Mobile document detection and orientation based on reference object characteristics
First Claim
1. A computer-implemented method for processing a digital image depicting a document, the method comprising:
- analyzing, using a processor of a mobile device, the digital image to detect one or more of a presence and a location of one or more reference objects;
detecting, using the processor of the mobile device, one or more geometric characteristics of at least one of the reference objects, wherein the one or more geometric characteristics are selected from;
a height of the at least one of the reference objects, an average height of the at least one of the reference objects, a width of the at least one of the reference objects, an average width of the at least one of the reference objects, an aspect ratio of the at least one of the reference objects, an average aspect ratio of the at least one of the reference objects, an area of the at least one of the reference objects, an average area of the at least one of the reference objects, and a contour of the at least one of the reference objects;
defining, using the processor of the mobile device, one or more region(s) of interest of the digital image within which to search for one or more edges of the document, the region(s) of interest being defined based at least in part on one or more of the detected geometric characteristics; and
detecting, using the processor of the mobile device, a presence or an absence of one or more of the edges of the document within each defined region of interest;
estimating a bounding box for the document based on the detected presence or absence of the edge of the document within each defined region of interest; and
estimating a confidence score of the bounding box based on one or more of;
confidence scores computed for each side of the bounding box;
a confidence score of an estimated aspect ratio of the bounding box; and
a color consistency confidence score.
5 Assignments
0 Petitions
Accused Products
Abstract
In various embodiments, methods, systems, and computer program products for detecting, estimating, calculating, etc. characteristics of a document based on reference objects depicted on the document are disclosed. In one approach, a computer-implemented method for processing a digital image depicting a document includes analyzing the digital image to determine one or more of a presence and a location of one or more reference objects; determining one or more geometric characteristics of at least one of the reference objects; defining one or more region(s) of interest based at least in part on one or more of the determined geometric characteristics; and detecting a presence or an absence of an edge of the document within each defined region of interest. Additional embodiments leverage the type of document depicted in the image, multiple frames of image data, and/or calculate or extrapolate document edges rather than locating edges in the image.
701 Citations
19 Claims
-
1. A computer-implemented method for processing a digital image depicting a document, the method comprising:
-
analyzing, using a processor of a mobile device, the digital image to detect one or more of a presence and a location of one or more reference objects; detecting, using the processor of the mobile device, one or more geometric characteristics of at least one of the reference objects, wherein the one or more geometric characteristics are selected from;
a height of the at least one of the reference objects, an average height of the at least one of the reference objects, a width of the at least one of the reference objects, an average width of the at least one of the reference objects, an aspect ratio of the at least one of the reference objects, an average aspect ratio of the at least one of the reference objects, an area of the at least one of the reference objects, an average area of the at least one of the reference objects, and a contour of the at least one of the reference objects;defining, using the processor of the mobile device, one or more region(s) of interest of the digital image within which to search for one or more edges of the document, the region(s) of interest being defined based at least in part on one or more of the detected geometric characteristics; and detecting, using the processor of the mobile device, a presence or an absence of one or more of the edges of the document within each defined region of interest; estimating a bounding box for the document based on the detected presence or absence of the edge of the document within each defined region of interest; and estimating a confidence score of the bounding box based on one or more of; confidence scores computed for each side of the bounding box; a confidence score of an estimated aspect ratio of the bounding box; and a color consistency confidence score. - View Dependent Claims (2, 3, 4, 5, 6, 17, 18, 19)
-
-
7. A computer-implemented method for processing a plurality of digital image frames, each frame comprising at least a partial digital representation of a document, and the method comprising:
-
analyzing, using a processor of the computer, a first frame among the plurality of frames to determine one or more of a presence and a location of one or more reference objects within the first frame; detecting, using the processor, one or more geometric characteristics of at least one reference object within the first frame, wherein the one or more geometric characteristics are selected from;
a height of the at least one reference object, an average height of the at least one reference object, a width of the at least one reference object, an average width of the at least one reference object, an aspect ratio of the at least one reference object, an average aspect ratio of the at least one reference object, an area of the at least one reference object, an average area of the at least one reference object, and a contour of the at least one reference object;defining, using the processor, one or more region(s) of interest of the first frame within which to search for one or more edges of the document, the one or more region(s) of interest being defined based at least in part on; a priori knowledge regarding a relative position of the at least one reference object within the document; and one or more of the determined geometric characteristics of the at least one reference object within the first frame; defining, using the processor, one or more subregion(s) of interest within which to search for the one or more edges of the document, the one or more subregion(s) of interest being defined within a second frame; detecting, using the processor, a presence or an absence of the one or more of the edges of the document within each defined subregion of interest; wherein each subregion of interest is defined based at least in part on; one or more geometric characteristics of at least one of the region(s) of interest within which the subregion of interest was defined; and one or more of the geometric characteristics of the reference object(s) detected within the first frame; and estimating a bounding box for the document based on the detected presence or absence of the edge of the document within each defined region of interest; and estimating a confidence score of the bounding box based on one or more of; confidence scores computed for each side of the bounding box; a confidence score of an estimated aspect ratio of the bounding box; and a color consistency confidence score. - View Dependent Claims (8, 9, 10, 11, 12, 13)
-
-
14. A computer-implemented method for processing a digital image comprising a digital representation of a document, the method comprising:
-
determining, using a processor of the computer, the document corresponds to one of a predefined set of document types; analyzing, using the processor, the digital image to determine a location of one or more reference objects within the document; detecting, using the processor, one or more geometric characteristics of at least one of the reference objects, wherein the one or more geometric characteristics are selected from;
a height of the at least one of the reference objects, an average height of the at least one of the reference objects, a width of the at least one of the reference objects, an average width of the at least one of the reference objects, an aspect ratio of the at least one of the reference objects, an average aspect ratio of the at least one of the reference objects, an area of the at least one of the reference objects, an average area of the at least one of the reference objects, and a contour of the at least one of the reference objects;extrapolating, using the processor, a location of one or more edges of the document within the digital image based at least in part on;
the determined document type, the determined location of the one or more reference objects, and the detected geometric characteristics of the at least one of the reference objects; andestimating a bounding box for the document based on the extrapolated location of the one or more edges of the document; and estimating a confidence score of the bounding box based on one or more of; confidence scores computed for each side of the bounding box; a confidence score of an estimated aspect ratio of the bounding box; and a color consistency confidence score; and outputting the bounding box, the extrapolated location of the one or more edges of the document, or both to a display of a mobile device. - View Dependent Claims (15, 16)
-
Specification