Out-of-bounds detection of a document in a live camera feed

Abstract

Aspects of the present disclosure provide methods and apparatuses for processing a digital image of a document, for example, to determine whether the document is a long document. An exemplary method generally includes obtaining a plurality of digital images of the document, segmenting at least a first digital image of the plurality of images into pixels associated with a foreground of the first digital image and pixels associated with a background of the first digital image, detecting a plurality of contours in the segmented first digital image, deciding, for each detected contour of the plurality of contours, whether that contour is an open contour or a closed contour, and determining that one or more sides of the document is out-of-bounds based, at least in part, on the decisions.

Description

BACKGROUNDField[0001]The present disclosure generally relates to processing digital images of documents or forms. More specifically, the present disclosure provides techniques for detecting whether one or more sides of a document is out of bounds in a live camera feed.Related Art[0002]In the course of using a mobile application, it is sometimes useful to capture an image of a document. For example, a user of a financial management application may capture an image of a receipt related to a financial transaction for use within the application. In some cases, however, due to the limitations of cameras, such as restricted fields of view, a document may be too long to capture in a single image of sufficient quality to identify the document's textual content.SUMMARY[0003]Aspects of the present disclosure provide a computer-implemented method for processing a digital image of a document. The computer-implemented method generally includes obtaining a plurality of digital images of the docum...

AI Technical Summary

Benefits of technology

The present patent provides a computer-implemented method for processing a digital image of a document by obtaining multiple images, segmenting them into foreground and background pixels, detecting contours, and determining if the document is a long document or if its sides are out-of-bounds based on the detected contours. This method can be implemented using computer-readable storage media and a processor. The technical effect of this patent is to provide a more efficient and accurate way to process digital images of documents.

Problems solved by technology

In some cases, however, due to the limitations of cameras, such as restricted fields of view, a document may be too long to capture in a single image of sufficient quality to identify the document's textual content.

Images