Patents Examined by Gregory M. Desire
-
Patent number: 11829854Abstract: A system and methods are disclosed for using a trained machine learning model to identify constituent images within composite images. A method may include providing pixel data of a first image as input to the trained machine learning model, obtaining one or more outputs from the trained machine learning model, and extracting, from the one or more outputs, an indication that the first image is a composite image that includes a constituent image, wherein at least a portion of the constituent image is in a spatial area of the first image.Type: GrantFiled: August 16, 2021Date of Patent: November 28, 2023Assignee: Google LLCInventors: Filip Pavetic, King Hong Thomas Leung, Dmitrii Tochilkin
-
Patent number: 11823471Abstract: According to implementations of the subject matter described herein, there is provided a solution for text recognition in an image. In this solution, a target text line area, which is expected to include a text to be recognized, is determined from an image. Probability distribution information of a character model element(s) present in the target text line area is determined using a single character model. The single character model is trained based on training text line areas and respective ground-truth texts in the training text line areas. Texts in the training text line areas are arranged in different orientations, and/or the ground-truth texts comprise texts are related to various languages (e.g., texts related to a Latin and an Eastern languages). The text in the target text line area can be determined based on the determined probability distribution information. The single character model enables more efficient and convenient text recognition.Type: GrantFiled: January 20, 2021Date of Patent: November 21, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Wenping Hu, Qiang Huo
-
Patent number: 11823351Abstract: An image processing method includes receiving an input image and a guide image corresponding to the input image, extracting informative features from the input image and the guide image to enhance the input image, selectively obtaining a first feature for the input image from among the informative features, and processing the input image based on the first feature.Type: GrantFiled: June 24, 2021Date of Patent: November 21, 2023Assignee: Samsung Electronics Co., Ltd.Inventors: Jihye Kim, Seon Min Rhee, Jongseok Kim, Heewon Kim, Seungju Han, Jaejoon Han
-
Patent number: 11823382Abstract: An ultrasound diagnostic apparatus 1 includes an image acquisition unit 17 that acquires an ultrasound image of a subject a bladder extraction unit 18 that extracts a bladder from the ultrasound image; a prostate extraction unit 19 that extracts a prostate or cervix from the ultrasound image from which the bladder is extracted; a region-of-interest setting unit 20 that sets a region of interest at a depth position in the ultrasound image based on a position of the extracted prostate or cervix in a case where the prostate or cervix is extracted and that sets a region of interest at a depth position in the ultrasound image based on a position of the extracted bladder in a case where the prostate or cervix is not extracted; and an image quality adjustment unit 21 that adjusts the transmission/reception condition according to the depth position of the region of interest.Type: GrantFiled: April 6, 2021Date of Patent: November 21, 2023Assignee: FUJIFILM CorporationInventor: Takuya Tsutaoka
-
Patent number: 11822621Abstract: Systems and methods described herein relate to training a machine-learning-based monocular depth estimator.Type: GrantFiled: March 31, 2021Date of Patent: November 21, 2023Assignee: Toyota Research Institute, Inc.Inventors: Vitor Guizilini, Rares A. Ambrus, Adrien David Gaidon, Jie Li
-
Patent number: 11823358Abstract: A handwritten content removing method and device and a storage medium. The handwritten content removing method comprises: acquiring an input image of a text page to be processed, the input image comprising a handwritten region, which comprises a handwritten content (S10); identifying the input image so as to determine the handwritten content in the handwritten region (S11); and removing the handwritten content in the input image so as to obtain an output image (S12).Type: GrantFiled: December 29, 2020Date of Patent: November 21, 2023Assignee: Hangzhou Dana Technology Inc.Inventors: Tao He, Huan Luo, Mingquan Chen
-
Patent number: 11823326Abstract: An image processing method includes obtaining two-dimensional and three-dimensional images of an object, extracting luminance and depth information from the three-dimensional image to generate luminance and depth image for the object, graying the two-dimensional image to obtain a single-channel grayscale image, selecting at least three same-location points from each of the grayscale and luminance image, calculating a coordinate transformation matrix between the grayscale and luminance images based on coordinates of the at least three same-location points in each of the grayscale and luminance images, and aligning the two-dimensional image with the luminance and depth images based on the coordinate transformation matrix to obtain fused image data. The fused image data includes color information of the two-dimensional image and the luminance and depth information of the three-dimensional image.Type: GrantFiled: May 13, 2023Date of Patent: November 21, 2023Assignee: CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITEDInventors: Guannan Jiang, Lili Han
-
Patent number: 11810579Abstract: A system for tracking biomarkers in subjects. In one embodiment, the biomarker tracking system has a sensory array including an RGB-D camera or RGB camera, a memory, and an electronic processor. The microphone captures voice data, including but not limited to tremor detection data, speech volume and pronunciation data, speech strength data, changes in tonality, hesitance in voice, and changes in speed or verbiage. A stored baseline biomarker model may comprise a voice data profile which may be pre-stored in the memory of a server and include a plurality of benchmarks. This electronic processor is configured to use this pre-stored voice data and compare it to the voice data captured with the microphone. The electronic processor is further configured to determine a set of attributes for the voice data, and generates a speech data deviation model based, at least in part, on the comparison of the speech data to the stored baseline biomarker model.Type: GrantFiled: November 26, 2019Date of Patent: November 7, 2023Assignee: NEUROPATH SPRLInventor: Benoit Yvonne Tas
-
Patent number: 11797926Abstract: A system and method for operating a robotic system to register unrecognized objects is disclosed. The robotic system may use first image data representative of an unrecognized object to derive an initial minimum viable region (MVR). The robotic system may analyze second image data representative of the unrecognized object to detect a condition representative of an accuracy of the initial MVR. The robotic system may register the initial MVR or an adjustment thereof based on the detected condition.Type: GrantFiled: October 27, 2021Date of Patent: October 24, 2023Assignee: MUJIN, Inc.Inventors: Rosen Nikolaev Diankov, Russell Islam, Xutao Ye
-
Patent number: 11798183Abstract: Apparatuses, systems, and techniques to estimate or predict depth information for image data. In at least one embodiment, depth information is predicted based at least in part on color information and geometry information associated with an image.Type: GrantFiled: March 8, 2021Date of Patent: October 24, 2023Assignee: NVIDIA CorporationInventors: Luyang Zhu, Arsalan Mousavian, Yu Xiang, Dieter Fox
-
Patent number: 11798169Abstract: A system may include one or more processors configured to receive a plurality of images representing an environment. The images may include image data generated by an image capture device. The processors may also be configured to transmit the image data to an image segmentation network configured to segment the images. The processors may also be configured to receive sensor data associated with the environment including sensor data generated by a sensor of a type different than an image capture device. The processors may be configured to associate the sensor data with segmented images to create a training dataset. The processors may be configured to transmit the training dataset to a machine learning network configured to run a sensor data segmentation model, and train the sensor data segmentation model using the training dataset, such that the sensor data segmentation model is configured to segment sensor data.Type: GrantFiled: October 11, 2022Date of Patent: October 24, 2023Assignee: Zoox, Inc.Inventor: David Pfeiffer
-
Patent number: 11792441Abstract: A computing system automatically detects, within a digital video frame, a video frame region that depicts a textual expression of a scoreboard. The computing system (a) engages in an edge-detection process to detect edges of at least scoreboard image elements depicted by the digital video frame, with at least some of these edges being of the textual expression and defining alphanumeric shapes; (b) applies pattern-recognition to identify the alphanumeric shapes; (c) establishes a plurality of minimum bounding rectangles each bounding a respective one of the identified alphanumeric shapes; (d) establishes, based on at least two of the minimum bounding rectangles, a composite shape that encompasses the identified alphanumeric shapes that were bounded by the at least two minimum bounding rectangles; and (e) based on the composite shape occupying a particular region, deems the particular region to be the video frame region that depicts the textual expression.Type: GrantFiled: April 6, 2021Date of Patent: October 17, 2023Assignee: Gracenote, Inc.Inventors: Jeffrey Scott, Markus Kurt Peter Cremer, Nishit Umesh Parekh, Dewey Ho Lee
-
Patent number: 11783456Abstract: Techniques for cascade filtering of a set of points of interest (POIs) in a light detection and ranging (LiDAR) system is described. The method includes performing a series of cascaded filtering of a set of points of interest (POIs) on a first point cloud. The method includes calculating, for each POI of the set of POIs, at least a first metric for a first set of neighborhood points to make a decision with respect to a subset of the set of POIs for transmission to a second point cloud. The method also includes extracting at least one of range or velocity information based on the second point cloud based on the decision.Type: GrantFiled: November 21, 2022Date of Patent: October 10, 2023Assignee: Aeva, Inc.Inventors: Krishna Toshniwal, Bruno Hexsel, Kumar Bhargav Viswanatha, Jose Krause Perin
-
Patent number: 11783009Abstract: A method for processing an image, which is performed by an image processing apparatus, is provided. The method includes acquiring a first image including an object and a second image including an object identical to the object in the first image under the same condition, acquiring three-dimensional direction information of a specific part of the object in the first image, and providing a three-dimensionally processed image by three-dimensionally rotating the object in the second image by an angle that corresponds to the acquired three-dimensional direction information of the specific part of the object in the first image.Type: GrantFiled: September 13, 2022Date of Patent: October 10, 2023Assignee: Suprema Inc.Inventors: Hyogi Lee, Kideok Lee, Bong Seop Song
-
Patent number: 11763472Abstract: Apparatus for optical sensing includes an illumination assembly, which directs first optical radiation toward a target scene over a first range of angles and second optical radiation over at least one second range of angles, which is smaller than and contained within the first range, while modulating the optical radiation with a carrier wave having at least one predetermined carrier frequency. A detection assembly includes an array of sensing elements, which output respective signals in response to the first and the second optical radiation. Processing circuitry drives the illumination assembly to direct the first and the second optical radiation toward the target scene in alternation, and processes the signals output by the sensing elements in response to the first optical radiation in order to compute depth coordinates of points in the target scene, while correcting the computed depth coordinates in response to the second optical radiation.Type: GrantFiled: March 14, 2021Date of Patent: September 19, 2023Assignee: APPLE INC.Inventors: Yazan Z. Alnahhas, Harish Venkataraman
-
Patent number: 11756204Abstract: The invention belongs to scene segmentation's field in computer vision and is a depth-aware method for mirror segmentation. PDNet successively includes a multi-layer feature extractor, a positioning module, and a delineating module. The multi-layer feature extractor uses a traditional feature extraction network to obtain contextual features; the positioning module combines RGB feature information with depth feature information to initially determine the position of the mirror in the image; the delineating module is based on the image RGB feature information, combined with depth information to adjust and determine the boundary of the mirror. This method is the first method that uses both RGB image and depth image to achieve mirror segmentation in an image. The present invention has also been further tested. For mirrors with a large area in a complex environment, the PDNet segmentation results are still excellent, and the results at the boundary of the mirrors are also satisfactory.Type: GrantFiled: June 2, 2021Date of Patent: September 12, 2023Assignee: DALIAN UNIVERSITY OF TECHNOLOGYInventors: Wen Dong, Xin Yang, Haiyang Mei, Xiaopeng Wei, Qiang Zhang
-
Patent number: 11748451Abstract: An image differentiation system receives input feature vectors for multiple input images and reference feature vectors for multiple reference images. In some cases, the feature vectors are extracted by an image feature extraction module trained based on training image triplets. A differentiability scoring module determines a differentiability score for each input image based on a distance between the input feature vectors and the reference feature vectors. The distance for each reference feature vector is modified by a weighting factor based on interaction metrics associated with the corresponding reference image. In some cases, an input image is identified as a differentiated image based on the corresponding differentiability score. Additionally or alternatively, an image modification module determines an image modification that increases the differentiability score of the input image. The image modification module generates a recommended image by applying the image modification to the input image.Type: GrantFiled: September 15, 2020Date of Patent: September 5, 2023Assignee: Adobe Inc.Inventors: Arshiya Aggarwal, Sanjeev Tagra, Sachin Soni, Ryan Rozich, Prasenjit Mondal, Jonathan Roeder, Ajay Jain
-
Patent number: 11734746Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform: inputting one or more pairs of digital images into a neural network; determining, using the neural network, a respective contrastive loss for each respective pair of digital images of the one or more pairs of digital images; receiving one or more new digital images; and determining, using the neural network, the one or more new digital images and the respective contrastive loss, at least one image to which the one or more new digital images is similar. Other embodiments are disclosed herein.Type: GrantFiled: August 30, 2021Date of Patent: August 22, 2023Assignee: WALMART APOLLO, LLCInventors: Stephen Dean Guo, Kannan Achan, Venkata Syam Prakash Rapaka
-
Patent number: 11734799Abstract: The present disclosure relates to a point cloud feature enhancement and apparatus, a computer device and a storage medium. The method includes: acquiring a three-dimensional point cloud, the three-dimensional point cloud including a plurality of input points; performing feature aggregation on neighborhood point features of the input point to obtain a first feature of the input point; mapping the first feature to an attention point corresponding to the corresponding input point; performing feature aggregation on neighborhood point features of the attention point to obtain a second feature of the corresponding input point; and performing feature fusion on the first feature and the second feature of the input point to obtain a corresponding enhanced feature. An enhancement effect of point cloud features can be improved with the method.Type: GrantFiled: October 12, 2021Date of Patent: August 22, 2023Assignee: SHENZHEN UNIVERSITYInventors: Hui Huang, Liqiang Lin
-
Patent number: 11734807Abstract: An image generating device for obtaining an image of an object, comprising: a control module configured to generate a first signal having a first frequency component and a first phase component for a first axis direction, and a second signal having a second frequency component and a second phase component for a second axis direction, an emitting unit configured to emit light to the object using the first signal and the second signal; and a light receiving unit configured to obtain light receiving signal based on returned light from the object.Type: GrantFiled: January 27, 2022Date of Patent: August 22, 2023Assignee: VPIX Medical IncorporationInventors: Kyungmin Hwang, Ji Won Kim, Yeong Ryeol Kim