公开(公告)号：US20220215205A1

公开(公告)日：2022-07-07

申请号：US17142030

申请日：2021-01-05

Applicant: ADOBE INC.

Inventor： Viswanathan Swaminathan ,  John Philip Collomosse ,  Eric Nguyen

IPC: G06K9/62 ,  G06K9/46 ,  G06K9/00 ,  G06T7/60 ,  G06F16/532 ,  G06F16/583 ,  G06N20/00

Abstract: A visual search system facilitates retrieval of provenance information using a machine learning model to generate content fingerprints that are invariant to benign transformations while being sensitive to manipulations. The machine learning model is trained on a training image dataset that includes original images, benign transformed variants of the original images, and manipulated variants of the original images. A loss function is used to train the machine learning model to minimize distances in an embedding space between benign transformed variants and their corresponding original images and increase distances between the manipulated variants and their corresponding original images.

公开(公告)号：US12147495B2

公开(公告)日：2024-11-19

申请号：US17142030

申请日：2021-01-05

Applicant: ADOBE INC.

Inventor： Viswanathan Swaminathan ,  John Philip Collomosse ,  Eric Nguyen

IPC: G06F18/214 ,  G06F16/532 ,  G06F16/583 ,  G06F18/213 ,  G06N20/00 ,  G06T7/60 ,  G06V10/40 ,  G06V20/00

Abstract: A visual search system facilitates retrieval of provenance information using a machine learning model to generate content fingerprints that are invariant to benign transformations while being sensitive to manipulations. The machine learning model is trained on a training image dataset that includes original images, benign transformed variants of the original images, and manipulated variants of the original images. A loss function is used to train the machine learning model to minimize distances in an embedding space between benign transformed variants and their corresponding original images and increase distances between the manipulated variants and their corresponding original images.