23-09-2021 дата публикации
Номер: US20210295103A1
Автор:
Chen Jiayi,
CHING Man Lok,
GREEN Riley,
HIGGINS Luke,
KULKARNI Aditi,
LEMA Reuben,
Liu Xiaolei,
MOORE Isabella Phoebe Groenewegen,
SUN Xiwen,
TANNIRU Rajendra Prasad,
VIJAYARAGHAVAN Koushik M.
Принадлежит:
A device may receive image data that includes an image of a document and lexicon data identifying a lexicon, and may perform an extraction technique on the image data to identify at least one field in the document. The device may utilize form segmentation to automatically generate label data identifying labels for the image data, and may process the image data, the label data, and data identifying the at least one field, with a first model, to identify visual features. The device may process the image data and the visual features, with a second model, to identify sequences of characters, and may process the image data and the sequences of characters, with a third model, to identify strings of characters. The device may compare the lexicon data and the strings of characters to generate verified strings of characters that may be utilized to generate a digitized document. 1. A method , comprising:receiving, by a device, image data that includes an image of a document to be digitized and lexicon data identifying a lexicon associated with the document;performing, by the device, an extraction technique on the image data to identify at least one field provided in the document;utilizing, by the device, form segmentation to automatically generate label data identifying labels for the image data;processing, by the device, the image data, the label data, and data identifying the at least one field, with a convolutional neural network model, to identify visual features of the image data;processing, by the device, the image data and the visual features, with a recurrent neural network model, to identify sequences of characters in the image data;processing, by the device, the image data and the sequences of characters, with a connectionist temporal classification model, to identify strings of characters in the image data;comparing, by the device, the lexicon data and the strings of characters to verify the strings of characters and to generate verified strings of characters and ...
Подробнее