Patents by Inventor Naama ANTEBI

Naama ANTEBI 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).

  • Facial anonymization with consistent facial attribute preservation in video
    Patent number: 11526626
    Abstract: To consistently anonymize video, an identity-preserving encoder may be trained with a decoder to preserve identity information unique to an individual in an encoded space. The identity-preserving encoder may encode source video images of a source identity to generate identity-preserving encoded data representing the source identity. A de-identification engine may generate de-identifying encoded data representing a different target identity. A transformation may be generated based on a difference between the identity-preserving and de-identifying encoded data, representing swapping the source identity with the target identity. The identity may be consistently swapped from the source to target in the encoded space by applying the same transformation to the identity-preserving encoded data for the source images.
    Type: Grant
    Filed: July 10, 2020
    Date of Patent: December 13, 2022
    Assignee: DE-IDENTIFICATION LTD.
    Inventors: Eliran Kuta, Sella Blondheim, Gil Perry, Yoav Hacohen, Amitay Nachmani, Naama Antebi, Matan Ben-Yosef, Or Gorodissky
  • FACIAL ANONYMIZATION WITH CONSISTENT FACIAL ATTRIBUTE PRESERVATION IN VIDEO
    Publication number: 20220012362
    Abstract: To consistently anonymize video, an identity-preserving encoder may be trained with a decoder to preserve identity information unique to an individual in an encoded space. The identity-preserving encoder may encode source video images of a source identity to generate identity-preserving encoded data representing the source identity. A de-identification engine may generate de-identifying encoded data representing a different target identity. A transformation may be generated based on a difference between the identity-preserving and de-identifying encoded data, representing swapping the source identity with the target identity. The identity may be consistently swapped from the source to target in the encoded space by applying the same transformation to the identity-preserving encoded data for the source images.
    Type: Application
    Filed: July 10, 2020
    Publication date: January 13, 2022
    Applicant: DE-IDENTIFICATION LTD.
    Inventors: Eliran KUTA, Sella BLONDHEIM, Gil PERRY, Yoav HACOHEN, Amitay NACHMANI, Naama ANTEBI, Matan BEN-YOSEF, Or GORODISSKY