Patents by Inventor Huguens Jean
Huguens Jean 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: 20240168993Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: ApplicationFiled: December 5, 2023Publication date: May 23, 2024Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Patent number: 11868394Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: GrantFiled: October 20, 2021Date of Patent: January 9, 2024Assignee: DST Technologies, Inc.Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Publication number: 20220044055Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: ApplicationFiled: October 20, 2021Publication date: February 10, 2022Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Patent number: 11182640Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: GrantFiled: August 2, 2019Date of Patent: November 23, 2021Assignee: DST Technologies, Inc.Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Publication number: 20210049401Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: ApplicationFiled: August 2, 2019Publication date: February 18, 2021Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Patent number: 10373012Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: GrantFiled: April 10, 2017Date of Patent: August 6, 2019Assignee: CAPTRICITY, INC.Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Publication number: 20170255840Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: ApplicationFiled: April 10, 2017Publication date: September 7, 2017Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Patent number: 9652688Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: GrantFiled: May 15, 2015Date of Patent: May 16, 2017Assignee: Captricity, Inc.Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Publication number: 20160148074Abstract: Methods, apparatuses, and embodiments related to analyzing the content of digital images. A computer extracts multiple sets of visual features, which can be keypoints, based on an image of a selected object. Each of the multiple sets of visual features is extracted by a different visual feature extractor. The computer further extracts a visual word count vector based on the image of the selected object. An image query is executed based on the extracted visual features and the extracted visual word count vector to identify one or more candidate template objects of which the selected object may be an instance. When multiple candidate template objects are identified, a matching algorithm compares the selected object with the candidate template objects to determine a particular candidate template of which the selected object is an instance.Type: ApplicationFiled: May 15, 2015Publication date: May 26, 2016Inventors: Huguens Jean, Yoriyasu Yano, Hui Peng Hu, Kuang Chen
-
Publication number: 20120144247Abstract: A system, apparatus and method for providing training through incorporation of metaphorical expressions are provided. A method includes receiving selected user preferences via a computer. The method also includes displaying a story board based on the selected user preferences, where the display shows text and images and the computer simultaneously plays vocals. Further, the method includes prompting the user to perform a task. Where the user successfully completes the task, the method includes taking the user to a next task. If the user does not successfully complete the task, the method includes repeating the story board and prompting the user to attempt the task again until the task is successfully completed.Type: ApplicationFiled: December 5, 2011Publication date: June 7, 2012Inventors: Kimberly Ann Brown, Huguens Jean