Patents by Inventor Karen A. Panetta
Karen A. Panetta 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: 20240062530Abstract: A system for training a neural network includes a neural network configured to receive a training input in an image space and produce an enhanced image. The system further includes an error signal generator configured to compare the enhanced image to a ground truth and generate an error signal that is communicated back to the neural network to train the neural network. Additionally, the system includes a neural input enhancer configured to modify the training input in response to receiving at least one of an output from the neural network or the error signal. Modifying the training input improves one of an efficiency or a training result of the neural network beyond the communication of the error signal to only the neural network.Type: ApplicationFiled: December 17, 2021Publication date: February 22, 2024Applicants: Trustees of Tufts College, Research Foundation of the City University of New YorkInventors: Karen A. Panetta, Shreyas Kamath Kalasa Mohandas, Shishir Paramathma Rao, Srijith Rajeev, Rahul Rajendran, Sos S. Agaian
-
Publication number: 20240055101Abstract: The disclosure generally relates to the artificial intelligence (AI) automatic methods, computer program product, and systems and methodology for dietary and medical treatment planning, food waste estimation, analyzing three-dimensional food image construction, measurement, nutrient estimation, nutritional assessment, evaluation, prediction and management. More particularly, the embodiments described herein relate to utilizing an AI-based algorithm that can automatically, detect food items from images acquired by cameras for dietary assessment, dietary planning, and for estimating food waste. In one aspect, the method may include food calorie estimation techniques using machine learning and computer vision techniques for dietary assessment. In another aspect, the tools may apply to personalized nutrition. The method may also include the automation of nutrition planning.Type: ApplicationFiled: December 17, 2021Publication date: February 15, 2024Applicants: Trustees of Tufts College, Research Foundation of the City University of New YorkInventors: Karen A. Panetta, Shishir Paramathma Rao, Shreyas Kamath Kalasa Mohandas, Rahul Rajendran, Srijith Rajeev, Erin Hennessy, Christina Economos, Eleanor Tate Shonkoff, Sos S. Agaian
-
Publication number: 20240046612Abstract: A method comprising: obtaining a plurality of data sets, each of the plurality of data sets being generated, at least in part, by using by a different one of a plurality of sensors, each of a plurality of sensors including a wearable sensor that is worn by a user or a sensor that is positioned at a same location as the user; combining the plurality of data sets to produce a fused data set; processing the fused data set to identify at least one of a performance of the user in completing a task, a cognitive load of the user, and/or one or more objects that are positioned at the same location as the user; and outputting an indication of a state of the user based on an outcome of the processing.Type: ApplicationFiled: December 17, 2021Publication date: February 8, 2024Applicants: Trustees of Tufts College, Research Foundation of the City University of New YorkInventors: Karen A. Panetta, Sos S. Agaian, Aruna Ramesh, Shishir Paramathma Rao, Shreyas Kamath Kalasa Mohandas, Srijith Rajeev, Rahul Rajendran
-
Publication number: 20230099984Abstract: The present disclosure includes systems and methods for multimedia image analytic including automated binarization, segmentation, and enhancement using bio-inspired based visual morphology schemes. The present disclosure further includes systems and methods for biometric multimedia content authentication using extracted geometric features and one or more of the binarization, segmentation, and enhancement methods.Type: ApplicationFiled: August 12, 2022Publication date: March 30, 2023Inventors: Karen PANETTA, Shreyas KAMATH KALASA MOHANDAS, Sos AGAIAN
-
Patent number: 11615559Abstract: The present disclosure includes systems and methods for color transfer. The method includes receiving a target image, and determining dominant source colors. The method further includes transforming the target image into a color model including a target luminance component and a target color information component. Additionally, the method includes segmenting the target image into a plurality of target segments based on the target color information component or the target luminance component and extracting dominant target colors from the target image by extracting information for at least one of the dominant target colors from each target segment of the plurality of target segments. Further, the method includes generating a color mapping relationship between the dominant target colors and the dominant source colors, and creating a recolored target image using the color mapping relationship.Type: GrantFiled: October 11, 2021Date of Patent: March 28, 2023Assignees: Trustees of Tufts College, The Board of Regents of the University of Texas SystemInventors: Karen Panetta, Long Bao, Sos Agaian
-
Patent number: 11450087Abstract: The present disclosure includes systems and methods for multimedia image analytic including automated binarization, segmentation, and enhancement using bio-inspired based visual morphology schemes. The present disclosure further includes systems and methods for biometric multimedia content authentication using extracted geometric features and one or more of the binarization, segmentation, and enhancement methods.Type: GrantFiled: April 18, 2019Date of Patent: September 20, 2022Inventors: Karen Panetta, Shreyas Kamath Kalasa Mohandas, Sos Agaian
-
Publication number: 20220028126Abstract: The present disclosure includes systems and methods for color transfer. The method includes receiving a target image, and determining dominant source colors. The method further includes transforming the target image into a color model including a target luminance component and a target color information component. Additionally, the method includes segmenting the target image into a plurality of target segments based on the target color information component or the target luminance component and extracting dominant target colors from the target image by extracting information for at least one of the dominant target colors from each target segment of the plurality of target segments. Further, the method includes generating a color mapping relationship between the dominant target colors and the dominant source colors, and creating a recolored target image using the color mapping relationship.Type: ApplicationFiled: October 11, 2021Publication date: January 27, 2022Inventors: Karen Panetta, Long Bao, Sos Agaian
-
Patent number: 11158091Abstract: The present disclosure includes systems and methods for color transfer. The method includes receiving a target image, and determining dominant source colors. The method further includes transforming the target image into a color model including a target luminance component and a target color information component. Additionally, the method includes segmenting the target image into a plurality of target segments based on the target color information component or the target luminance component and extracting dominant target colors from the target image by extracting information for at least one of the dominant target colors from each target segment of the plurality of target segments. Further, the method includes generating a color mapping relationship between the dominant target colors and the dominant source colors, and creating a recolored target image using the color mapping relationship.Type: GrantFiled: September 7, 2017Date of Patent: October 26, 2021Assignees: Trustees of Tufts College, THE BOARD OF REGENTS OF THE UNIVERSITY OF TEXAS SYSTEMInventors: Karen Panetta, Long Bao, Sos Agaian
-
Patent number: 11076950Abstract: The present disclosure relates to electrolarynx devices, systems, and their use. In particular, the present disclosure relates to methods and compositions (e.g., devices) that provide electrolarynx (EL) users with improved speech quality.Type: GrantFiled: April 30, 2018Date of Patent: August 3, 2021Assignee: TRUSTEES OF TUFTS COLLEGEInventors: Karen Panetta, Chiamaka Chima, Paul Lehrman
-
Publication number: 20210124977Abstract: The present disclosure includes systems and methods for multimedia image analytic including automated binarization, segmentation, and enhancement using bio-inspired based visual morphology schemes. The present disclosure further includes systems and methods for biometric multimedia content authentication using extracted geometric features and one or more of the binarization, segmentation, and enhancement methods.Type: ApplicationFiled: April 18, 2019Publication date: April 29, 2021Inventors: Karen PANETTA, Shreyas KAMATH KALASA MOHANDAS, Sos AGAIAN
-
Publication number: 20200069414Abstract: The present disclosure relates to electrolarynx devices, systems, and their use. In particular, the present disclosure relates to methods and compositions (e.g., devices) that provide electrolarynx (EL) users with improved speech quality.Type: ApplicationFiled: April 30, 2018Publication date: March 5, 2020Inventors: Karen Panetta, Chiamaka Chima, Paul Lehrman
-
Publication number: 20190279402Abstract: The present disclosure includes systems and methods for color transfer. The method includes receiving a target image, and determining dominant source colors. The method further includes transforming the target image into a color model including a target luminance component and a target color information component. Additionally, the method includes segmenting the target image into a plurality of target segments based on the target color information component or the target luminance component and extracting dominant target colors from the target image by extracting information for at least one of the dominant target colors from each target segment of the plurality of target segments. Further, the method includes generating a color mapping relationship between the dominant target colors and the dominant source colors, and creating a recolored target image using the color mapping relationship.Type: ApplicationFiled: September 7, 2017Publication date: September 12, 2019Inventors: Karen Panetta, Long Bao, Sos Agaian
-
Patent number: 9396531Abstract: An image/video may be analyzed to determine quality of its attributes, including local, global and pixel colorfulness, sharpness, and contrast to obtain an image quality measure. Invented quality may be obtained for captured images or videos and compared to a database or reference value of quality measures to identify quality of products, component anomalies, and product matches.Type: GrantFiled: December 22, 2014Date of Patent: July 19, 2016Assignees: Tufts University, The Board of Regents of The University of Texas SystemInventors: Karen Panetta, Sos Agaian, Chen Gao
-
Patent number: 9299130Abstract: Methods and apparatus to providing image fusion using a number of image processing approaches. In one embodiment, a single image is processed and image fusion is performed. In exemplary embodiments of the invention, image enhancement, denoising, edge detection, etc., can be provided.Type: GrantFiled: March 14, 2014Date of Patent: March 29, 2016Assignee: TRUSTEES OF TUFTS COLLEGEInventors: Karen A. Panetta, Shahan Nercessian, Sos Agaian
-
Publication number: 20150243041Abstract: An image/video may be analyzed to determine quality of its attributes, including local, global and pixel colorfulness, sharpness, and contrast to obtain an image quality measure. Invented quality may be obtained for captured images or videos and compared to a database or reference value of quality measures to identify quality of products, component anomalies, and product matches.Type: ApplicationFiled: December 22, 2014Publication date: August 27, 2015Inventors: Karen Panetta, Sos Agaian, Chen Gao
-
Publication number: 20140341481Abstract: Methods and apparatus to providing image fusion using a number of image processing approaches. In one embodiment, a single image is processed and image fusion is performed. In exemplary embodiments of the invention, image enhancement, denoising, edge detection, etc., can be provided.Type: ApplicationFiled: March 14, 2014Publication date: November 20, 2014Inventors: Karen A. Panetta, Shahan Nercessian, Sos Agaian
-
Publication number: 20130294613Abstract: The present invention relates to electrolarynx devices and their use. In particular, the present invention relates to methods and compositions (e.g., devices) to provide electrolarynx (EL) users with greater intonation in their speech.Type: ApplicationFiled: July 28, 2011Publication date: November 7, 2013Inventors: George Nagel, Jael Jose, Nicholas Matiasz, Karen Panetta
-
Patent number: 8285070Abstract: Methods and apparatus for restoration of a digital image. In one embodiment, a method for repairing a defect in a digital image to provide a restored image comprises determining a plurality of pixel locations to form a neighborhood relating to the defect and whether or not the neighborhood has a well-defined, dark border along its edge. Should the neighborhood not have dark border, one embodiment of the method entails processing the neighborhood to bring the neighborhood approximately to uniform darkness, processing the neighborhood to match surroundings in the digital image, copying an edge of a neighborhood in the digital image into the processed neighborhood, processing pixels of the edge to repair the copied edge pixels, and outputting the restored image for display to a user.Type: GrantFiled: April 7, 2009Date of Patent: October 9, 2012Assignee: The Trustees of Tufts CollegeInventors: Karen A. Panetta, Sos Agaian, Aaron Greenblatt
-
Patent number: 8285076Abstract: Methods and apparatus for image processing include performing visual sub-band decomposition of an image using human visual system characteristics to generate a plurality of sub-band decomposed images, independently processing the plurality of sub-band decomposed images with at least one application, and fusing the independently processed sub-band decomposed images to reconstruct an output image.Type: GrantFiled: March 26, 2009Date of Patent: October 9, 2012Assignee: The Trustees of Tufts CollegeInventors: Karen A. Panetta, Sos Agaian
-
Publication number: 20090274386Abstract: Methods and apparatus for restoration of a digital image. In one embodiment, a method for repairing a defect in a digital image to provide a restored image comprises determining a plurality of pixel locations to form a neighborhood relating to the defect and whether or not the neighborhood has a well-defined, dark border along its edge. Should the neighborhood not have dark border, one embodiment of the method entails processing the neighborhood to bring the neighborhood approximately to uniform darkness, processing the neighborhood to match surroundings in the digital image, copying an edge of a neighborhood in the digital image into the processed neighborhood, processing pixels of the edge to repair the copied edge pixels, and outputting the restored image for display to a user.Type: ApplicationFiled: April 7, 2009Publication date: November 5, 2009Inventors: Karen A. Panetta, Sos Agaian, Aaron Greenblatt