Patents Examined by Jianxun Yang
-
Patent number: 11551445Abstract: An electronic apparatus and method for heatmap visualization of object detections is provided. The electronic apparatus inputs an image frame including an object of interest to Deep Neural Network (DNN) model and extracts an object detection result associated with the object of interest as output of the DNN model for the input image frame. The object detection result includes bounding box coordinates for the object of interest. The electronic apparatus segments the input image frame into a plurality of image portions based on the bounding box coordinates and determines, for each of the plurality of image portions, a weight value indicative of a likelihood that a corresponding image portion belongs to the object of interest. The electronic apparatus generates, based on the determined weight value, a visualization frame which includes heatmap visualization of a region that is included in the image frame and is bounded by the bounding box coordinates.Type: GrantFiled: August 14, 2020Date of Patent: January 10, 2023Assignee: SONY CORPORATIONInventors: Abhishake Jha, Shehnaz Mohamed
-
Patent number: 11539831Abstract: A wearable device that communicates with a host device can be used to initiate a communication functionality of the host device (e.g., telephone calls, text messages). The wearable device can obtain user input indicating a recipient of the communication and in some instances content for the communication and can provide an instruction to the host device. The host device can use the indicated recipient and content to initiate communication and where applicable to send the content. Recipients and/or content can be selected from predefined lists available on the wearable device.Type: GrantFiled: November 11, 2019Date of Patent: December 27, 2022Assignee: Apple Inc.Inventor: Nikhil M. Bhatt
-
Patent number: 11538234Abstract: Information about a drug-containing vessel is determined by capturing image data of the curved surface of a cylindrical portion of a drug-containing vessel. The image data is unfurled from around the curved surface, binarised, and a template matching algorithm employed to determine that the label information comprises candidate information about the vessel and/or the drug.Type: GrantFiled: May 3, 2018Date of Patent: December 27, 2022Assignee: Ares Trading S.A.Inventors: Robert Jones, Robert F. Marchington, David Rimmer, Bogdan-Alexandru Cociu, William D. Addison, Matthew J. Hayes, Ruairi Duffy, Quentin Le Masne
-
Patent number: 11531851Abstract: Computational algorithms integrate and analyze data to consider multiple interdependent, heterogeneous sources and forms of patient data, and using a classification model, provide new learning paradigms, including privileged learning and learning with uncertain clinical data, to determine patient status for conditions such as acute respiratory distress syndrome (ARDS) or non-ARDS.Type: GrantFiled: February 5, 2020Date of Patent: December 20, 2022Assignee: THE REGENTS OF THE UNIVERSITY OF MICHIGANInventors: Kayvan Najarian, Jonathan Gryak, Elyas Sabeti, Joshua Drews
-
Patent number: 11527019Abstract: One or more multi-stage optimization iterations are performed with respect to a compression algorithm. A given iteration comprises a first stage in which hyper-parameters of a perceptual quality algorithm are tuned independently of the compression algorithm. A second stage of the iteration comprises tuning hyper-parameters of the compression algorithm using a set of perceptual quality scores generated by the tuned perceptual quality algorithm. The final stage of the iteration comprises performing a compression quality evaluation test on the tuned compression algorithm.Type: GrantFiled: May 15, 2020Date of Patent: December 13, 2022Assignee: Amazon Technologies, Inc.Inventors: Luitpold Staudigl, Thomas Sydney Austin Wallis, Mike Mueller, Muhammad Bilal Javed, Pablo Barbachano
-
Patent number: 11525202Abstract: Disclosed is an artificial intelligence (AI)-based self-control air conditioner. The AI-based self-control air conditioner includes a communication unit configured to receive an image including member data for identifying the member from an image acquisition apparatus corresponding to a group including at least one member, and a processor configured to recognize the member data from the received image, to acquire operation data including an operation condition of an air conditioner, which is desired by the member, based on the recognized data, to store member information including the member data and the operation data in a database, and to acquire and analyze the operation condition of the air conditioner, which is desired by the member, with respect to at least one member from a plurality of pieces of member information corresponding to the group stored in the database, wherein the air conditioner is autonomously driven according to control of the processor.Type: GrantFiled: June 28, 2019Date of Patent: December 13, 2022Assignee: LG ELECTRONICS INC.Inventors: Jooseong Lee, Taeyup Song, Dayun Han
-
Patent number: 11521400Abstract: A method for identifying a logo within at least one image includes identifying an area containing the logo within the at least one image, extracting logo features from the area by analyzing image gradient vectors associated with the at least one image, and using a machine learning model to identify the logo from the extracted logo features, wherein the machine learning model is trained to identify at least one target logo based on a received image data containing the logo features.Type: GrantFiled: December 6, 2019Date of Patent: December 6, 2022Assignee: SYNAMEDIA LIMITEDInventors: Amit Chhabra, Sandipan Bhattacharjee, Sonu Mariam George
-
Patent number: 11513081Abstract: A substrate inspection method in a substrate treatment system including a plurality of treatment apparatuses each performing a predetermined treatment on a substrate, includes: imaging a surface of a substrate before being treated in the treatment apparatuses to acquire a first substrate image; extracting a predetermined feature amount from the first substrate image; selecting an inspection recipe corresponding to the feature amount extracted from the first substrate image, from a storage unit in which a plurality of inspection recipes each set corresponding to the feature amount in a different range are stored; imaging the surface of the substrate after being treated in the treatment apparatuses to acquire a second substrate image; and determining presence or absence of a defect of the substrate, based on the selected inspection recipe and the second substrate image.Type: GrantFiled: November 20, 2019Date of Patent: November 29, 2022Assignee: Tokyo Electron LimitedInventors: Takuya Mori, Makoto Hayakawa
-
Patent number: 11516411Abstract: Disclosed are an image processing method and apparatus, an electronic device and a computer-readable storage medium. The method comprises: acquiring a video image; when a preset target is detected in the video image, superimposing a foreground sticker on a target image corresponding to the preset target; and when a preset action of the preset target in the video image is detected, generating a screen special effect, in the embodiments of the present disclosure, a video image is acquired, when a preset target is detected in the video image, a foreground sticker is superimposed on a target image corresponding to the preset target, and when a preset action of the preset target in the video image is detected, a screen special effect is generated, such that a screen special effect for the preset action of the preset target can be realized.Type: GrantFiled: February 15, 2022Date of Patent: November 29, 2022Assignee: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD.Inventor: Jingye Wang
-
Patent number: 11509918Abstract: A semiconductor device and electronic device with reduced power consumption are provided. The semiconductor device includes an encoder, a decoder, and a source driver circuit. An output terminal of the encoder is electrically connected to an input terminal of the source driver circuit, and an output terminal of the source driver circuit is electrically connected to an input terminal of the decoder. The encoder converts input image data into feature-extracted image data, and the decoder restores the feature-extracted image data to the original image data. In addition, provision of a circuit that performs convolution processing using a weight filter for the encoder enables calculation using a convolutional neural network.Type: GrantFiled: January 16, 2018Date of Patent: November 22, 2022Assignee: SEMICONDUCTOR ENERGY LABORATORY CO., LTD.Inventor: Yoshiyuki Kurokawa
-
Patent number: 11488308Abstract: A three-dimensional object detection method includes: extracting a target in a two-dimensional image by a pre-trained deep convolutional neural network to obtain a plurality of target objects; determining a point cloud frustum in a corresponding three-dimensional point cloud space based on each target object; segmenting the point cloud in the frustum based on a point cloud segmentation network to obtain a point cloud of interest; and estimating parameters of a 3D box in the point cloud of interest based on a network with the weighted channel features to obtain the parameters of the 3D box for three-dimensional object detection. According to the present invention, the features of the image can be learned more accurately by the deep convolutional neural network and the parameters of the 3D box in the point cloud of interest are estimated based on the network with the weighted channel features.Type: GrantFiled: April 19, 2019Date of Patent: November 1, 2022Assignee: INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCESInventors: Xin Zhao, Kaiqi Huang, Zhe Liu
-
Patent number: 11481578Abstract: A deep learning model and dimensionality reduction are applied to each of a plurality of records of physiological information to derive a plurality of feature vectors. A similarities algorithm is applied to the plurality of feature vectors to form a plurality of clusters, each including a set of feature vectors. An output comprising information that enables a display of one or more of the plurality of clusters is provided, and a mechanism for selecting at least one feature vector within a selected cluster of the plurality of clusters is enabled. Upon selection of a feature vector, an output comprising information that enables a display of the record of physiological information corresponding to the selected feature vector is provided, and a mechanism for assigning a label to the displayed record is enabled. The assigned label is then automatically assigned to the records corresponding to the remaining feature vectors in the selected cluster.Type: GrantFiled: February 20, 2020Date of Patent: October 25, 2022Assignee: NeuroPace, Inc.Inventors: Sharanya Arcot Desai, Thomas K. Tcheng, Benjamin E. Shanahan
-
Patent number: 11475655Abstract: A method is provided for Optical Character Recognition (OCR). A plurality of OCR decoding results each having a plurality of positions is obtained from capturing and decoding a plurality of images of the same one or more OCR characters. A recognized character in each OCR decoding result is compared with the recognized character that occupies an identical position in each of the other OCR decoding results. A number of occurrences that each particular recognized character occupies the identical position in the plurality of OCR decoding results is calculated. An individual confidence score is assigned to each particular recognized character based on the number of occurrences, with a highest individual confidence score assigned to a particular recognized character having the greatest number of occurrences.Type: GrantFiled: April 10, 2020Date of Patent: October 18, 2022Assignee: DATAMAX-O'NEIL CORPORATIONInventor: H. Sprague Ackley
-
Patent number: 11466976Abstract: In a method and system for measuring a height map of a surface of an object, the following steps are carried out. Height maps of different sections of the surface of the object are measured, using an optical profilometer having a field of view covering an individual section, wherein each height map comprises height data. The measured height maps are grouped into different sets of height maps, wherein within each set each one of the height maps of the set has a valid overlap to at least one other height map of the set, and wherein each height map belongs to one set and does not have a valid overlap with any height map of another set. Within each set, the measured height maps are stitched to a sub-composite stitched height map. The sub-composite stitched height maps are combined to a composite height map.Type: GrantFiled: January 15, 2019Date of Patent: October 11, 2022Assignee: MITUTOYO CORPORATIONInventor: Johannes Anna Quaedackers
-
Patent number: 11461594Abstract: Discussed herein are devices, systems, and methods for disentangling static and dynamic features of content. A method can include encoding by a transform disentangling autoencoder (AE), first content to generate first static features and first dynamic features and second content to generate second static features and second dynamic features, and constructing, by the AE, third content based on a combination of third static features and the first dynamic features and fourth content based on a combination of fourth static features and the second dynamic features, the third and fourth static features being determined based on the first static features and the second static features.Type: GrantFiled: March 23, 2020Date of Patent: October 4, 2022Assignee: Raytheon CompanyInventor: Philip A. Sallee
-
Patent number: 11461581Abstract: Disclosed is system and method of connection information regularization, graph feature extraction and graph classification based on adjacency matrix. By concentrating the connection information elements in the adjacency matrix into a specific diagonal region of the adjacency matrix in order to reduce the non-connection information elements in advance. The subgraph structure of the graph is further extracted along the diagonal direction using the filter matrix. Then a stacked convolutional neural network is used to extract a larger subgraph structure. On the one hand, it greatly reduces the amount of computation and complexity, solving the limitations of the computational complexity and the limitations of window size. And on the other hand, it can capture large subgraph structure through a small window, as well as deep features from the implicit correlation structures at both vertex and edge level, which improves the accuracy and speed of the graph classification.Type: GrantFiled: December 26, 2019Date of Patent: October 4, 2022Assignee: ZHEJIANG UNIVERSITYInventors: Zhiling Luo, Jianwei Yin, Zhaohui Wu, Shuiguang Deng, Ying Li, Jian Wu
-
Patent number: 11457417Abstract: A method and related apparatus for transferring data between a mobile communication unit and a plurality of access points, wherein each of said plurality of access points and said mobile communication unit is provided with a transceiver, said mobile communication unit being arranged to travel a predetermined route, the method comprising: adjusting transmission power of at least the transceiver of the mobile communication unit substantially to a maximum level; and attenuating transmission signal of each transceiver such that signal level of a received signal in a transmission between the mobile communication unit and each of the access points is more optimal, wherein the level of attenuation is set constant at least in the mobile communication unit.Type: GrantFiled: June 11, 2015Date of Patent: September 27, 2022Assignee: Teleste OyjInventors: Jani Vare, Kari Virtanen
-
Patent number: 11450126Abstract: Described herein is a computer-implemented method for automatic extraction of canonical data from an electronic document. The method comprises classifying a first text rectangle in an electronic document as a label and a second text rectangle as a value using a first machine learning algorithm. A first probability score of a likelihood of the first text rectangle corresponding to a first canonical category is determined using a second machine learning algorithm. A second probability score of a likelihood of the second text rectangle corresponding to a first canonical category is determined using a third machine learning algorithm. A relative spatial position of the second text rectangle relative to the first text rectangle is calculated. Based on the relative spatial position, the first probability score, and the second probability score, the first text rectangle, and the second text rectangle are classified into the first canonical category.Type: GrantFiled: March 30, 2020Date of Patent: September 20, 2022Assignee: COUPA SOFTWARE INCORPORATEDInventors: Hongyang Yu, Hanieh Borhanazad, Mark Oliver Burch
-
Patent number: 11446487Abstract: System and methods for determining placement of a transducer array relative to a subject's head, which may be used in treating cancer in the subject, are provided. These techniques may include constructing, based on one or more images, a representation of the subject's head that includes information for a plurality of structures including one or more tumors positioned within the subject's brain. The representation of the subject's head may be used to calculate electric field propagation for one or more arrangements of a transducer array on a surface of the subject's head. These techniques may further include determining one or more rate of energy absorption distributions and/or one or more electric field distributions using the calculated electric field propagation for multiple arrangements of the transducer array. A rate of energy absorption distribution may indicate a rate of energy absorbed at the one or more tumors.Type: GrantFiled: September 22, 2017Date of Patent: September 20, 2022Assignee: Beth Israel Deaconess Medical Center, Inc.Inventors: Eric Wong, Edwin Lok
-
Patent number: 11443133Abstract: A system for analog gauge monitoring uses a machine learning model for computer vision that is trained using synthetic training data generated based on one or a few images of the gauge being monitored and a geometric model describing the scale and the indicator of the gauge. In some embodiments, the synthetic training data is generated using an image model implemented as a generative adversarial network (GAN) type neural network and trained to modify an image of a given gauge such that the gauge face is preserved while the gauge indicator is added to or removed from the image of the given gauge for any given gauge.Type: GrantFiled: December 10, 2019Date of Patent: September 13, 2022Assignee: RICOH COMPANY, LTD.Inventor: Edward L. Schwartz