Patents by Inventor Donald Tanguay
Donald Tanguay 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: 9721182Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: GrantFiled: December 21, 2016Date of Patent: August 1, 2017Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Patent number: 9530076Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: GrantFiled: February 16, 2015Date of Patent: December 27, 2016Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Publication number: 20150161480Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: ApplicationFiled: February 16, 2015Publication date: June 11, 2015Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Patent number: 8958629Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: GrantFiled: April 22, 2014Date of Patent: February 17, 2015Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Patent number: 8867866Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: GrantFiled: April 14, 2014Date of Patent: October 21, 2014Assignee: A9.com, Inc.Inventors: Mark R. Ruzon, Donald Tanguay
-
Patent number: 8825612Abstract: The present invention relates to a method, system, and a computer program product for delivering content to a communication device, in response to an image sent by the communication device. The received image is matched with a plurality of images, and, when a match is found for the received image, content corresponding to the image is delivered to the communication device. The plurality of images is stored in an image database, and the corresponding content is stored in a content repository. The present invention enables a content provider to automatically update the image database and the content repository without any human intervention.Type: GrantFiled: February 28, 2013Date of Patent: September 2, 2014Assignee: A9.com, Inc.Inventors: Mark Andrew Ruzon, Keshav Menon, Gurumurthy D. Ramkumar, Donald Tanguay, Supratik Bhattacharyya, Gautam Bhargava
-
Publication number: 20140226868Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: ApplicationFiled: April 14, 2014Publication date: August 14, 2014Applicant: A9.com, Inc.Inventors: Mark R. Ruzon, Donald Tanguay
-
Publication number: 20140226913Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: ApplicationFiled: April 22, 2014Publication date: August 14, 2014Applicant: A9.com, Inc.Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Patent number: 8705848Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: GrantFiled: February 6, 2013Date of Patent: April 22, 2014Assignee: A9.com, Inc.Inventors: Mark Andrew Ruzon, Raghavan Manmatha, Donald Tanguay
-
Patent number: 8699828Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: GrantFiled: September 30, 2013Date of Patent: April 15, 2014Assignee: A9.com, Inc.Inventors: Mark Andrew Ruzon, Donald Tanguay
-
Publication number: 20140056480Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: ApplicationFiled: September 30, 2013Publication date: February 27, 2014Applicant: A9.com, Inc.Inventors: MARK R. RUZON, Donald Tanguay
-
Patent number: 8548279Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: GrantFiled: February 21, 2013Date of Patent: October 1, 2013Assignee: A9.com, Inc.Inventors: Mark Andrew Ruzon, Donald Tanguay
-
Patent number: 8412687Abstract: The present invention relates to a method, system, and a computer program product for delivering content to a communication device, in response to an image sent by the communication device. The received image is matched with a plurality of images, and, when a match is found for the received image, content corresponding to the image is delivered to the communication device. The plurality of images is stored in an image database, and the corresponding content is stored in a content repository. The present invention enables a content provider to automatically update the image database and the content repository without any human intervention.Type: GrantFiled: February 27, 2012Date of Patent: April 2, 2013Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Keshav Menon, Gurumurthy D. Ramkumar, Donald Tanguay, Supratik Bhattacharyya, Gautam Bhargava
-
Patent number: 8406507Abstract: A method, system and computer program product for representing an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: GrantFiled: January 14, 2009Date of Patent: March 26, 2013Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Patent number: 8401342Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: GrantFiled: January 16, 2009Date of Patent: March 19, 2013Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Donald Tanguay
-
Patent number: 8126858Abstract: The present invention relates to a method, system, and a computer-readable storage medium containing executable instructions for delivering content to a communication device, in response to an image sent by the communication device. The received image is matched with a plurality of images, and, when a match is found for the received image, content corresponding to the matching image is delivered to the communication device. The plurality of images is stored in an image database, and the corresponding content is stored in a content repository. The present invention enables a content provider to automatically update the image database and the content repository without any human intervention.Type: GrantFiled: September 19, 2008Date of Patent: February 28, 2012Assignee: A9.com, Inc.Inventors: Mark A. Ruzon, Keshav Menon, Gurumurthy D. Ramkumar, Donald Tanguay, Supratik Bhattacharyya, Gautam Bhargava
-
Publication number: 20100183229Abstract: A method, system and computer program product for matching images is provided. The images to be matched are represented by feature points and feature vectors and orientations associated with the feature points. First, putative correspondences are determined by using feature vectors. A subset of putative correspondences is selected and the topological equivalence of the subset is determined. The topologically equivalent subset of putative correspondences is used to establish a motion estimation model. An orientation consistency test is performed on the putative correspondences and the corresponding motion estimation transformation that is determined, to avoid an infeasible transformation. A coverage test is performed on the matches that satisfy orientation consistency test. The candidate matches that do not cover a significant portion of one of the images are rejected. The final match images are provided in the order of decreasing matching, in case of multiple images satisfying all the test requirements.Type: ApplicationFiled: January 16, 2009Publication date: July 22, 2010Inventors: Mark A. Ruzon, Donald Tanguay
-
Publication number: 20100177966Abstract: A method, system and computer program product for representing an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in lo the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.Type: ApplicationFiled: January 14, 2009Publication date: July 15, 2010Inventors: Mark A. Ruzon, Raghavan Manmatha, Donald Tanguay
-
Publication number: 20070248350Abstract: An exemplary method for automatically generating a computed design of a composite camera having multiple digital imaging devices comprises obtaining a target volume to be captured by the composite camera, obtaining a target resolution for capturing the target volume, generating a representation of a view frustum of each of a plurality of digital imaging devices based on at least one characteristic of each device, organizing the plurality of digital imaging devices based on the view frusta, selecting a set of digital imaging devices from the organized digital imaging devices based on at least one characteristic of each selected device, the view frusta of the set of digital imaging devices substantially covering the target volume with at least the target resolution, positioning the set of digital imaging devices based on each device's physical characteristics, and generating a computed design of the composite camera comprising the positioned digital imaging devices together with a mechanical fixture to hold theType: ApplicationFiled: April 25, 2006Publication date: October 25, 2007Inventors: Henry Baker, Ian Robinson, Donald Tanguay
-
Publication number: 20060244817Abstract: A method and system for videoconferencing between parties at N sites. Specifically, a virtual space arrangement of N sites is created. Video sequences of N?1 remote sites are simultaneously displayed on a non-planar display arranged around a local party at a local site consistent with the virtual space arrangement. The displayed images of the remote parties are scaled consistently with their true physical sizes at their distances from the local party in the virtual space arrangement. Real-time video streams of the local party are captured from a plurality of viewpoints and are used to generate N?1 video view streams representing views of the local party from approximately the local display locations of the N?1 remote parties.Type: ApplicationFiled: April 29, 2005Publication date: November 2, 2006Inventors: Michael Harville, Donald Tanguay, Henry Baker, W. Culbertson