis section 206 that, based on the extracted existence region of the biological sample and the detected liquid-level position of the biological sample, identifies a determination target portion for a category of the biological sample, and acquires color information on the identified portion, in order to determine a category of the biological sample contained in the blood collection tube 209.Type: GrantFiled: October 10, 2017Date of Patent: August 10, 2021Assignee: HITACHI HIGH-TECH CORPORATIONInventors: Kiyotaka Sugiyama, Tatsuo Nakagawa, Iwao Suzuki, Tsukasa Suenari
-
Patent number: 11080536Abstract: An image processing device is provided with a communication device and a processor. The processor is configured to acquire a first video obtained by imaging outside scenery of a first vehicle, when the processor detects that a second vehicle appears on the first video, implement image processing that degrades visibility of a video with respect to a first image area corresponding to at least a part of the second vehicle on the first video, when the processor detects that the second vehicle appears on the first video and then a specific part of the second vehicle appears on the first video, end the image processing with respect to the first image area and implement image processing that degrades visibility of a video with respect to a second image area corresponding to the specific part of the second vehicle on the first video.Type: GrantFiled: July 31, 2019Date of Patent: August 3, 2021Assignee: Toyota Jidosha Kabushiki KaishaInventor: Kazuya Nishimura
-
Patent number: 11074695Abstract: An image processing device includes at least one memory configured to store instructions and at least one processor configured to execute the instructions to: from input subject data that include positions of a plurality of subjects, detect subject appearance data including an appearing subject and subject disappearance data including a disappearing subject; based on the subject appearance data and the subject disappearance data that are detected and an appearance position distribution and a disappearance position distribution of subjects that are learned in advance, calculate appearance validity of the subject appearance data and disappearance validity of the subject disappearance data; and based on the appearance validity and the disappearance validity calculated, acquire a combination of subject appearance data and subject disappearance data detected, the combination satisfying a predetermined condition.Type: GrantFiled: December 27, 2017Date of Patent: July 27, 2021Assignee: NEC CORPORATIONInventor: Yosuke Iwamatsu
-
Patent number: 11074448Abstract: A method for mapping 2-dimensional point of interest to a 3-dimensional view. The disclosed method includes capturing a 3-dimensional (3D) image with an augmented reality device. Matching images of a 2D image database with the captured 3D-image, the 2D image database containing 2-dimensional (2D) images associated with points of interest having a 2-dimensional (2D) data set. When the 2D-image matches the 3D image, capturing 3D-data for the matched 2D-image and converting the 2D-data set of the point-of-interest to a 3D-data set. The disclosed method simplifies the configuration of points of interest for 3D applications, such as an augmented reality device.Type: GrantFiled: October 5, 2017Date of Patent: July 27, 2021Assignee: Schneider Electric Industries SASInventors: Thierry Chiche, Romain Gassion
-
Patent number: 11074696Abstract: An image processing device includes at least one memory configured to store instructions and at least one processor configured to execute the instructions to: from input subject data that include positions of a plurality of subjects, detect subject appearance data including an appearing subject and subject disappearance data including a disappearing subject; based on the subject appearance data and the subject disappearance data that are detected and an appearance position distribution and a disappearance position distribution of subjects that are learned in advance, calculate appearance validity of the subject appearance data and disappearance validity of the subject disappearance data; and based on the appearance validity and the disappearance validity calculated, acquire a combination of subject appearance data and subject disappearance data detected, the combination satisfying a predetermined condition.Type: GrantFiled: October 15, 2019Date of Patent: July 27, 2021Assignee: NEC CORPORATIONInventor: Yosuke Iwamatsu
-
Patent number: 11073484Abstract: An image acceleration processing device including a field programmable gate array (FPGA) processing platform; and a personal computer (PC). The FPGA processing platform includes: a first fiber interface configured to receive configuration parameters and test commands, and to output test results; a second fiber interface configured to exchange data with the PC; a third fiber interface configured to receive image data and output the configuration parameters and the test commands; a fourth fiber interface configured to control the generation of a screen lighting signal; and a fifth fiber interface configured to control an input/output (IO) light source.Type: GrantFiled: April 29, 2020Date of Patent: July 27, 2021Assignee: WUHAN JINGCE ELECTRONIC GROUP CO., LTD.Inventors: Changdong Ou, Zhou Wang, Biaohua Deng, Wentian Tang, Linhai Mei, Wenzhong Dong, Bo Li, Moxiao Xu
-
Patent number: 11074733Abstract: A control circuit access a source image that includes a source face and an image to be modified that includes a face to be modified. The control circuit then employs a trained identity encoder to transform at least a part of the source image into a corresponding identity vector and then also employs an attribute encoder to form an attribute feature vector that represents characterizing information for a plurality of features of the image to be modified. The control circuit then employs an image generator to decode the attribute feature vector to obtain the characterizing information for the plurality of features of the image to be modified and to then modify the identity vector as a function of the characterizing information for the plurality of features of the image to be modified to provide a resultant image that includes a resultant face that is essentially the face of the image to be modified but with facial features that emulate corresponding facial features of the source face.Type: GrantFiled: March 15, 2019Date of Patent: July 27, 2021Assignee: Neocortext, Inc.Inventors: Oles Petriv, Nazar Shmatko