公开(公告)号：EP4105825A1

公开(公告)日：2022-12-21

申请号：EP21179304.7

申请日：2021-06-14

申请人： Onfido Ltd

发明人： Mahadevan, Mohan ,  Annunziata, Roberto ,  Botros, Philip ,  Christiansen, Lewis ,  Picciotti, Francesco ,  Zakizadeh, Roshanak ,  Li, Yuanwei ,  Ivanova, Lisa

IPC分类号： G06K9/32 ,  G06K9/00 ,  G06K9/62

摘要： A computer implemented method of training a system for detecting anomalies in images of documents in a class of documents is disclosed. The method comprises first of obtaining a plurality of training document images of training documents in the class of documents. Then, for each training document image, the method discloses segmenting the training document image into a plurality of region of interest, ROI, images, each ROI image corresponding to a respective ROI of the training document, and for each ROI image, applying a plurality of transformations to the ROI image to generate respective transform-specific features for the ROI image and generating respective transform-specific anomaly scores from the transform-specific features. Finally, the method discloses computing, threshold based on the respective anomaly scores of the plurality of training document images, a transform-specific for each transformation to separate document images containing an anomaly from document images not containing an anomaly.