Patents by Inventor Heather Underwood
Heather Underwood 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).
-
Patent number: 10803275Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: GrantFiled: October 4, 2018Date of Patent: October 13, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Patent number: 10380174Abstract: A method for template based recognition of food product information includes capturing an image of food product packaging and extracting an attribute from the image. The attribute is used to find a matching template in a template database. The matching template is then used to extract food product information from the image.Type: GrantFiled: February 5, 2016Date of Patent: August 13, 2019Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Varun Bhagwan, Justin Ormont, Heather Underwood
-
Publication number: 20190042817Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: ApplicationFiled: October 4, 2018Publication date: February 7, 2019Applicant: International Business Machines CorporationInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Patent number: 10140495Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: GrantFiled: October 3, 2016Date of Patent: November 27, 2018Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Publication number: 20170024594Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: ApplicationFiled: October 3, 2016Publication date: January 26, 2017Applicant: International Business Machines CorporationInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Patent number: 9508116Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: GrantFiled: April 16, 2014Date of Patent: November 29, 2016Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Publication number: 20160154823Abstract: A method for template based recognition of food product information includes capturing an image of food product packaging and extracting an attribute from the image. The attribute is used to find a matching template in a template database. The matching template is then used to extract food product information from the image.Type: ApplicationFiled: February 5, 2016Publication date: June 2, 2016Applicant: International Business Machines CorporationInventors: VARUN BHAGWAN, JUSTIN ORMONT, HEATHER UNDERWOOD
-
Patent number: 9292565Abstract: A method for template based recognition of food product information includes capturing an image of food product packaging and extracting an attribute from the image. The attribute is used to find a matching template in a template-database. The matching template is then used to extract food product information from the image.Type: GrantFiled: June 30, 2010Date of Patent: March 22, 2016Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Varun Bhagwan, Justin Ormont, Heather Underwood
-
Publication number: 20140226878Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: ApplicationFiled: April 16, 2014Publication date: August 14, 2014Applicant: International Business Machines CorporationInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Patent number: 8792748Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: GrantFiled: October 12, 2010Date of Patent: July 29, 2014Assignee: International Business Machines CorporationInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Patent number: 8505823Abstract: A method for noise removal from color barcode images includes acquiring a barcode image using a color imaging array and separating the barcode image into color channels. Weighting factors are associated with the color channels and at least one weighting factor is reduced. The weighting factors are applied to the color channels to produce a first transformed image. A portion of the first transformed image is analyzed to produce a first set of decoded data from the barcode.Type: GrantFiled: June 30, 2010Date of Patent: August 13, 2013Assignee: International Business Machine CorporationInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Publication number: 20120087551Abstract: A method for deconvolution of digital images includes obtaining a degraded image from a digital sensor, a processor accepting output from the digital sensor and recognizing a distorted element within the image. The distorted element is compared with a true shape of the element to produce a degrading function. The degrading function is deconvolved from at least a portion of the image to improve image quality of the image. A method of indirectly decoding a barcode includes obtaining an image of a barcode using an optical sensor in a mobile computing device, the image comprising barcode marks and a textual character. The textual character is optically recognized and an image degrading characteristic is identified from the textual character. Compensating for the image degrading characteristic renders previously undecodable barcode marks decodable. A system for deconvolution of digital images is also included.Type: ApplicationFiled: October 12, 2010Publication date: April 12, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Publication number: 20120000983Abstract: A method for noise removal from color barcode images includes acquiring a barcode image using a color imaging array and separating the barcode image into color channels. Weighting factors are associated with the color channels and at least one weighting factor is reduced. The weighting factors are applied to the color channels to produce a first transformed image. A portion of the first transformed image is analyzed to produce a first set of decoded data from the barcode.Type: ApplicationFiled: June 30, 2010Publication date: January 5, 2012Inventors: Varun Bhagwan, Timothy Liu, Justin Ormont, Heather Underwood
-
Publication number: 20120005222Abstract: A method for template based recognition of food product information includes capturing an image of food product packaging and extracting an attribute from the image. The attribute is used to find a matching template in a template-database. The matching template is then used to extract food product information from the image.Type: ApplicationFiled: June 30, 2010Publication date: January 5, 2012Inventors: Varun Bhagwan, Justin Ormont, Heather Underwood