Patents by Inventor Jason Richards
Jason Richards has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20190279044Abstract: An artificial intelligence system for identifying attributes in an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: extracting first features; categorizing the first images in a first group or a second group; modifying first metadata associated with each image in the first images to include a binary label; calculating a classification function; classifying a second plurality of images using the classification function; extracting second features from the second images classified in the first group; categorizing the second images in the first group by attribute; calculating an attribute identification function that identifies attributes of the second images; and identifying at least one attribute associated with a client image using the attribute identification function, the client image being received from the client device.Type: ApplicationFiled: January 22, 2019Publication date: September 12, 2019Applicant: Capital One Services, LLCInventors: Sunil Subrahmanyam VASISHT, Geoffrey DAGLEY, Qiaochu TANG, Sean REDDY, Jason Richard HOOVER, Stephen Michael WYLIE, Micah PRICE
-
Publication number: 20190279263Abstract: The present disclosure relates to systems, methods, and computer readable media for processing an image including a vehicle using machine learning. The systems can include determining a location of the client device. The systems can further include receiving a first image of a vehicle from an image sensor of the client device and matching, using machine learning, the first image to one or more images of vehicles in a vehicle database to identify the vehicle. The vehicle database can list vehicles located at the determined location of the client device and images of the vehicles. The systems can include retrieving vehicle information from the vehicle database, based on the identified vehicle, and obtaining comparison information based at least in part on the vehicle information. The systems can include estimating a quote for the vehicle based on the comparison information and transmitting the estimated quote for display on the client device.Type: ApplicationFiled: June 15, 2018Publication date: September 12, 2019Applicant: CAPITAL ONE SERVICES, LLCInventors: QIAOCHU TANG, SUNIL SUBRAHMANYAM VASISHT, STEPHEN MICHAEL WYLIE, GEOFFREY DAGLEY, MICAH PRICE, JASON RICHARD HOOVER
-
Publication number: 20190274101Abstract: Systems and methods for preventing machine learning models from negatively affecting mobile devices are provided. For example, a mobile device including a camera, memory devices, and one or more processors are provided. In some embodiments, the processors may be configured to provide images captured by the camera to a machine learning model at a first rate. The processors may also be configured to determine whether one or more of the images includes an object. If one or more of the images includes the object, the processors may be further configured to adjust the first rate of providing the images to the machine learning model to a second rate, and in some embodiments, determine whether to adjust the second rate of providing the images to the machine learning model to a third rate based on output received from the machine learning model.Type: ApplicationFiled: March 6, 2018Publication date: September 5, 2019Applicant: Capital One Services, LLCInventors: Micah PRICE, Sunil Subrahmanyam VASISHT, Stephen Michael WYLIE, Geoffrey DAGLEY, Qiaochu TANG, Jason Richard HOOVER
-
Publication number: 20190272481Abstract: Systems and methods for preventing machine learning models from negatively affecting mobile devices are provided. For example, a mobile device including a camera, memory devices, and one or more processors are provided. In some embodiments, the processors may be configured to provide images captured by the camera to a machine learning model at a first rate. The processors may also be configured to determine whether one or more of the images includes an object. If one or more of the images includes the object, the processors may be further configured to adjust the first rate of providing the images to the machine learning model to a second rate, and in some embodiments, determine whether to adjust the second rate of providing the images to the machine learning model to a third rate based on output received from the machine learning model.Type: ApplicationFiled: March 5, 2018Publication date: September 5, 2019Applicant: Capital One Services, LLCInventors: Micah PRICE, Sunil Subrahmanyam VASISHT, Stephen Michael WYLIE, Geoffrey DAGLEY, Qiaochu TANG, Jason Richard HOOVER
-
Patent number: 10395313Abstract: A system for processing an image including a vehicle using machine learning can include a processor in communication with a client device, and a storage medium storing instructions that, when executed, cause the processor to perform operations including: receiving an image of a vehicle from the client device; extracting one or more features from the image; based on the extracted features and using a machine learning algorithm, determining a make and a model of the vehicle; obtaining user information relating to a financing request for the vehicle; determining a real-time quote for the vehicle based on the make, the model, and the user information; and transmitting the real-time quote for display on the client device.Type: GrantFiled: March 8, 2018Date of Patent: August 27, 2019Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Sunil Subrahmanyam Vasisht, Stephen Michael Wylie, Geoffrey Dagley, Micah Price, Jason Richard Hoover, Sanjiv Yajnik, Raman Bajaj, Arjun Dugal
-
Patent number: 10345965Abstract: The present disclosure relates to interactive projection systems. In one implementation, a system for projecting a user interface may include a film affixed to a surface; a first projector configured to project a user interface onto the film; a second projector configured to project a plurality of light beams such that the plurality of light beams form a plane above the film that does not intersect the film; and an image sensor configured to receive reflections caused by the projected plurality of light beams. The system may further include at least one processor configured to receive an indication of a reflection from the image sensor; determine a location associated with the reflection; in response to the received indication, determine a change for the user interface based on the determined location; and transmit a command to the first projector to modify the projected user interface according to the determined change.Type: GrantFiled: October 19, 2018Date of Patent: July 9, 2019Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Stephen Michael Wylie, Geoffrey Dagley, Jason Richard Hoover
-
Publication number: 20190203527Abstract: A pet door is provided herein. The pet door includes a pivotal flap and a frame that defines a through-way. A rotatable knob is mounted to the frame and has a handle portion and a stop wall. The handle portion and stop wall include various profiles and configurations that work in concert to control the flap's direction of pivotal movement. In a first configuration, the flap may swing outwardly or inwardly. A second configuration prevents the flap from swinging inwardly. A third configuration prevents the flap from swinging outwardly. A fourth configuration places the flap is in a locked position to prevent swinging in either direction. The electronic door also includes an electronic latch mechanism which selectively latches and unlatches the flap. The latch mechanism unlatches the flap in response to a wireless signal from an electronic transmitter that may be affixed to a pet.Type: ApplicationFiled: March 6, 2019Publication date: July 4, 2019Inventors: Cody Lee Stricklin, Marc Edward Brush, Jason Richard Graves
-
Patent number: 10325315Abstract: A system for processing an image including a vehicle using machine learning can include a processor in communication with a client device, and a storage medium storing instructions that, when executed, cause the processor to perform operations including: determining a location of the client device; receiving an image of a vehicle from the client device; matching, using a machine learning algorithm, the image to one or more images of vehicles in a database, the database listing vehicles located at the determined location and including images of the vehicles; retrieving vehicle information from the database based on the matched one or more images in the database; obtaining user information relating to a financing request for the vehicle; determining a real-time quote for the vehicle based on the vehicle information and user information; and transmitting the real-time quote for display on the client device.Type: GrantFiled: March 8, 2018Date of Patent: June 18, 2019Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Sunil Subrahmanyam Vasisht, Stephen Michael Wylie, Geoffrey Dagley, Micah Price, Jason Richard Hoover, Sanjiv Yajnik, Raman Bajaj, Arjun Dugal
-
Patent number: 10325178Abstract: The present disclosure relates to image preprocessing to improve object recognition. In one implementation, a system for preprocessing an image for object recognition may include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving the image, detecting a plurality of bounding boxes within the image, grouping the plurality of bounding boxes into a plurality of groups such that bounding boxes within a group have shared areas exceeding an area threshold, deriving a first subset of the plurality of bounding boxes by selecting bounding boxes having highest class confidence scores from at least one group, selecting a bounding box from the first subset having a highest score based on area and class confidence score, and outputting the selected bounding box.Type: GrantFiled: November 28, 2018Date of Patent: June 18, 2019Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Sunil Subrahmanyam Vasisht, Stephen Michael Wylie, Geoffrey Dagley, Micah Price, Jason Richard Hoover
-
Patent number: 10319007Abstract: A method for processing an image including a vehicle using machine learning can include determining a location of the client device. The method can further include receiving a first image of a vehicle from an image sensor of the client device and matching, using machine learning, the first image to one or more images of vehicles in a vehicle database to identify the vehicle. The vehicle database can list vehicles located at the determined location of the client device and images of the vehicles. The method can include retrieving vehicle information from the vehicle database, based on the identified vehicle, and obtaining comparison information based at least in part on the vehicle information. The method can include estimating a quote for the vehicle based on the comparison information and transmitting the estimated quote for display on the client device.Type: GrantFiled: March 8, 2018Date of Patent: June 11, 2019Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Sunil Subrahmanyam Vasisht, Stephen Michael Wylie, Geoffrey Dagley, Micah Price, Jason Richard Hoover
-
Patent number: 10274303Abstract: A device and method for measuring dimensional variation of a part, particularly total runout, is provided. The device includes an indicator check body, a clamping device within the indicator check body and an end cap that engages the indicator check body and the clamping device. When the indicator check body and the clamping device are engaged, the device is secured to the part allowing dimensional variations to be measured along the surface of the indicator check body.Type: GrantFiled: June 12, 2017Date of Patent: April 30, 2019Assignee: Ford Motor CompanyInventors: Jason Richard Savage, Robert Thomas Kraus, Jay Kupiszewski
-
Patent number: 10268925Abstract: The present disclosure relates to image preprocessing to improve object recognition. In one implementation, a system for preprocessing an image for object recognition may include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving the image, detecting a plurality of bounding boxes within the image, grouping the plurality of bounding boxes into a plurality of groups such that bounding boxes within a group have shared areas exceeding an area threshold, deriving a first subset of the plurality of bounding boxes by selecting bounding boxes having highest class confidence scores from at least one group, selecting a bounding box from the first subset having a highest score based on area and class confidence score, and outputting the selected bounding box.Type: GrantFiled: May 14, 2018Date of Patent: April 23, 2019Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Sunil Subrahmanyam Vasisht, Stephen Michael Wylie, Geoffrey Dagley, Micah Price, Jason Richard Hoover
-
Publication number: 20190106646Abstract: The present invention generally relates to compositions for use in lubricating oils. In certain aspects, the present invention is generally directed to boroxine compounds having alkyl groups where one or more of the alkyl groups contains at least 8 carbon atoms. Such compounds may present improved hydrolytic stability, compared to other boroxine compounds. Such boroxine compounds may be used, for example, to improve seal compatibility in an engine. Other aspects of the invention are generally directed to systems and methods for making such boroxine compounds, engine oils containing such boroxine compounds, methods of using such boroxine compounds, or the like.Type: ApplicationFiled: November 10, 2016Publication date: April 11, 2019Applicant: Afton Chemical CorporationInventors: Jason Richard Bell, Carl W. Bennett
-
Patent number: 10235762Abstract: The disclosed technology includes image-based systems and methods for object tracking within an asset area. Some exemplary methods include receiving, from an ingress detector, an ingress indication of a first object entering an asset area and receiving, from one or more image capture devices positioned to view respective portions of the asset area, data indicative of a plurality of captured images. The methods also include performing, by at least one processor, object classification of the first object based on the ingress indication, one or more of at least one of the plurality of captured images, and an identification signal detected by the ingress detector. The methods further include determining a first object location of the first object based at least in part on the object classification and outputting an indication of the first object location.Type: GrantFiled: September 12, 2018Date of Patent: March 19, 2019Assignee: CAPITAL ONE SERVICES, LLCInventors: Stephen Michael Wylie, Jason Richard Hoover, Geoffrey Dagley, Micah Price, Qiaochu Tang
-
Patent number: 10235602Abstract: An artificial intelligence system for identifying attributes in an image. The system may include a processor in communication with a client device; and a storage medium. The storage medium may store instructions that, when executed, configure the processor to perform operations including: extracting first features; categorizing the first images in a first group or a second group; modifying first metadata associated with each image in the first images to include a binary label; calculating a classification function; classifying a second plurality of images using the classification function; extracting second features from the second images classified in the first group; categorizing the second images in the first group by attribute; calculating an attribute identification function that identifies attributes of the second images; and identifying at least one attribute associated with a client image using the attribute identification function, the client image being received from the client device.Type: GrantFiled: April 9, 2018Date of Patent: March 19, 2019Assignee: CAPITAL ONE SERVICES, LLCInventors: Sunil Subrahmanyam Vasisht, Geoffrey Dagley, Qiaochu Tang, Sean Reddy, Jason Richard Hoover, Stephen Michael Wylie, Micah Price
-
Publication number: 20190069508Abstract: An electronic pet door is provided herein. The electronic pet door includes a pivotal flap and a frame that defines a through-way. A rotatable knob is mounted to the frame and has a handle portion and a stop wall. The handle portion and stop wall include various profiles and configurations that work in concert to control the flap's direction of pivotal movement. In a first configuration, the flap may swing outwardly or inwardly. A second configuration prevents the flap from swinging inwardly. A third configuration prevents the flap from swinging outwardly. A fourth configuration places the flap is in a locked position to prevent swinging in either direction. The electronic door also includes an electronic latch mechanism which selectively latches and unlatches the flap. The latch mechanism unlatches the flap in response to a wireless signal from an electronic transmitter that may be affixed to a pet.Type: ApplicationFiled: August 17, 2018Publication date: March 7, 2019Inventors: Cody Lee Stricklin, Marc Edward Brush, Jason Richard Graves
-
Publication number: 20190048332Abstract: Embodiments provided herein relate to methods and compositions for preparing an immobilized library of barcoded DNA fragments of a target nucleic acid, identifying genomic variants, determining the contiguity information, phasing information, and methylation status of the target nucleic acid.Type: ApplicationFiled: October 29, 2018Publication date: February 14, 2019Inventors: Frank J. Steemers, Kevin L. Gunderson, Fan Zhang, Jason Richard Betley, Niall Anthony Gormley, Wouter Meuleman, Jacqueline Weir, Avgousta Ioannou, Gareth Jenkins, Rosamond Jackson, Natalie Morrell, Dmitry K. Pokholok, Steven J. Norberg, Molly He, Amirali Kia, Igor Goryshin, Rigo Pantoja
-
Publication number: 20190040382Abstract: Embodiments provided herein relate to methods and compositions for preparing an immobilized library of barcoded DNA fragments of a target nucleic acid, identifying genomic variants, determining the contiguity information, phasing information, and methylation status of the target nucleic acid.Type: ApplicationFiled: October 16, 2015Publication date: February 7, 2019Applicant: ILLUMINA CAMBRIDGE LIMITEDInventors: Frank J. Steemers, Kevin L. Gunderson, Fan Zhang, Jason Richard Betley, Niall Anthony Gormley, Wouter Meuleman, Jacqueline Weir, Avgousta Ioannou, Gareth Jenkins, Rosamond Jackson, Natalie Morrell, Dmitry K. Pokholok, Steven J. Norberg, Molly He, Amirali Kia, Igor Goryshin, Rigo Pantoja
-
Patent number: 10157331Abstract: The present disclosure relates to image preprocessing to improve object recognition. In one implementation, a system for preprocessing an image for object recognition may include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving the image, detecting a plurality of bounding boxes within the image, grouping the plurality of bounding boxes into a plurality of groups such that bounding boxes within a group have shared areas exceeding an area threshold, deriving a first subset of the plurality of bounding boxes by selecting bounding boxes having highest class confidence scores from at least one group, selecting a bounding box from the first subset having a highest score based on area and class confidence score, and outputting the selected bounding box.Type: GrantFiled: March 8, 2018Date of Patent: December 18, 2018Assignee: Capital One Services, LLCInventors: Qiaochu Tang, Sunil Subrahmanyam Vasisht, Stephen Michael Wylie, Geoffrey Dagley, Micah Price, Jason Richard Hoover
-
Publication number: 20180356200Abstract: A device and method for measuring dimensional variation of a part, particularly total runout, is provided. The device includes an indicator check body, a clamping device within the indicator check body and an end cap that engages the indicator check body and the clamping device. When the indicator check body and the clamping device are engaged, the device is secured to the part allowing dimensional variations to be measured along the surface of the indicator check body.Type: ApplicationFiled: June 12, 2017Publication date: December 13, 2018Applicant: Ford Motor CompanyInventors: Jason Richard Savage, Robert Thomas Kraus, Jay Kupiszewski