Facebook, Inc.

Michael Muesch

Raphael A Rodriguez

David Thor

Ryan Cahill

Xiaolu Xiong

Justin Boyd

The present disclosure describes a method to determine whether a physical identification document is authentic. An authentication manager receives an image of a physical identification document to be authenticated. The authentication manager extracts a set of characteristics of the document from the image. The authentication manager determines a class of the document based on the set of characteristics. The authentication manager applies a convolution kernel, convolving the image with the kernel to generate a feature map. The authentication manager determines a score based on the feature map, where the score identifies the likelihood that the document is valid. The authentication manager then provides an indication that the physical document is authentic based on the score.

Classification and authentication of identification documents using a convolutional neural network

The present disclosure describes systems and methods to classify and authenticate ID documents based on the information contained on the face of the ID document. This present system can automatically classify, authenticate, and extracting data from documents using artificial intelligence (AI) based machine learning for image recognition. In some implementations, the machine learning techniques include a convolutional neural network. The system can also determine the authenticity of other documents, such as currency, stamps, and invoices.

Growing community of inventors

Somerville, MA, United States of America

Michael Muesch