公开(公告)号：US12067796B2

公开(公告)日：2024-08-20

申请号：US17719199

申请日：2022-04-12

申请人： Onfido Ltd.

发明人： Jochem Gietema ,  Mohan Mahadevan ,  Roberto Annunziata ,  Pieter-jan Reynaert ,  Elizaveta Ivanova ,  Yuanwei Li ,  Tal Shaharabany ,  Shachar Ben Dayan ,  Erez Farhan ,  Francesco Picciotti

IPC分类号： G06V30/41 ,  G06V30/19

CPC分类号： G06V30/41 ,  G06V30/19013 ,  G06V30/19173

摘要： Described are methods and systems for detecting fraud in documents. First images of a first set of genuine documents and second images of a second set of genuine documents are obtained. A printed feature, spacings between printed features in the first images, and positions of printed features in the second images are selected. Selected features, spacings and positions are annotated to obtain original landmark locations for each printed feature, spacing and position. Annotated features, spacings and positions are transformed to obtain transformed features, transformed spacings and transformed positions. The transformed features, spacings and positions are combined with a noise model to generate modified features, modified spacings and modified positions. Each modified feature, modified spacing and modified position comprises annotations indicating modified landmark locations. Input data for a machine learning model is generated using original landmark locations and modified landmark locations. The machine learning model is trained using the input data.

公开(公告)号：US20220351532A1

公开(公告)日：2022-11-03

申请号：US17719199

申请日：2022-04-12

申请人： Onfido Ltd.

发明人： Jochem Gietema ,  Mohan Mahadevan ,  Roberto Annunziata ,  Pieter-jan Reynaert ,  Elizaveta Ivanova ,  Yuanwei Li ,  Tal Shaharabany ,  Shachar Ben Dayan ,  Erez Farhan ,  Francesco Picciotti

IPC分类号： G06V30/41 ,  G06V30/19

摘要： Described are methods and systems for detecting fraud in documents. First images of a first set of genuine documents and second images of a second set of genuine documents are obtained. A printed feature, spacings between printed features in the first images, and positions of printed features in the second images are selected. Selected features, spacings and positions are annotated to obtain original landmark locations for each printed feature, spacing and position. Annotated features, spacings and positions are transformed to obtain transformed features, transformed spacings and transformed positions. The transformed features, spacings and positions are combined with a noise model to generate modified features, modified spacings and modified positions. Each modified feature, modified spacing and modified position comprises annotations indicating modified landmark locations. Input data for a machine learning model is generated using original landmark locations and modified landmark locations. The machine learning model is trained using the input data.

公开(公告)号：US20210125104A1

公开(公告)日：2021-04-29

申请号：US17075473

申请日：2020-10-20

申请人： ONFIDO LTD

发明人： Lewis Carl Christiansen ,  Zhiyuan Shi ,  Romain Raymond Jackie Sabathé ,  Philip Samuël Botros ,  Jochem Gietema ,  Pieter-Jan Louis Christianne Reynaert ,  Sophie Dermaux ,  Karolina Dabkowska ,  Daniele Pizzocchero ,  Pouria Mortazavian ,  Mohan Mahadevan

IPC分类号： G06N20/00 ,  G06K9/62 ,  G06T1/20

摘要： The present invention relates to a machine learning inference system and processing modules thereof. In particular, the present invention relates to a machine learning inference system, a confidence module, a data minder module, a data remapping module, an adversarial defense module, and an update module. The machine learning inference system and processing modules thereof are useful for mission-critical applications to increase and maintain performance of a machine learning model.