Textiles Or Clothing Patents (Class 382/111)
  • Patent number: 11400614
    Abstract: Disclosed is a cutting machine for cutting a flat surface having a graphical design with optical registration features. The cutting machine includes a working surface for receiving at least one object, a first camera unit arranged so that the field of vision encompasses the whole working surface, a working group above the working surface, and at least one cutting device for cutting the at least one object. A computing unit with a circuit and program code for controlling the cutting machine includes a storage unit, a circuit and program code for evaluating images of the first camera unit to identify registration features of the at least one object in an image of the first camera unit, and being designed to define a cutting path for the cutting device according to at least one stored instruction and based on positions of the registration features in the image.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: August 2, 2022
    Assignee: Zünd Systemtechnik AG
    Inventors: Rolf Sutter, Andreas Grüter
  • Patent number: 11386615
    Abstract: A series of captured images of a user is received. Using a processor, the images are processed to identify a portion of each of the images corresponding to the user. Parameters of a predetermined three-dimensional human model are modified to fit a modified version of the predetermined three-dimensional human model across the identified portions of the images to determine a set of specific parameters representing a body profile of the user.
    Type: Grant
    Filed: April 9, 2021
    Date of Patent: July 12, 2022
    Assignee: Stitch Fix, Inc.
    Inventor: Christopher Erick Moody
  • Patent number: 11348007
    Abstract: A method and system where a first subsystem makes observations and performs surveillance using sensors in a mode that conserves a resource such as power, data transmission band width or processing cycles. This is accomplished by reducing illumination, pixel count, sampling rate or other functions that result in a limited granularity or data collection rate. A machine model is applied to the limited data and, when it evaluates to a suitable result or a prediction of an interesting condition, another subsystem or the same subsystem in a different mode collects data at a finer granularity with a higher data collection size or rate and evaluates that data to determine the nature of the first evaluation. The machine model may be trained in stages on a large scale server and on a small field processor. Data from the sensor may be used for training to improve the second step.
    Type: Grant
    Filed: May 3, 2020
    Date of Patent: May 31, 2022
    Inventor: Thomas Danaher Harvey
  • Patent number: 11315689
    Abstract: Utilizing graphical elements representing human bodies to estimate physical measurements of a user is described. In at least one example, a service provider can access a database storing a plurality of data items. The service provider can cause a set of data items of the plurality of data items to be presented to the user. Data items in the set of data items are associated with at least one graphical element representing a human body with individual magnitudes corresponding to individual dimensions of a plurality of dimensions. The service provider can receive data indicating a selection of a data item associated with a first magnitude associated with a first dimension and a second magnitude associated with a second dimension. The service provider can estimate physical measurements associated with the user based partly on a first magnitude and/or the second magnitude.
    Type: Grant
    Filed: October 21, 2019
    Date of Patent: April 26, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Jake M. Hofman, Daniel G. Goldstein
  • Patent number: 11308676
    Abstract: Provided are systems and methods for single image-based body animation. An example method includes receiving an input image that includes a body of a person and segmenting the input image into a body portion and a background portion. The method further includes fitting a model to the body portion. The model is configured to receive a set of pose parameters representing a pose of the body and generate an output image including an image of the body adopting the pose. The method further includes receiving a series of further sets of pose parameters, each representing at least one of further poses of the body. The further sets of pose parameters are generated using a generic model. The method also includes generating a series of output images of the body adopting the further poses and generating an output video based on the series of output images.
    Type: Grant
    Filed: October 2, 2020
    Date of Patent: April 19, 2022
    Assignee: Snap Inc.
    Inventors: Egor Nemchinov, Sergei Gorbatyuk, Aleksandr Mashrabov, Egor Spirin, Iaroslav Sokolov, Andrei Smirdin, Igor Tukh
  • Patent number: 11301682
    Abstract: A clothing item being captured is appropriately measured without requiring a dedicated sheet of paper or the like.
    Type: Grant
    Filed: July 30, 2020
    Date of Patent: April 12, 2022
    Assignee: Mercad, Inc.
    Inventors: Nisho Matsushita, Kohei Arai
  • Patent number: 11273378
    Abstract: Disclosed are a system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for digital avatars. An interface module receives a request message to determine measurements of a user. A graphics engine sub-module accesses a first set of data that is indicative of locations in a first image of a user. The locations are points of the user's body in the first image. The graphics engine sub-module accesses a second set of data that is indicative of a first physical-space measurement of the user. A computational sub-module determines, based at least partly on the locations and the first physical-space measurement characteristic, an estimate of a second physical-space measurement of the user.
    Type: Grant
    Filed: March 31, 2020
    Date of Patent: March 15, 2022
    Assignee: EBAY, INC.
    Inventors: Akshay Gadre, Kerri Breslin
  • Patent number: 11238188
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating personalized exosuits. In some implementations, sensor data indicating a three-dimensional shape of stretchable template garment while the template garment is worn by a person and has been stretched to align with the person's anatomy is obtained. The template garment can include indicators corresponding to positions for components of an exosuit, and can correspond to an exosuit design. The sensor data is analyzed to determine locations of the indicators of the template garment. A personalized exosuit design is generated for the person by adjusting a computer model for the exosuit design to locate components of the exosuit at regions corresponding to the identified locations of the indicators of the template garment. The personalized exosuit design is provided to one or more manufacturing devices.
    Type: Grant
    Filed: April 1, 2020
    Date of Patent: February 1, 2022
    Assignee: X Development LLC
    Inventors: Joseph Hollis Sargent, Rhoda Jill Kentin
  • Patent number: 11200471
    Abstract: Methods and systems for identifying cut-out patterns from a scanned raw image file and arranging shapes within a document prior to printing cut-out patterns are described. A printing device may identify and group contents in a page of a print job as shapes to be cut out from the paper after they are printed. The printing device may then detect the grouped page contents as cut-out patterns. For each cut-out pattern, the printing device may detect the white spaces of content of the cut-out pattern and mark them as available for printing other cut-out patterns. Thus, the printing device may print multiple cut-out patterns on a same page based on using the white space within larger cut-out patterns.
    Type: Grant
    Filed: February 12, 2020
    Date of Patent: December 14, 2021
    Assignee: KYOCERA Document Solutions Inc.
    Inventors: Philip Ver Paloma Dabon, Neil-Paul Payoyo Bermundo
  • Patent number: 11182675
    Abstract: The present disclosure relates to systems and methods for creating and training neural networks. The method includes collecting a set of signals from a database; applying a transform to each signal to create a modified set of signals, wherein signals of the modified set of signals are wavelets; iteratively, for each of a subset of the modified signals: training the neural network using a modified signal of the subset by adding at least one node to the neural network in response to an error function of an analysis of the modified signal exceeding a threshold; removing nodes from the neural network with activation rates below an activation rate threshold; and grouping each node into a lobe among a plurality of lobes, wherein nodes belonging to a lobe have a common characteristic.
    Type: Grant
    Filed: May 18, 2021
    Date of Patent: November 23, 2021
    Assignee: DEEP LABS INC.
    Inventors: Patrick Faith, Scott Edington
  • Patent number: 11164381
    Abstract: An improved system to provide a clothing model in augmented reality and/or virtual reality is disclosed. In one embodiment, the system provides a fully simulated garment, on the user's device, in an augmented reality or virtual reality display. In one embodiment, the process uses a parameterized smart garment model which enables real-time interaction with the garment on a device such as a mobile phone or tablet, with limited memory and processing power. In one embodiment, the system permits nearly instantaneous alteration of garment sizes. Because the garment is modeled to accurately reflect physical details, the lay of the garment changes as the size of the garment or body changes.
    Type: Grant
    Filed: November 2, 2018
    Date of Patent: November 2, 2021
    Assignee: GERBER TECHNOLOGY LLC
    Inventors: James F O'Brien, David T Jackson, Carlo Camporesi, Daniel Ram, David Macy, Edilson de Aguiar, James L. Andrews, Justin Lee, Karen M Stritzinger, Kevin Armin Samii, Nathan Mitchell, Tobias Pfaff, Scott M Frankel
  • Patent number: 11145128
    Abstract: An extended reality (XR) device and a method for controlling the same are disclosed. The XR device is applicable to 5G communication technology, robot technology, autonomous driving technology, and Artificial Intelligence (AI) technology, and a method for controlling the same.
    Type: Grant
    Filed: August 27, 2019
    Date of Patent: October 12, 2021
    Assignee: LG ELECTRONICS INC.
    Inventor: Dongseok Kim
  • Patent number: 11132811
    Abstract: A method and system that facilitates the size selection for garments such as hosiery or pantyhose with the aim to improve comfort and fit for the wearer is provided.
    Type: Grant
    Filed: March 6, 2017
    Date of Patent: September 28, 2021
    Assignee: THE LYCRA COMPANY LLC
    Inventor: Willem Bakker
  • Patent number: 11100699
    Abstract: In a measurement method, a processor selects one first image included in a plurality of two-dimensional images of a subject. The processor sets one of the selected first image and one second image extracted from the plurality of two-dimensional images on the basis of the selected first image as a measurement image. The processor extracts at least one third image from the plurality of two-dimensional images. The processor generates a three-dimensional shape of the subject on the basis of a position and a posture of a camera when each image is generated. The processor determines whether or not an image is suitable for measurement with respect to at least one of the first image, the measurement image, and the third image.
    Type: Grant
    Filed: February 13, 2020
    Date of Patent: August 24, 2021
    Assignee: OLYMPUS CORPORATION
    Inventor: Naofumi Endo
  • Patent number: 11086297
    Abstract: Systems and methods for designing, fabricating, selecting, evaluating and/or improving therapeutic compression garments for patients or individuals using compression garments.
    Type: Grant
    Filed: December 4, 2018
    Date of Patent: August 10, 2021
    Assignee: SIGVARIS AG
    Inventor: Emilie Bertaux Hegemann
  • Patent number: 11074713
    Abstract: A recognition device a first recognition unit, a second recognition unit, and a third recognition unit. The first recognition unit acquires image information of a target person, and determines, based on a first discriminator and a feature in the image information, a first range corresponding to the image information of the target person. The second recognition unit acquires distance information of the target person, and determines, based on a second discriminator and a feature in the distance information, a second range corresponding to the distance information of the target person. The third recognition unit determines, based on the first range determined by the first recognition unit and the second range determined by the second recognition unit, a direction that a body of the target person is facing, and recognizes, based on the determined direction and a joint position dictionary, a skeleton of the target person.
    Type: Grant
    Filed: October 9, 2019
    Date of Patent: July 27, 2021
    Assignee: FUJITSU LIMITED
    Inventor: Hiroaki Fujimoto
  • Patent number: 11055538
    Abstract: Techniques for object re-identification based on temporal context. Embodiments extract, from a first image corresponding to a first camera device and a second image corresponding to a second camera device, a first plurality of patch descriptors and a second plurality of patch descriptors, respectively. A measure of visual similarity between the first image and the second image is computed, based on the first plurality of patch descriptors and the second plurality of patch descriptors. A temporal cost between the first image and the second image is computed, based on a first timestamp at which the first image was captured and a second timestamp at which the second image was captured. The measure of visual similarity and the temporal cost are combined into a single cost function, and embodiments determine whether the first image and the second image depict a common object, using the single cost function.
    Type: Grant
    Filed: March 31, 2017
    Date of Patent: July 6, 2021
    Assignee: Disney Enterprises, Inc.
    Inventors: Michal Koperski, Slawomir W. Bak, G. Peter K. Carr
  • Patent number: 11030657
    Abstract: A system includes one or more processors to receive a product placement opportunity for at least one clothing item from a studio client computing device and store information associated with the product placement opportunity in a memory, transmit the information associated with the product placement opportunity to at least one fashion client computing device, receive an acceptance of the product placement opportunity from a fashion client computing device and transmit information associated with the acceptance to the studio client computing device, and receive a payment from at least one of the studio client computing device and the fashion client computing device and hold the payment in escrow.
    Type: Grant
    Filed: September 3, 2014
    Date of Patent: June 8, 2021
    Assignee: Contra Software, LLC
    Inventor: Christopher Lee Palmer
  • Patent number: 11021840
    Abstract: Soft absorbent sheets, structuring fabrics for producing soft absorbent sheets, and methods of making soft absorbent sheets. The soft absorbent sheets have a plurality of domed regions or projected regions extending from a surface of the sheets, and connecting regions form a network between domed regions. The domed and projected regions include indented bars that extend across the domed and projected regions in a substantially cross machine direction of the absorbent sheets. The absorbent sheets can be formed by structuring fabrics that have long warp yarn knuckles.
    Type: Grant
    Filed: May 2, 2019
    Date of Patent: June 1, 2021
    Assignee: GPCP IP Holdings LLC
    Inventors: Daniel Hue Ming Sze, Xiaolin Fan, Hung-Liang Chou, Taiye Philips Oriaran, Farminder Singh Anand, Dean Joseph Baumgartner, Joseph Henry Miller
  • Patent number: 10991115
    Abstract: A technology is required in which clothing can be accurately classified, regardless of a posture of a subject. An image processing device, includes: an acquisition means for acquiring an image to be processed including an image of clothing worn by a subject on a lower body; a specifying means for specifying a position of an end portion of the clothing, in the image to be processed; an extraction means for extracting a connected region which is positioned to be adjacent to the end portion of the clothing and is configured by connecting prescribed pixels, from the image to be processed; and a determination means for determining a type of the clothing, on the basis of the connected region.
    Type: Grant
    Filed: March 6, 2017
    Date of Patent: April 27, 2021
    Assignee: Rakuten, Inc.
    Inventor: Yeongnam Chae
  • Patent number: 10962404
    Abstract: Disclosed are systems and methods for body weight prediction from one or more images. The method includes the steps of receiving one or more subject parameters; receiving one or more images containing a subject; identifying one or more annotation key points for one or more body features underneath a clothing of the subject from the one or more images utilizing one or more annotation deep-learning networks; calculating one or more geometric features of the subject based on the one or more annotation key points; and generating a prediction of the body weight of the subject utilizing a weight machine-learning module based on the one or more geometric features of the subject and the one or more subject parameters.
    Type: Grant
    Filed: March 26, 2020
    Date of Patent: March 30, 2021
    Assignee: Bodygram, Inc.
    Inventors: Kyohei Kamiyama, Chong Jin Koh, Yu Sato
  • Patent number: 10964084
    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a digital animation of a digital animation character by utilizing a generative adversarial network and a hip motion prediction network. For example, the disclosed systems can utilize an unconditional generative adversarial network to generate a sequence of local poses of a digital animation character based on an input of a random code vector. The disclosed systems can also utilize a conditional generative adversarial network to generate a sequence of local poses based on an input of a set of keyframes. Based on the sequence of local poses, the disclosed systems can utilize a hip motion prediction network to generate a sequence of global poses based on hip velocities. In addition, the disclosed systems can generate an animation of a digital animation character based on the sequence of global poses.
    Type: Grant
    Filed: June 25, 2019
    Date of Patent: March 30, 2021
    Assignee: ADOBE INC.
    Inventors: Jingwan Lu, Yi Zhou, Connelly Barnes, Jimei Yang
  • Patent number: 10909714
    Abstract: An approach is provided for rendering a distance marker in an image. The approach, for example, involves determining a plurality of camera characteristics of a camera used to capture the image. The plurality of camera characteristics, for instance, can include a camera field of view, a horizon offset, a camera mounting height, a camera mounting axis, or a combination thereof. The approach also involves determining a ground plane extending to a horizon depicted in the image, a camera position with respect to the ground plane, and an image plane based on the plurality of characteristics, wherein the image plane is orthogonal to the ground plane and intersects the ground plane at a designated distance from the camera position. The approach further involves projecting a ray from the camera position through the distance marker on the ground plane to a marker position on the image plane, and rendering the distance marker in the image based on the marker position on the image plane.
    Type: Grant
    Filed: October 30, 2018
    Date of Patent: February 2, 2021
    Assignee: HERE GLOBAL B.V.
    Inventor: Mike Milici
  • Patent number: 10878229
    Abstract: A shape discriminating device includes an image acquisition means configured to acquire a target image being an image where pants are shown, a diverging position acquisition means configured to acquire, as a diverging position, a position where the pants diverge into two leg parts or a position which can be regarded as a position where the pants diverge into two leg parts, a leg region extraction means configured to extract a leg region from a region showing the pants in the target image, a leg shape acquisition means configured to acquire leg shape information concerning variation in lateral width of a leg part of the pants based on the diverging position and the leg region, a specifying means configured to specify a shape of the pants based on the leg shape information, and an output means configured to output information concerning the specified shape of the pants.
    Type: Grant
    Filed: May 26, 2016
    Date of Patent: December 29, 2020
    Assignee: Rakuten, Inc.
    Inventor: Yeongnam Chae
  • Patent number: 10853952
    Abstract: An image processing apparatus, comprising a generation unit configured to generate a three-dimensional shape model of an object present in a field, based on a plurality of captured images obtained by a plurality of cameras that capture the field from different directions, a specification unit configured to specify a direction of the three-dimensional shape model generated by the generation unit, and a storage control unit configured to cause the direction of the three-dimensional shape model specified by the specification unit to be stored in a storage unit together with identification information of the object.
    Type: Grant
    Filed: September 19, 2017
    Date of Patent: December 1, 2020
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Tomohiro Nishiyama
  • Patent number: 10839586
    Abstract: Provided are systems and methods for single image-based body animation. An example method includes receiving a input image, the input image including a body of a person, segmenting the input image into a body portion and a background portion, wherein the body portion includes pixels corresponding to the body of the person, fitting a model to the body portion, wherein the model is configured to receive pose parameters representing a pose of the body and generate an output image including an image of the body adopting the pose, receiving a series of further pose parameters, each of the series of further pose parameters representing one of further poses of the body, providing each of the series of further pose parameters to the model to generate a series of output images of the body adopting the further poses, and generating, based on the series of output images, an output video.
    Type: Grant
    Filed: June 7, 2019
    Date of Patent: November 17, 2020
    Assignee: Snap Inc.
    Inventors: Egor Nemchinov, Sergei Gorbatyuk, Aleksandr Mashrabov, Egor Spirin, Iaroslav Sokolov, Andrei Smirdin, Igor Tukh
  • Patent number: 10810647
    Abstract: One embodiment provides a method, including: obtaining, at an information handling device, an image of a person; determining physical characteristics of the person by analyzing the image; receiving an image of at least one selected piece of jewelry, the selected jewelry having a given jewelry profile, wherein the jewelry profile describes features and construction of the selected piece of jewelry; overlaying the image of the at least one selected piece of jewelry onto an image of the person, wherein the overlaying comprises analyzing resizing the image of the at least one selected piece of jewelry to match the physical characteristics of the person, in view of the jewelry profile of the at least one selected piece of jewelry; and providing, on a display of the information handling device, an output image of the image of the person comprising the overlaid image of the at least one piece of jewelry.
    Type: Grant
    Filed: June 9, 2017
    Date of Patent: October 20, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Mohit Jain, Pratyush Kumar, Megha Nawhal, Ashok Pon Kumar Sree Prakash, Anshul Bhavesh Shah, Gyanendra Sharma, Amith Singhee
  • Patent number: 10789702
    Abstract: Systems and methods for analyzing a fabric article to determine fiber damage are provided herein. In an embodiment of a method for analyzing a fabric article, the fabric article is provided and at least one image of the fabric article is captured using a three-dimensional imaging device. The at least one image is processed using a contrast function to produce a processed data set that is representative of fiber damage in a viewing area of the three-dimensional imaging device. Optionally, a processed image is produced based upon the processed data set.
    Type: Grant
    Filed: June 25, 2018
    Date of Patent: September 29, 2020
    Assignee: Henkel IP & Holding GmbH
    Inventors: Joseph D. Dahlmeyer, Jr., Wendy A. Saladyga
  • Patent number: 10760899
    Abstract: A shape discrimination device includes an approximate curve calculator configured to calculate an approximate curve of a contour, the contour being a line having a finite length representing a part of an outline of an object shown in an image, the approximate curve being a line approximating to the contour and calculated based on coordinates forming the contour, a distance calculator configured to calculate a first distance and a second distance being distances from a first and second end of the contour to a first and second end of the approximate curve, respectively, a coincidence calculator configured to calculate a center coincidence being a degree of coincidence between a center of the contour and the approximate curve, and a specifier configured to specify a shape of the object or a part of the object based on the first distance, the second distance, and the center coincidence.
    Type: Grant
    Filed: December 25, 2015
    Date of Patent: September 1, 2020
    Assignee: Rakuten, Inc.
    Inventor: Yeongnam Chae
  • Patent number: 10691899
    Abstract: A computer implemented method for learning a function configured for captioning a region of an image. The method comprises providing a dataset of triplets each including a respective image, a respective region of the respective image, and a respective caption of the respective region. The method also comprises learning, with the dataset of triplets, a function that is configured to generate an output caption based on an input image and on an input region of the input image. Such a method constitutes an improved solution for captioning a region of an image.
    Type: Grant
    Filed: May 2, 2018
    Date of Patent: June 23, 2020
    Assignee: DASSAULT SYSTEMES
    Inventors: Niels Lubbers, Malika Boulkenafed
  • Patent number: 10592960
    Abstract: The disclosure relates to determining thermal insulation levels of clothing a user should wear when traveling to a destination. To do this, a thermal insulation level of clothing worn by a user and levels worn by a crowd can be analyzed from images including the user or the crowd. A thermal sensitivity bias for the user can be determined by comparing those levels for similar locations. Environment data can then be collected for the destination. A thermal insulation level of clothing worn by the crowd for the destination can be predicted based on the environment data. This level can be adjusted with the bias for the user to generate a thermal insulation level of clothing to be worn by the user at the destination. An image having clothing with that level can be displayed to recommend a style of clothing for the user to wear at the destination.
    Type: Grant
    Filed: December 19, 2017
    Date of Patent: March 17, 2020
    Assignee: FUTUREWEI TECHNOLOGIES, INC.
    Inventors: Yaya Chu, I-Hsuan Yang
  • Patent number: 10521429
    Abstract: Utilizing graphical elements representing human bodies to estimate physical measurements of a user is described. In at least one example, a service provider can access a database storing a plurality of data items. The service provider can cause a set of data items of the plurality of data items to be presented to the user. Data items in the set of data items are associated with at least one graphical element representing a human body with individual magnitudes corresponding to individual dimensions of a plurality of dimensions. The service provider can receive data indicating a selection of a data item associated with a first magnitude associated with a first dimension and a second magnitude associated with a second dimension. The service provider can estimate physical measurements associated with the user based partly on a first magnitude and/or the second magnitude.
    Type: Grant
    Filed: October 23, 2015
    Date of Patent: December 31, 2019
    Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC.
    Inventors: Jake M. Hofman, Daniel G. Goldstein
  • Patent number: 10489640
    Abstract: A device that determines whether a first person extracted from a first image is identified with a second person extracted from a second image, includes a processor configured to extract a first feature value of a contour portion of the first person, from the first image, extract a second feature value of a contour portion of the second person, from the second image, and determine whether the first person is identified with the second person, based on comparison processing in which a first effect on a first comparison result of the first feature value and the second feature value becomes greater than a second effect on a second comparison result of a third feature value of a portion further from a contour than the contour portion of the first person and a fourth feature value of a portion further from the contour than the contour portion of the second person.
    Type: Grant
    Filed: February 2, 2016
    Date of Patent: November 26, 2019
    Assignee: FUJITSU LIMITED
    Inventors: Kentaro Tsuji, Mingxie Zheng, Yuji Matsuda, Nobuhiro Miyazaki, Akihiro Minagawa, Yusuke Uehara
  • Patent number: 10475195
    Abstract: Techniques are provided for global (non-rigid) scan point registration between a scanned object and an associated model, from an arbitrary initial starting position, based on a combination of iterative coarse registration and fine registration. A methodology implementing the techniques according to an embodiment includes generating a model transformation based on a coarse registration between the model and the point scan. The method further includes calculating an alignment metric based on a distance measurement between the point scan and the transformed model. If the alignment metric exceeds a selected threshold value, a fine registration is performed between the transformed model and the point scan. Otherwise, the method continues by performing a random rotation of the model; a translation of the rotated model towards a centroid of the point scan; and iterating the coarse registration using the translated model until the alignment metric is achieved, after which the fine registration is performed.
    Type: Grant
    Filed: March 9, 2017
    Date of Patent: November 12, 2019
    Assignee: INTEL CORPORATION
    Inventors: Rana Hanocka, Shahar Fleishman, Jackie Assa
  • Patent number: 10474928
    Abstract: In an example, a computerized neural fabric is created by representing each pattern of learned weights of one or more machine learning algorithm-trained models specifying a specific set of products as a column in the computerized neural fabric, each pattern comprising one or more clusters representing combinations of convolutional filters, each cluster learning low level features and sending output via a vertical flow up the corresponding column to a final classification within the corresponding pattern. One or more potential lateral flows between patterns in the computerized neural fabrics is dynamically determined based on resemblance of a new product in a candidate image to the specific sets of products in each of the patterns and identifying possible mutations of the patterns based on the resemblance. Then, one of the one or more potential lateral flows is selected as a new model.
    Type: Grant
    Filed: November 14, 2017
    Date of Patent: November 12, 2019
    Assignee: SAP SE
    Inventors: Sivakumar N, Praveenkumar A K, Raghavendra D, Vijay G, Pratik Shenoy, Kishan Kumar Kedia
  • Patent number: 10460158
    Abstract: In a method of generating a three dimensional representation of a human body shape from a depth image of a clothed human subject is disclosed.
    Type: Grant
    Filed: June 19, 2014
    Date of Patent: October 29, 2019
    Assignee: KABUSHIKI KAISHA TOSHIBA
    Inventors: Frank Perbet, Minh-Tri Pham, Bjorn Stenger, Sam Johnson
  • Patent number: 10427348
    Abstract: Automatic process control of additive manufacturing. The system includes an additive manufacturing device for making an object and a local network computer controlling the device. At least one camera is provided with a view of a manufacturing volume of the device to generate network accessible images of the object. The computer is programmed to stop the manufacturing process when the object is defective based on the images of the object.
    Type: Grant
    Filed: November 28, 2017
    Date of Patent: October 1, 2019
    Assignee: Massachusetts Institute of Technology
    Inventors: Alfonso Alexander Perez, Christopher Michael Haid, Mateo Pena Doll, Forrest W. Pieper
  • Patent number: 10430551
    Abstract: In scan data retrieval, a mesh is fit (32) to surface data of a current patient, such as data from an optical or depth sensor (18). Meshes are also fit (48) to medical scan data, such as fitting (48) to skin surface segments of computed tomography data. The meshes or parameters derived from the meshes may be more efficiently compared (34) to identify (36) a previous patient with similar body shape and/or size. The scan configuration (38) for that patient, or that patient as altered to account for differences from the current patient, is used. In some embodiments, the parameter vector used for searching (34) includes principle component analysis coefficients. In further embodiments, the principle component analysis coefficients may be projected to a more discriminative space using metric learning.
    Type: Grant
    Filed: November 6, 2015
    Date of Patent: October 1, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Jiangping Wang, Kai Ma, Vivek Singh, Mingqing Chen, Yao-Jen Chang, Shaohua Kevin Zhou, Terrence Chen, Andreas Krauss
  • Patent number: 10417529
    Abstract: One embodiment provides a method comprising receiving an input, and classifying the input utilizing a learned linear combination of multi-dimensional filters. Each multi-dimensional filter identifies a multi-dimensional pattern of a homogenous feature. The method further comprises generating an output indicative of a classification of the input.
    Type: Grant
    Filed: September 15, 2016
    Date of Patent: September 17, 2019
    Assignee: SAMSUNG ELECTRONICS CO., LTD.
    Inventors: Justin Martineau, Jonathan J. Currey
  • Patent number: 10410043
    Abstract: The system and method deal with three-dimensional (3D) scanning technology which produces object representations which permit rapid, highly-accurate part identification which is not afforded by traditional two-dimensional (2D) camera imaging. The system and method are applicable to any field wherein repair/replacement parts are needed, such as the plumbing, automotive, fastener, marine, window, door, etc. fields.
    Type: Grant
    Filed: November 11, 2016
    Date of Patent: September 10, 2019
    Assignee: Skusub LLC
    Inventors: Keith H. Meany, Matthew Antone
  • Patent number: 10403031
    Abstract: Methods, systems, and apparatus for obtaining first image features derived from an image of an object, providing the first image features to a three-dimensional estimator neural network, and obtaining, from the three-dimensional estimator neural network, data specifying an estimated three-dimensional shape and texture based on the first image features. The estimated three-dimensional shape and texture are provided to a three-dimensional rendering engine, and a plurality of three-dimensional views of the object are generated by the three-dimensional rendering engine based on the estimated three-dimensional shape and texture. The plurality of three-dimensional views are provided to the object recognition engine, and second image features derived from the plurality of three-dimensional views are obtained from the object recognition engine. A loss is computed based at least on the first and second image features, and the three-dimensional estimator neural network is trained based at least on the computed loss.
    Type: Grant
    Filed: November 15, 2017
    Date of Patent: September 3, 2019
    Assignee: Google LLC
    Inventors: Forrester H. Cole, Kyle Genova
  • Patent number: 10402994
    Abstract: A method implemented with a smart body scanner with applications for online apparel retail, fitness, and healthcare applications includes, with a plurality of depth sensors implemented in the body scanner, creating 3D depth images of a body. In a hardware processing step, 3D depth images are generated as recorded part-images with saturated bright regions and lost dark regions. In a pre-processing step, using High Dynamic Range (HDR) processing, depth data obtained in the bright regions is combined with depth data obtained in the dark regions. In a model fusion step, a single 3D body model is created from a stream of the 3D depth images obtained from multiple angles of view during rotating of the body.
    Type: Grant
    Filed: May 12, 2016
    Date of Patent: September 3, 2019
    Assignee: Naked Labs Austria GmbH
    Inventors: Farhad Farahbakhshian, Peter Kreuzgruber
  • Patent number: 10373373
    Abstract: Systems and methods are provided for enabling the reduction of the time required to simulate a garment fitting onto a destination body shape with high visual quality, while also offering high performance and accuracy. The embodiments described herein include, for example, caching of source body meshes having a geometric difference with a destination body mesh that is within a predefined threshold. At least one of the cached source body meshes is selected, based, at least in part, on a wearable measurement range of the garment. For each of the selected cached source body meshes, a deformable object mesh representing the garment is generated, wherein the generating is based, at least in part, on the selected cached source body mesh. A source body mesh having body measurements that most closely match the body measurements of the destination body mesh is identified from among the selected cached source body meshes.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: August 6, 2019
    Assignee: STYLEME LIMITED
    Inventors: Jonathan Zhan Hua Leong, Ying-Hung Chen, Tsung-Chih Tsai
  • Patent number: 10346893
    Abstract: Machine learning-based approaches are used to identify complementary sets of items, such as articles of clothing and accessories that “match,” and suggest items that would complement a given item of interest. A simulated representation of how the item of interest and the identified complementary items would look together is then generated. For example, given a particular piece of clothing or other apparel item of interest, additional items that complement the item of interest can be identified and suggested to a potential purchaser of the item. Additionally, a three-dimensional (3D) or pseudo-3D representation of a human body can be generated to model the apparel item of interest and the identified complementary apparel items to give the user an idea of how the suggested outfit would look on a user. The representation can be modified to more closely resemble a particular user.
    Type: Grant
    Filed: March 21, 2016
    Date of Patent: July 9, 2019
    Assignee: A9.com, Inc.
    Inventors: Lixin Duan, Rahul Bhotika, Song Cao
  • Patent number: 10339667
    Abstract: A method and apparatus for locating and/or determining the condition of a wear part in an image of an operating implement associated with heavy equipment is disclosed. The method involves capturing at least one image of the operating implement during operation of the heavy equipment, the image including a plurality of pixels each having an intensity value. The method also involves selecting successive pixel subsets within the plurality of pixels, and processing each pixel subset to determine whether pixel intensity values in the pixel subset meet a matching criterion indicating a likelihood that the pixel subset corresponds to the wear part. The matching criterion is based on processing a labeled set of training images during a training exercise prior to capturing the at least one image of the operating implement.
    Type: Grant
    Filed: May 13, 2016
    Date of Patent: July 2, 2019
    Assignee: Motion Metrics International Corp
    Inventors: Shahram Tafazoli Bilandi, Mahdi Ramezani, Amin Suzani, Neda Parnian, Matthew Alexander Baumann, Saman Nouranian, Nazanin Hamzei, Mohammad Sameti, Saeed Karimifard
  • Patent number: 10329716
    Abstract: Soft absorbent sheets, structuring fabrics for producing soft absorbent sheets, and methods of making soft absorbent sheets. The soft absorbent sheets have a plurality of domed regions or projected regions extending from a surface of the sheets, and connecting regions form a network between domed regions. The domed and projected regions include indented bars that extend across the domed and projected regions in a substantially cross machine direction of the absorbent sheets. The absorbent sheets can be formed by structuring fabrics that have long warp yarn knuckles.
    Type: Grant
    Filed: March 6, 2018
    Date of Patent: June 25, 2019
    Assignee: GPCP IP Holdings LLC
    Inventors: Daniel Hue Ming Sze, Xiaolin Fan, Hung-Liang Chou, Taiye Philips Oriaran, Farminder Singh Anand, Dean Joseph Baumgartner, Joseph Henry Miller
  • Patent number: 10324673
    Abstract: Methods and systems for arranging shapes within a document prior to printing cut-out patterns are described. A printing device may identify and group contents in a page of a print job as shapes to be cut out from the paper after they are printed. The printing device may then detect the grouped page contents as cut-out patterns. For each cut-out pattern, the printing device may detect the white spaces of content of the cut-out pattern and mark them as available for printing other cut-out patterns. Thus, the printing device may print multiple cut-out patterns on a same page based on using the white space within larger cut-out patterns.
    Type: Grant
    Filed: January 5, 2018
    Date of Patent: June 18, 2019
    Assignee: KYOCERA Document Solutions Inc.
    Inventors: Philip Ver Paloma Dabon, Neil-Paul Payoyo Bermundo
  • Patent number: 10265733
    Abstract: An apparatus that facilitates the manual sorting of objects is disclosed. The apparatus includes a display surface having a surface that can be selectively illuminated and that is adapted for receiving the objects. An identification reader reads identification information stored on the objects. A controller causes an area on the display surface corresponding to one of the objects to be illuminated based on the identification information and indicates a location to which the illuminated object is to be moved. In one aspect of the invention, the display surface includes an area adapted for positioning a receiver for the objects. The display surface provides an indication of a position in the receiver at which the one of the objects is to be placed.
    Type: Grant
    Filed: November 1, 2017
    Date of Patent: April 23, 2019
    Assignee: Agilent Technologies, Inc.
    Inventors: Robert Kincaid, Melanie Tory, Joachim Schmid
  • Patent number: 10248884
    Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.
    Type: Grant
    Filed: April 10, 2017
    Date of Patent: April 2, 2019
    Assignee: Linear Algebra Technologies Limited
    Inventors: David Moloney, Alireza Dehghani
  • Patent number: 10163003
    Abstract: Certain embodiments involve recognizing combinations of body shape, pose, and clothing in three-dimensional input images. For example, synthetic training images are generated based on user inputs. These synthetic training images depict different training figures with respective combinations of a body pose, a body shape, and a clothing item. A machine learning algorithm is trained to recognize the pose-shape-clothing combinations in the synthetic training images and to generate feature descriptors describing the pose-shape-clothing combinations. The trained machine learning algorithm is outputted for use by an image manipulation application. In one example, an image manipulation application uses a feature descriptor, which is generated by the machine learning algorithm, to match an input figure in an input image to an example image based on a correspondence between a pose-shape-clothing combination of the input figure and a pose-shape-clothing combination of an example figure in the example image.
    Type: Grant
    Filed: December 28, 2016
    Date of Patent: December 25, 2018
    Assignee: Adobe Systems Incorporated
    Inventors: Zhili Chen, Duygu Ceylan, Byungmoon Kim, Liwen Hu, Jimei Yang