Idemia Identity & Security France

Idemia Public Security France

Brian Martin

Rein-Lien Hsu

Alexandru Bogdan

Hui Zhu

An authentication processing system includes a memory storing a portrait fraud detection application, and a processing unit coupled with the memory and configured to execute the portrait fraud detection application. The portrait fraud detection application, when executed, configures the processing unit to receive a capture of a document including a portrait photo and at least one overlay, detect a face in the portrait photo among the at least one overlay in the capture, and determine the portrait photo is fraudulent; and initiate an indication the document is fraudulent.

Automatic system and method for document authentication using portrait fraud detection

A system for authenticating a subject identification document includes instructions causing a processor to receive a first image of the document, depicting, in RGB color space, the document illuminated by UV light, and transform the first image to a second image in YCbCr color space. The instructions cause the processor to divide the second image into regions of interest (ROIs), and, for each ROI, generate a color profile descriptor including first data elements associated with pixel color in the YCbCr color space, and second data elements associated with pixel intensity of pixels within the ROI. The instructions also cause the processor to generate a score for the second image based on a comparison of the color profile descriptor for each ROI to a corresponding ROI of an enrolled document template, and compare the score to a threshold to determine whether the document is authenticated.

Systems and methods for document authentication

A computer-implemented method and a computing system are provided for training a matting neural network to generate mattes for creating portraits to be used on identity documents. The matting neural network is trained by using standardized images conforming to a template which prescribes that each standardized image should depict a human face. A standardized image is obtained by adjusting an input image which includes an area representing a face of the person and was, e.g., taken with a camera, so that a relationship between the size of the adjusted input image and the distance between target points (which represent parts of the person) in the adjusted input image satisfies a condition determined by the template, and in the adjusted input image the area is in a position defined by the template.

Method and system for training matting neural network, and method and device for generating portrait to be used on identity document

Techniques for texture-based authentication of digital identity documents are disclosed. The disclosed techniques include authentication based on global texture information and/or on local texture information. Global texture-based authentication may include generating a global texture profile for an identity document image and comparing the global texture profile with a stored profile associated with a jurisdiction class of the identity document. Local texture-based authentication may include generating one or more local texture patches representative of texture information of one or more select local blocks of the ID. The one or more local texture patches are provided as input to one or more local detectors each trained to detect the presence of a forgery based on a target manipulation space.

Growing community of inventors

McMurray, PA, United States of America

Brian Martin