Expense report system with receipt image processing

摘要

A system and method for capturing image data is disclosed. A receipt image processing service selects from a repository a template that guides data capture of receipt data from a receipt image and presents the template to a user on an image capture device. A user previews the receipt image and the selected template. If the user decides that the template does not correctly indicate locations of data areas for data items in the receipt image, then the user either updates an existing template or creates a new template that correctly indicates the location of selected data areas in the receipt image. The selected template, the updated template, or the new template is then used to extract receipt data from the receipt image. The receipt data and receipt image data are then provided to the expense report system.

主权项

1. A non-transitory computer readable medium storing instructions for capture of image data, wherein processing the instructions by one or more processors causes:
receiving receipt image data from an image capture device, the receipt image data having a particular layout of data items; processing the receipt image data received from the image capture device to determine locations of the data items in the particular layout; for each respective image template of a plurality of image templates, comparing, by an OCR engine, the locations of the data items in the particular layout of the receipt image data with locations of a plurality of data areas defined by the respective image template; based on comparing the locations of the data items in the particular layout of the receipt image data with locations of data areas defined by the respective image template for each respective image template of the plurality of image templates, selecting by the OCR engine, an image template from the plurality of image templates based on an accuracy value that indicates a matching accuracy between an image template layout of the plurality of data areas and the particular layout of data items in the receipt image data, wherein a particular location for each respective data area of the plurality of data areas in the selected image template corresponds to a respective location of one or more data items in the receipt image data, wherein the selected image template identifies a particular label for each respective data area of the plurality of data areas; transferring the selected image template to the image capture device for review by a user; obtaining a final image template based on the review of the selected image template; and extracting receipt data from the receipt image data in accordance with the final image template.