Patents by Inventor Eric Wengrowski

Eric Wengrowski 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).

  • Light-field messaging to embed a hidden message into a carrier
    Patent number: 11790475
    Abstract: A method of light messaging, in which a hidden message is transmitted via coded image emitted from a display device and retrieved using a camera, comprises training a camera-display transfer model that receives images with hidden messages from an embedding model and generates modified coded images based on training data that accounts for properties of displays and cameras, the modified coded images delivered to a recovery model that decodes the hidden messages and outputs hidden message determinations, training both the embedding and recovery models using the CDTF model and training data to minimize differences between the input hidden messages and the hidden message determinations. After training the CDTF model and other models, embedding a hidden message in a carrier image using the embedding model, displaying the coded image using the display device, receiving the coded image at the camera, and retrieving the hidden message using the recovery model.
    Type: Grant
    Filed: June 10, 2020
    Date of Patent: October 17, 2023
    Assignee: Rutgers, The State University of New Jersey
    Inventors: Eric Wengrowski, Kristin Dana
  • LIGHT-FIELD MESSAGING
    Publication number: 20220261944
    Abstract: A method of light messaging, in which a hidden message is transmitted via coded image emitted from a display device and retrieved using a camera, comprises training a camera-display transfer model that receives images with hidden messages from an embedding model and generates modified coded images based on training data that accounts for properties of displays and cameras, the modified coded images delivered to a recovery model that decodes the hidden messages and outputs hidden message determinations, training both the embedding and recovery models using the CDTF model and training data to minimize differences between the input hidden messages and the hidden message determinations. After training the CDTF model and other models, embedding a hidden message in a carrier image using the embedding model, displaying the coded image using the display device, receiving the coded image at the camera, and retrieving the hidden message using the recovery model.
    Type: Application
    Filed: June 10, 2020
    Publication date: August 18, 2022
    Inventors: Eric Wengrowski, Kristin Dana
  • Medical Image Object Detection with Dense Feature Pyramid Network Architecture in Machine Learning
    Publication number: 20190139216
    Abstract: For object detection, deep learning is applied with an architecture designed for low contrast objects, such as lymph nodes. The architecture uses a combination of dense deep learning or features, which employs feed-forward connections between convolutions layers, and a pyramidal arrangement of the dense deep learning using different resolutions.
    Type: Application
    Filed: November 3, 2017
    Publication date: May 9, 2019
    Inventors: Bogdan Georgescu, Eric Wengrowski, Siqi Liu, Daguang Xu, Dorin Comaniciu, Shaohua Kevin Zhou