Patents Examined by Sean M Conner
-
Patent number: 11069056Abstract: Methods and apparatus for computer-aided prostate condition diagnosis are disclosed. An example computer-aided prostate condition diagnosis apparatus includes a memory to store instructions and a processor. The example processor is to execute the instructions to implement at least a prostate assessor, a lesion assessor, and an outcome generator. The example prostate assessor is to evaluate a volume and density of a prostate gland in an image of a patient to determine a prostate-specific antigen level for the prostate gland. The example lesion assessor is to analyze a lesion on the prostate gland in the image. The example outcome generator is to generate an assessment of prostate gland health based on the prostate-specific antigen level and the analysis of the lesion.Type: GrantFiled: November 20, 2018Date of Patent: July 20, 2021Assignee: General Electric CompanyInventors: Baptiste Maurice Perrin, Melodie Sperandio, Lucile Nosjean, Lorraine Jammes
-
Patent number: 11068686Abstract: Low power consumption baseline tracking systems and methods for automatically tracking a baseline input into a capacitive sensor having a plurality of transmitter electrodes and a plurality of receiver electrodes. A partial baseline scan is captured by driving all or a portion of the plurality of transmitter electrodes simultaneously and detecting receiver signals from a subset of the at least one receiver electrode simultaneously, and the partial baseline scan is compared with a stored baseline image. When a difference between the captured partial baseline scan and the stored baseline image exceeds a threshold value, a full baseline image scan is acquired, and the stored baseline image is updated.Type: GrantFiled: September 12, 2018Date of Patent: July 20, 2021Assignee: Synaptics IncorporatedInventor: Guozhong Shen
-
Patent number: 11062488Abstract: Systems and methods are provided for iterative reconstruction of a magnetic resonance image using magnetic resonance fingerprinting. An image series is estimated according to the following four steps: a gradient step to improve data consistency, fingerprint matching, spatial regularization, and a merging step. The fingerprint matching and spatial regularization steps are performed in parallel.Type: GrantFiled: November 26, 2018Date of Patent: July 13, 2021Assignee: Siemens Healthcare GmbHInventors: Simon Arberet, Boris Mailhe, Xiao Chen, Mariappan S. Nadar
-
Patent number: 11062151Abstract: A method for ascertaining a description of a lane which is in an environment of a vehicle includes ascertaining an assignment function that is set up to assign different values of a feature vector different descriptions of a lane. The method also includes ascertaining environment data of the vehicle, where the environment data includes information about a roadway marking and/or about one or more objects in the environment of the vehicle. In addition, the method includes ascertaining a current value of the feature vector on the basis of the environment data, and determining a description of the lane using the assignment function and using the current value of the feature vector.Type: GrantFiled: November 17, 2017Date of Patent: July 13, 2021Assignee: Bayerische Motoren Werke AktiengesellschaftInventors: Yusaku Yamashita, Georg Tanzmeister, Marc Hofmann
-
Patent number: 11062120Abstract: Methods and systems for high-speed filtering of candidate fingerprint images in a gallery using a non-reference-point based matching involving histograms of tokens representing minutia data. The method or system may involve detecting minutia patterns in a probe image, defining tokens that represent the minutia patterns detected in the probe image, measuring a degree of similarity between the probe image and each gallery image by comparing a probability of occurrence of a set of the tokens defined for the probe image with a probability of occurrence of the same set of tokens in that gallery image, and identifying as a candidate for a match to the probe image each gallery image for which the measured degree of similarity satisfies a criterion.Type: GrantFiled: April 28, 2020Date of Patent: July 13, 2021Assignee: AWARE, INC.Inventors: Taras P. Riopka, Siddharth K. Madan
-
Patent number: 11047806Abstract: Methods and systems for discovery of defects of interest (DOI) buried within three dimensional semiconductor structures and recipe optimization are described herein. The volume of a semiconductor wafer subject to defect discovery and verification is reduced by storing images associated with a subset of the total depth of the semiconductor structures under measurement. Image patches associated with defect locations at one or more focus planes or focus ranges are recorded. The number of optical modes under consideration is reduced based on any of a comparison of one or more measured wafer level defect signatures and one or more expected wafer level defect signatures, measured defect signal to noise ratio, and defects verified without de-processing. Furthermore, verified defects and recorded images are employed to train a nuisance filter and optimize the measurement recipe. The trained nuisance filter is applied to defect images to select the optimal optical mode for production.Type: GrantFiled: November 29, 2017Date of Patent: June 29, 2021Assignee: KLA-Tencor CorporationInventors: Santosh Bhattacharyya, Devashish Sharma, Christopher Maher, Bo Hua, Philip Measor, Robert M. Danen
-
Patent number: 11037267Abstract: Systems and methods are provided for multimedia processing. For example, an encoded file is acquired; the encoded file is parsed to obtain application-indication information and watermark-indication information associated with the encoded file; a multimedia-recording application associated with the application-indication information is called; watermark information is generated based on at least the watermark-indication information; the watermark information displayed on a recording interface of the multimedia-recording application; and in response to multimedia information being generated on the recording interface of the multimedia-recording application, the watermark information and the multimedia information is integrated.Type: GrantFiled: January 30, 2018Date of Patent: June 15, 2021Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Zhu Liang, Dali Chen, Jinkai Ouyang, Mingwei Zhang, Xian Liu, Jiachao Xian, Bohan Zhang
-
Patent number: 11037027Abstract: A computer architecture for an and-or neural network is disclosed. A computing machine accesses an input vector. The input vector comprises a numeric representation of an input to a neural network. The computing machine provides the input vector to the neural network comprising a plurality of ordered layers. The plurality of ordered layers are alternating AND-layers and OR-layers. Each of the plurality of ordered layers receives input from a preceding layer and/or provides output to a next layer. The computing machine generates an output of the neural network based on an output of a last one of the plurality of ordered layers in the neural network.Type: GrantFiled: October 25, 2018Date of Patent: June 15, 2021Assignee: Raytheon CompanyInventor: Philip A. Sallee
-
Patent number: 11006152Abstract: A method and an apparatus for decoding at least one high dynamic range picture from a coded bitstream and a method and corresponding apparatus for coding the bitstream are disclosed. A standard dynamic range picture is decoded from the coded bitstream, a set of pivot points is decoded from the coded bitstream. The set of pivot points is representative of an adjustment function fadj. A predefined color correction function bp_default is selected. An adjusted color correction function badj is determined by 1/badj [?]=fadj [?]×(1/bp_default[?]), where ? is a luminance value. The high dynamic range picture is reconstructed from the decoded standard dynamic range picture and the adjusted color correction function badj.Type: GrantFiled: April 25, 2017Date of Patent: May 11, 2021Assignee: INTERDIGITAL VC HOLDINGS, INC.Inventors: Edouard Francois, Francois Cellier, David Touze, Kangying Cai
-
Patent number: 11004207Abstract: Multiple detection techniques are used to determine whether the individual pixels in an image are background or foreground. The outputs from the multiple techniques are combined according to a confidence metric associated with each technique, which may vary from pixel to pixel. The resulting blended value for each pixel is compared with a threshold to determine whether the pixel is foreground or background.Type: GrantFiled: June 1, 2018Date of Patent: May 11, 2021Inventors: Benjamin James Sheftel, Tryon Williams
-
Patent number: 11003893Abstract: A first face region within a first image is determined. The first face region includes a location of a face within the first image. Based on the determined first face region within the first image, a predicted face region within a second image is determined. A first region of similarity within the predicted face region is determined. The first region of similarity has at least a predetermined degree of similarity to the first face region within the first image. Whether a second face region is present within the second image is determined. The location of the face within the second image is determined based on the first region of similarity, the determination of whether the second face region is present within the second image, and a face region selection rule.Type: GrantFiled: July 9, 2020Date of Patent: May 11, 2021Assignee: Advanced New Technologies Co., Ltd.Inventors: Nan Wang, Zhijun Du, Yu Zhang
-
Patent number: 10997688Abstract: An apparatus includes a memory and a circuit. The memory may be configured to store data. The circuit may be configured to analyze a warp field and, in a first read mode, (i) generate a first read request for fetching one or more rectangular regions of an input array containing data from the memory, (ii) generate one or more tags defining how the data of the one or more rectangular regions returned by the memory are to be stored in one or more local buffers, and (iii) generate an output array by filtering the data stored in the one or more local buffers with the warp field.Type: GrantFiled: March 9, 2020Date of Patent: May 4, 2021Assignee: Ambarella International LPInventor: Beng-Han Lui
-
Patent number: 10977755Abstract: A computer-implemented screening method, system, and computer program product including detecting at least two disassembled components of an object spread across multiple sensor scan images of at least one container, storing a record of each disassembled component correlated with contextual information of each owner of each container corresponding to a sensor scan image, and flagging the owner of the container in the sensor scan image based on a joint assessment of the sensor scan image including a disassembled component that can be combined with another disassembled component in a different sensor scan image to assemble the object and the contextual information of each owner.Type: GrantFiled: November 21, 2017Date of Patent: April 13, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mani Abedini, Rajib Chakravorty, Rahil Garnavi, Zongyuan Ge
-
Patent number: 10970839Abstract: A method for analyzing a quality of an orthodontic aligner is described. The method includes receiving, by a processor, a digital representation of a fabricated orthodontic aligner, the digital representation having been generated based on imaging of the fabricated orthodontic aligner. The method further includes analyzing, by the processor, the digital representation of the fabricated orthodontic aligner to identify a quality-related property of the fabricated orthodontic aligner. The method further includes determining, based on the quality-related property, that the fabricated orthodontic aligner comprises a manufacturing flaw. The method further includes classifying, by the processor, the fabricated orthodontic aligner as requiring further inspection by a technician based on determining that the fabricated orthodontic aligner comprises the manufacturing flaw.Type: GrantFiled: July 23, 2020Date of Patent: April 6, 2021Assignee: Align Technology, Inc.Inventors: Anatoliy Parpara, Ivan Kharpalev, Stephan Albert Alexandre Dumothier, Andrey Cherkas, Alexey Kalinichenko, Jack Shaw, Israel Velazquez
-
Patent number: 10957033Abstract: Repeater defects on a wafer can be detected by fusing multiple die images. In an instance, multiple die images are statistically fused to form a die-fused image. Each of the die images can be of a different die on a wafer. A presence of a repeater defect is detected in the die-fused image. The die images can be generated using a laser-scanning system or other systems.Type: GrantFiled: September 14, 2017Date of Patent: March 23, 2021Assignee: KLA-Tencor CorporationInventors: Premchandra M. Shankar, Ashok Varadarajan, JuHwan Rha
-
Patent number: 10957062Abstract: In various embodiments, techniques are provided for photogrammetric 3D model reconstruction that modify the optimization performed in bundle adjustment operations of an automatic SfM stage to apply a depth-aware weighting to reprojection error of each 3D point used in the optimization. The reprojection error of each 3D point may be weighted based on a function of distance, density of a cluster, or a combination of distance and density. A loss function may be scaled to account for the weighting, and normalizations applied. Such weighting may force consideration of 3D points on an object of interest in the foreground and improve convergence of the optimization to global optima. In such manner, accurate and complete 3D models may be reconstructed of even ill-textured or very thin objects in the foreground of a scene with a highly textured background, while not consuming excessive processing and storage resources or requiring tedious workflows.Type: GrantFiled: January 3, 2019Date of Patent: March 23, 2021Assignee: Bentley Systems, IncorporatedInventor: Nicolas Gros
-
Patent number: 10956769Abstract: Disclosed herein are computer-implemented methods, computer-implemented systems, and non-transitory, computer-readable media for evaluating performance of an object detection model. One computer-implemented method includes generating a predicted bounding box representing an object based on the object detection model, where the object is positioned proximate to one or more adjacent objects. An area of intersection is determined between the predicted bounding box and a groundtruth bounding box of the object. A modified area of union is determined between the predicted bounding box and the groundtruth bounding box of the object. A score equal to the area of intersection between the predicted bounding box and the groundtruth bounding box of the object divided by the modified area of union is determined, where the score represents the performance of the object detection model.Type: GrantFiled: July 31, 2020Date of Patent: March 23, 2021Assignee: Advanced New Technologies Co., Ltd.Inventor: Jiangbo Huang
-
Patent number: 10943138Abstract: Exemplary embodiments are directed to biometric analysis systems generally including one or more illumination sources, a camera, and an analysis module. The illumination sources are configured to illuminate at least a portion of a face of a subject. The camera is configured to capture one or more images of the subject during illumination of the face of the subject. The analysis module is configured to analyze the one or more images captured by the camera to determine an indication of liveliness of the subject and prevent spoofing.Type: GrantFiled: July 27, 2017Date of Patent: March 9, 2021Assignee: Princeton Identity, Inc.Inventors: David Alan Ackerman, Andrew James Bohl, Christopher Robert Martin
-
Patent number: 10916005Abstract: Systems, methods, and related technologies for automated inspection are described. In certain aspects, one or more images of a reference part can be captured and the one or more images of the reference part can be processed to generate an inspection model of the reference part. One or more regions of the inspection model can be associated with one or more analysis parameters. An inspection plan can be generated based on the inspection model and the one or more analysis parameters. Based on the inspection plan, one or more images of a part to be inspected can be captured and the one or more images of the part can be processed in relation to the analysis parameters to compute one or more determinations with respect to the part. One or more outputs can be providing based on the one or more determinations.Type: GrantFiled: November 24, 2015Date of Patent: February 9, 2021Assignee: Kitov Systems LtdInventors: Nir Avrahami, Joseph Rubner
-
Patent number: 10916001Abstract: Methods and systems are provided for transforming sketches into stylized electronic paintings. A neural network system is trained where the training includes training a first neural network that converts input sketches into output images and training a second neural network that converts images into output paintings. Similarity for the first neural network is evaluated between the output image and a reference image and similarity for the second neural network is evaluated between the output painting, the output image, and a reference painting. The neural network system is modified based on the evaluated similarity. The trained neural network is used to generate an output painting from an input sketch where the output painting maintains features from the input sketch utilizing an extrapolated intermediate image and reflects a designated style from the reference painting.Type: GrantFiled: March 13, 2017Date of Patent: February 9, 2021Assignee: ADOBE INC.Inventors: Jingwan Lu, Patsorn Sangkloy, Chen Fang