-
公开(公告)号：EP4105815A1
公开(公告)日：2022-12-21
申请号：EP21179303.9
申请日：2021-06-14
申请人： Onfido Ltd
发明人： Botros, Philip , Sabathe, Romain , Christiansen, Lewis , Bonev, Slavi , Annunziata, Roberto , Mahadevan, Mohan
摘要： A computer implemented method of training a machine learning model for detecting anomalies in images of documents of a class of documents is provided. The method comprises obtaining, for each document, at least one first digital image of a first set of digital images of documents within the class of documents, each first digital image being an image of a region of the respective document comprising a portion of or the whole respective document and the first set of digital images comprising at least one digital image of a document of the class of documents containing an anomaly and at least one digital image of a document of the class of documents not containing an anomaly. The method further comprises applying a plurality of signal processing algorithms to each of the first digital images to generate a respective signal for each first digital image of the first set of digital images of documents and each signal processing algorithm and evaluating a discriminative power of each signal processing algorithm, wherein the discriminative power is indicative of the power of the signals generated with the respective signal processing algorithm to discriminate digital images of documents of the class of documents containing an anomaly from digital images of documents of the class of documents not containing an anomaly. The method further comprises selecting, based on at least the discriminative power of the respective signal processing algorithms, one or more of the plurality of signal processing algorithms, generating input data for the machine learning model using one or more respective signals generated by applying the selected one or more of the plurality of signal processing algorithms to each of a plurality of second digital images, wherein each second digital image is an image of the region of a respective document of a second set of digital images of documents within the class of documents and the second set of digital images comprises at least one digital image of a document of the class of documents containing an anomaly and at least one digital image of a document of the class of documents not containing an anomaly, and training the machine learning model using the input data to produce output data indicative of whether a digital image of a document of the class of documents contains an anomaly or not, wherein optionally, the first set of digital images of documents is the same as or different from, for example, a subset of, the second set of digital images of documents.
-
公开(公告)号：EP4242978A1
公开(公告)日：2023-09-13
申请号：EP23160538.7
申请日：2023-03-07
申请人： Onfido Ltd
发明人： Pizzocchero, Daniele , Moore, Jimmy , Shi, Zhiyuan , Sagonas, Christos , Mahadevan, Mohan , Li, Yuanwei
IPC分类号： G06V10/22 , G06V30/142 , G06V30/14 , G06V30/18 , G06V30/41
摘要： Described herein are computerized methods and systems for authentication of a physical document. An image capture device coupled to a mobile device captures images of a physical document, during which the mobile device adjusts operational parameters of the image capture device, resulting in a sequence of images captured using different capture settings. The mobile device partitions the sequence of images into subsets of images, wherein each subset comprises images with a similar alignment of the physical document and captured using the same capture settings. The mobile device processes the subsets of images to identify a region of interest in each image. The mobile device generates a representation of the identified region of interest using the processed images, generates an authentication score for the document using the representation of the identified region of interest, and determines whether the physical document is authentic based upon the authentication score.
-
公开(公告)号：EP4242977A1
公开(公告)日：2023-09-13
申请号：EP23160536.1
申请日：2023-03-07
申请人： Onfido Ltd
发明人： Pizzocchero, Daniele , Moore, Jimmy , Shi, Zhiyuan , Sagonas, Christos , Mahadevan, Mohan , Li, Yuanwei
IPC分类号： G06V10/22 , G06V10/24 , G06V30/142 , G06V30/14 , G06V30/146 , G06V30/41
摘要： Described herein are computerized methods and systems for authentication of a physical document. An image capture device coupled to a mobile device captures a sequence of images of a physical document as at least one of the physical document or the image capture device is rotated, during which the mobile device tracks the physical document throughout the sequence of images, and adjusts operational parameters of the image capture device based upon imaging conditions associated with the physical document. The mobile device selects images from the sequence of images and classifies the physical document using the selected images. The mobile device identifies a region of interest in the physical document using the selected images and the classification. The mobile device reconstructs the region of interest, generates an authentication score for the document using the reconstructed region of interest, and determines whether the physical document is authentic based upon the authentication score.
-
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
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.
-
公开(公告)号：EP4300446A1
公开(公告)日：2024-01-03
申请号：EP23181543.2
申请日：2023-06-26
申请人： Onfido Ltd
发明人： Bruveris, Martins , Mahadevan, Mohan , Sabathe, Romain , Ehrhardt, Sebastién , Richard, Théo , Opland, Mark
摘要： Described herein are computerized methods and systems for detecting fraud during biometric identity verification. A mobile device captures video comprising a plurality of frames of a person's face. The mobile device extracts from the video frames comprising at least two frames of the person's face from different angles. The mobile device creates a reconstruction of the person's face using the extracted frames and derives signals associated with features of the person's face. The mobile device generates an embedding for each extracted frame using the extracted frames, the three-dimensional reconstruction, and the signals. The mobile device calculates, for each extracted frame, a fraud confidence value based upon the embedding for the extracted frame, attributes of the person's face, and image quality attributes of the extracted image. The mobile device computes a fraud detection decision for the extracted frames based upon the fraud confidence values and the embeddings.
-
公开(公告)号：EP4083850A1
公开(公告)日：2022-11-02
申请号：EP21170789.8
申请日：2021-04-27
申请人： Onfido Ltd
发明人： Gietema, Jochem , Mahadevan, Mohan , Annunziata, Roberto , Reynaert, Pieter-jan , Ivanova, Elizaveta , Li, Yuanwei , Shaharabany, Tal , Ben Dayan, Shachar , Farhan, Erez , Picciotti, Francesco
摘要： A computer implemented method for training a machine learning model for detecting fraud in a document of a class of documents is disclosed. Training the machine learning model comprises obtaining first digital images of a first set of genuine documents in one or more classes of documents and second digital images of a second set of genuine documents of the class of documents. The next stage is selecting at least one of a plurality of printed features and a plurality of spacings between the plurality of printed features in the first digital images of the first set of genuine documents and a plurality of positions of a plurality of printed features in the second digital images. The selected plurality of printed features, spacings and positions are annotated to obtain original reference landmark locations for each printed feature, spacing and position. The annotated printed features, spacings and positions are transformed against a plurality of other instances of the respective annotated printed feature, annotated spacing and/or annotated position to obtain at least one of a plurality of annotated transformed printed features, a plurality of annotated transformed spacings and/or a plurality of annotated transformed positions. The plurality of annotated transformed printed features, spacings and positions are then combined with a noise model to generate at least one of a plurality of modified printed features , a plurality of modified spacings and a plurality of modified positions for each respective printed feature , spacing and position in the first digital images, where each modified printed feature, modified spacing and modified position comprises a plurality of annotations that indicate a plurality of modified reference landmark locations for the respective modified printed feature, modified spacing and modified position. The input data for the machine learning model is then generated using the plurality of original reference landmark locations and the plurality of modified reference landmark locations, and the machine learning model is trained using the input data.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.008 秒)
