Patents Examined by Shefali D Goradia
-
Patent number: 12783798Abstract: An identification system and an identification method are provided. The identification system includes a storage device and a processor. The storage device stores an identification module. The identification module includes a text encoder, a computing module, and an attentive pairwise interaction network model. The processor is coupled to the storage device and executes the identification module. The processor inputs the input data to the identification module, so that the identification module generates output data according to the input data. The input data is one of text data and picture data, and the output data is the other one of text data and picture data. Encoding data output by the text encoder or the attentive pairwise interaction network model is used as the input data of the computing module. The computing module generates output data according to the input data.Type: GrantFiled: May 15, 2024Date of Patent: November 3, 2026Assignee: VIA Technologies, Inc.Inventor: Cheng Yu Wen
-
Patent number: 12783598Abstract: The present disclosure relates to a computer-implemented method for r configuration of a sensor system, said method (500) comprising providing (510,520), for a training dataset X consisting of at least one data element Xi, for a measurement of the sensor system (200) relating to an initial set-up of the sensor system (200), a dictionary D forming a signal model comprising at least one basis function and at least one set of sparse coefficients S. Each set of sparse coefficients Si and the dictionary D represents one of the data elements Xi of said training dataset X. Determining (530) an optimal sub-sampling operator ? based on the dictionary D and said at least one set of sparse coefficients S, wherein the optimal sub-sampling operator ? is a selection of a true subset of the sample positions of the training dataset X, wherein the true subset corresponds to the sample positions containing the most important samples of the training dataset X.Type: GrantFiled: January 10, 2024Date of Patent: November 3, 2026Assignee: Sparsit ABInventors: Ehsan Miandji, Saghi Hajisharif, Jonas Unger
-
Patent number: 12784187Abstract: A diagnostic support program that is possible to display a movement of an organ is provided. A diagnostic support program that analyzes images of an organ of a human and displays analysis results, the program causing a computer to execute a process comprising: processing of acquiring a plurality of frame images, processing of calculating a cyclic change that characterizes a state of an organ between each of the frame images, processing of Fourier-transforming the cyclic change that characterizes the state of the organ, processing of extracting a spectrum in a fixed band including a spectrum corresponding to a frequency of a movement of an organ out of a spectrum obtained after the Fourier-transforming, processing of performing inverse Fourier transform on the spectrum extracted from the fixed band, and processing of outputting each of the images after performing the inverse Fourier transform, is provided.Type: GrantFiled: July 6, 2020Date of Patent: November 3, 2026Assignees: RADWISP PTE. LTD., MEDIOTT CO., LTD.Inventors: Takehiko Abe, Norifumi Yoshida
-
Patent number: 12776135Abstract: The present disclosure is directed to methods of machine-learning for on-the-fly adaptation of a predictive model configured for image processing. The method includes providing a first predictive model to provide first prediction task, providing a second predictive model to provide a second prediction task, the second predictive model including one or more parameters, the second prediction task being derivable from the first prediction task, providing context-based images from a first stream of images obtained from an optical sensor to both the first and the second predictive models, each image provided on-the-fly, and performing an on-the-fly adaptation for the second predictive model, the on-the-fly adaptation comprising, for each provided image: performing a respective first prediction by the first predictive model and a respective second prediction by the second predictive model, computing a cost function, and updating the one or more parameters of the second predictive model based on the cost function.Type: GrantFiled: March 11, 2022Date of Patent: October 27, 2026Assignee: DatakalabInventors: Arnaud Dapogny, Kevin Bailly, Lucas Fischer, Lucas Lugao Guimaraes
-
Patent number: 12755578Abstract: Provided is an information processing device that includes a first emotion estimation section that generates first emotion data by estimating emotion of a user based on a result of detection made by a first sensing section that detects a behavior of the user, the behavior being used for communication, and a second emotion estimation section that generates second emotion data by estimating emotion of the user based on a result of detection made by a second sensing section that detects a movement or response of the user, the movement or response not being used for communication. The information processing device further includes an emotion data generation section that determines ratios for the first emotion data and the second emotion data, and generates third emotion data by combining the first emotion data and the second emotion data based on ratios, and a communication section that transmits the third emotion data.Type: GrantFiled: September 7, 2022Date of Patent: October 6, 2026Assignee: SONY GROUP CORPORATIONInventor: Kiyoshi Yoshikawa
-
Patent number: 12755421Abstract: Systems, methods, and other embodiments described herein relate improve the estimation of poses within an environment including multiple people and uncalibrated cameras. In one embodiment, a method includes acquiring sensor data including images with depth information of a surrounding environment that includes multiple people. The method includes determining 2D poses and 3D features for the people according to the sensor data. The method includes generating camera poses using at least the depth information and the features for cameras that generated the images. The method includes generating 3D poses for the people according to the camera poses and the 3D features. The method includes providing the 3D poses of the people.Type: GrantFiled: November 8, 2023Date of Patent: October 6, 2026Assignees: DENSO INTERNATIONAL AMERICA INC., DENSO CORPORATION, CARNEGIE MELLON UNIVERSITYInventors: Jinhyung Park, Yu-Jhe Li, Rawal Khirodkar, Kris Kitani, Shawn Hunt
-
Patent number: 12749191Abstract: Methods and systems for predicting visual acuity response are provided. The methods and systems utilize one or more of a first input that includes two-dimensional imaging data and a second input that includes three-dimensional imaging data. A visual acuity response (VAR) output is predicted, via a neural network system, using the first input and/or the second input. The VAR output comprises a predicted change in visual acuity of a subject undergoing a treatment.Type: GrantFiled: June 2, 2023Date of Patent: September 29, 2026Assignee: HOFFMANN-LA ROCHE INC.Inventor: Jelena Novosel
-
Patent number: 12743736Abstract: Techniques are described herein for training a generative model to detect feature-level relationships across portions of an article representing a resource transfer. The method receives first and second images of respective areas containing user-defined features, supplies the images to a generative model that produces embeddings, and forms a combined embedding. A vector distance metric is computed by comparing the combined embedding to prior embeddings stored in a datastore. Based on whether the metric exceeds a threshold, a training label indicating match or mismatch is generated. The label is assigned a sample weight that varies with the age of the prior article that produced the compared prior embedding. The generative model is then trained by adjusting weights to reduce error between a generated output and the training label, yielding a trained model.Type: GrantFiled: December 10, 2025Date of Patent: September 22, 2026Assignee: The Huntington National BankInventors: Stephen James Hageman, Jonathan Murphy
-
Patent number: 12744870Abstract: System and techniques for adaptive color transformation to aid computer vision are described herein. Colors from an image are mapped into a multi-dimensional space to create a distribution of colors in the image. A dimension of the multi-dimensional space can correspond to a color characteristic. An array of condensed representations of the distribution of colors can be generated. Each condensed representation of the array can be generated by rotating the distribution of colors by a respective color angle about an axis perpendicular to the multi-dimensional space. Algorithms can determine which condensed representation is of a highest quality within the array. Here the highest quality can be determined based on signal energy calculated for each condensed representation. The colors in the image can be transformed into a reduced image using the color angle corresponding to the selected condensed representation. The reduced image can be transmitted to receiver circuitry of an agricultural vehicle.Type: GrantFiled: December 29, 2023Date of Patent: September 22, 2026Assignee: Raven Industries, Inc.Inventors: David Alan Rislov, Robert John Vaselaar
-
Patent number: 12734616Abstract: A method for quality control of a welding joint between a pair of ends of conducting elements of an inductive winding of a stator, the method being performed by a computer and comprising the steps of: acquiring a 3D reconstruction of the welding joint; extracting a plurality of 2D grayscale blob areas from the 3D reconstruction of the welding joint; converting the plurality of 2D grayscale blob areas to a function of 2D grayscale blob areas which depends on a distance from a peak of the welding joint with respect to each 2D grayscale blob area; calculating a respective first derivative of the function of 2D grayscale blob areas; calculating a respective second derivative of the function of 2D grayscale blob areas; and seeking instability peaks in a trend of the second derivative of the function of 2D grayscale blob areas.Type: GrantFiled: March 7, 2023Date of Patent: September 15, 2026Assignee: ATOP S.P.A.Inventors: Massimiliano Giachi, Emanuele Angelini
-
Patent number: 12738003Abstract: An information processing apparatus includes an acquisition unit that acquires a first image through imaging, a determination unit that determines whether a predetermined object is included in the first image acquired by the acquisition unit based on a model that has learned the predetermined object, and a selection unit that selects a second image from among images determined by the determination unit as including the predetermined object, and executes relearning of the model by using the selected second image.Type: GrantFiled: February 21, 2022Date of Patent: September 15, 2026Assignee: Sony Semiconductor Solutions CorporationInventor: Hareesh Jagadeesh
-
Patent number: 12737892Abstract: The systems and methods described herein provide for an automated photosensitivity detection system (PDS) configured to automatically execute processes for flash detection and pattern detection of a video. PDS outputs an analysis result for each type of pattern detection analysis for the video. The PDS can execute each type of pattern detection analysis independently of the other pattern detection processes. Each pattern detection process is a distinct process that can be calculated without reference to the other processes. The final analysis result can aggregate the results of each detection process executed by the PDS.Type: GrantFiled: March 29, 2024Date of Patent: September 15, 2026Assignee: Electronic Arts Inc.Inventors: Blanca Macazaga Zuazo, Alessandro Lentini, Angela Stockinger
-
Patent number: 12718511Abstract: An area including an object is detected from an input image with high accuracy. An information processing apparatus of the present disclosure includes: a first detection unit that performs detection processing of detecting an area including an object with respect to an input image; an identification unit that calculates a feature vector on the basis of an image of an area detected in the detection processing, identifies the object on the basis of the feature vector, and acquires identification reliability that is reliability of an identification result of the object; and a learning unit that selects a detection area for learning from a plurality of detection areas corresponding to a plurality of the feature vector on the basis of a plurality of the identification reliability, and learns a model that detects an area including the object on the basis of an image of the detection area selected.Type: GrantFiled: March 29, 2022Date of Patent: August 25, 2026Assignee: SONY GROUP CORPORATIONInventors: Yuki Yamamoto, Tokuhiro Nishikawa
-
Patent number: 12711655Abstract: A system generates applications based on a domain specific language (DSL). The applications allow a user to take measurements based on user movements using a client device (for example, a mobile phone) for providing to an expert. The domain specific language includes commands that cause the generated applications to perform various tasks, such as providing specific instructions to the user, starting and stopping recording, taking measurements, and so on. The system compiles the DSL specification to generate executable instructions that are deployed (for example, on a client device such as a mobile phone). The DSL specification allows users to specify virtual points based on multiple landmarks obtained from the images of the user. The DSL specification allows users to specify a point as a stable point for landmarks that are expected to be stationary but move across frames.Type: GrantFiled: June 1, 2023Date of Patent: August 18, 2026Assignee: Omada Health, Inc.Inventors: Alexander Floyd Prinsen, Arvind Menon, Shane Patrick Ahern, Brandon Piechowski
-
Patent number: 12707086Abstract: A three-dimensional data decoding method includes: selecting, from among contexts, a first context for an encoded first information item to be processed; and arithmetic-decoding the encoded first information item to be processed, using the first context, to generate a first information item to be processed. Encoded first information items including the encoded first information item to be processed are included in a bitstream generated by encoding an information item about positions of three-dimensional points. The encoded first information items are generated by arithmetic-encoding first information items including the first information item to be processed. The first information items each correspond to a different one of reference positions and indicate whether a three-dimensional point corresponding to a reference position corresponding to the first information item is present.Type: GrantFiled: November 29, 2023Date of Patent: August 11, 2026Assignee: PANASONIC INTELLECTUAL PROPERTY CORPORATION OF AMERICAInventors: Takahiro Nishi, Toshiyasu Sugio, Noritaka Iguchi
-
Patent number: 12705786Abstract: The present disclosure is related to imaging systems and methods. The method includes obtaining optical image data of a subject to be scanned by a medical device. The method includes determining a scan range of the subject based on the optical image data. The scan range includes at least one scan area of the subject. The method includes determining at least one parameter value of at least one scan parameter based on the at least one scan area of the subject. The method further includes causing the medical device to scan the subject based on the scan range and the at least one parameter value of the at least one scan parameter.Type: GrantFiled: June 12, 2023Date of Patent: August 11, 2026Assignee: SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD.Inventors: Shitao Liu, Jinlong Li
-
Patent number: 12694559Abstract: Systems and methods for estimating optimal gantry orientation and/or scanning parameters using image(s) from one or several cameras for a CT scan of a patient. Images are acquired of a patient. An optimal gantry tilt is estimated that keeps the patient's eye lenses outside a range of a beam during the scan. The CT scan is performed using the optimal gantry tilt. A scout scan is not used.Type: GrantFiled: February 9, 2023Date of Patent: July 28, 2026Assignee: Siemens Healthineers AGInventors: Brian Teixeira, Vivek Singh, Ankur Kapoor, Andreas Prokein
-
Patent number: 12688613Abstract: An imaging chamber configured to receive a flow of a fluid sample is provided. The imaging chamber includes a reservoir and an imaging window. The reservoir includes a contrast-enhancing agent and is configured to receive the flow of the fluid sample. The imaging window of the imaging chamber is downstream from the reservoir.Type: GrantFiled: March 1, 2023Date of Patent: July 21, 2026Assignee: HONEYWELL INTERNATIONAL INC.Inventors: Andy Walker Brown, Ronald W. Myers, Daniel Yee
-
Patent number: 12688688Abstract: An image processing apparatus configured to perform recognition processing for a target object in an input image, includes at least one memory storing a program, and at least one processor. The processor, by executing the program, causes the image processing apparatus to perform the recognition processing for the target object in a first image having a first resolution acquired based on the input image and acquire a first recognition result, determine whether or not a reliability of the first recognition result satisfies a predetermined standard, and perform the recognition processing for the target object in a second image which has a higher resolution than the first resolution acquired based on the input image, and acquire a second recognition result, in a case where it is determined that the reliability of the first recognition result does not satisfy the predetermined standard.Type: GrantFiled: January 25, 2023Date of Patent: July 21, 2026Assignee: CANON KABUSHIKI KAISHAInventors: Yuta Narukiyo, Takahiro Kuroyama
-
Patent number: 12675886Abstract: Systems and methods are provided to perform measurements of vibratory motion in three axes using two or more cameras. The cameras are mounted in a fixed spatial relationship to each other and are calibrated such that internal camera distortion and external camera coordinate transformations are determined. Data from each pair of cameras can be processed independently to determine the z-axis motion from changes in the x-axis and y-axis motion measured by the cameras. Measurement noise can impact the small differences in values from camera pairs and multiple techniques have been identified to reduce noise and make reliable measurements of the z-axis vibratory motion. If more than two cameras are utilized, then the data from each pair can be averaged to improve the measured values.Type: GrantFiled: November 8, 2023Date of Patent: July 7, 2026Assignee: RDI TECHNOLOGIES, INC.Inventors: Kenneth Ralph Piety, Jeffrey R. Hay, Mark William Slemp, Douglas A. Mann