Guided document image capture and processing
View Patent ↗Video frames of a document are captured. The edges of the document are identified from the frames as they appear within a field of view of a camera and a document rectangle for the document is tracked within the field of view. An area of the document determined from the frames is compared against the available area of the camera preview mode and a larger superimposed guiding rectangle is displayed as a guide within the camera preview mode. When a frame for the document is detected as having document edges that substantially fit within the guiding rectangle, the guiding rectangle is removed and an optimal image of the document is captured for subsequent downstream document image processing.
1. A method, comprising:
tracking edges that define a document within a field of view of a camera;
deriving a guiding rectangle that substantially outlines an available area within the field of view;
superimposing the guiding rectangle within the field of view; and
removing the guiding rectangle from the field of view when the edges of the document substantially align with the guiding rectangle, including when a top leftmost corner of two intersecting edges is within a predefined pixel distance of a top leftmost corner of the guiding rectangle.
2. The method of claim 1 further comprising, activating the camera as soon as the edges substantially align for capturing an optimal document image.
3. The method of claim 1 further comprising, presenting a button within the field of view that can be touched for activating the camera and capturing an optimal document image as soon as the edges substantially align.
4. The method of claim 1 further comprising, capturing, by the camera, an optimal document image as soon as the edges substantially align and sending the optimal image over a network connection to an external document processing service for Optical Character Recognition (OCR) processing.
5. The method of claim 1 , wherein tracking further includes deriving a perimeter rectangle comprised of the edges and tracking the perimeter rectangle within the field of view during operation of the camera.
6. The method of claim 5 , wherein deriving further includes monitoring the perimeter rectangle as the perimeter rectangle grows and shrinks within the field of view.
7. The method of claim 1 , wherein deriving further includes determining the guiding rectangle as a rectangle that outlines a perimeter of the available area for the field of view.
8. The method of claim 1 , wherein deriving further includes calculating the guiding rectangle as a rectangle that is a predefined percentage larger in area than a document rectangle defined by the edges or the document and that fits within the available area of the field of view.
9. The method of claim 1 , wherein superimposing further includes providing an animation within the field of view illustrating moving the camera or the document closer to or farther away from the document or the camera to align the edges of the document with the guiding rectangle depicted within the field of view.
10. The method of claim 1 , wherein removing further includes confirming that a calculated center of the document defined within the edges is within the predefined pixel distance of a center of the guiding rectangle.
11. A method, comprising:
automatically activating a camera of a device to begin recording frames;
determining from the frames four edges of a document;
resolving a document rectangle within the frames from the four edges for tracking movement and location of the document depicted within a field of view of the camera;
calculating a document area for the document rectangle within the field of view;
superimposing a guiding rectangle within the field of view that is a predefined percentage greater than the document area and that is less than or equal to a total area of the field of view; and
removing the guiding rectangle when a size and a modified area for the document rectangle overlaps a guiding rectangle size and guiding rectangle area for the guiding rectangle, including when a top leftmost corner of two intersecting edges is within a predefined pixel distance of a top leftmost corner of the guiding rectangle.
12. The method of claim 11 further comprising, activating the camera as soon as the document rectangle overlaps and aligns with the guiding rectangle within the field of view for capturing a document image of the document.
13. The method of claim 11 further comprising, superimposing a camera activation button within the field of view for capturing a document image as soon as the document rectangle overlaps and aligns with the guiding rectangle within the field of view.
14. The method of claim 11 further comprising, sending a document image captured as soon as the document rectangle overlaps and aligns with the guiding rectangle within the field of view to an external document processing service for Optical Character Recognition (OCR) processing.
15. The method of claim 11 , wherein removing further includes providing an instruction within the field of view for a user to move the document closer to or farther away from the camera to align the document rectangle within the guiding rectangle when the camera is one of: 1) a stationary camera, 2) a stationary combination scanner and camera, and 3) integrated into a stationary computing device.
16. The method of claim 11 , wherein removing further includes providing an instruction within the field of view for a user to move the camera closer to or farther away from the document to align the document rectangle within the guiding rectangle when the camera is one of: 1) a portable combination scanner and camera, and 2) integrated into a mobile device.
17. The method of claim 11 , wherein removing further includes one or more of: presenting a confirmation within the field of view as soon as the document rectangle overlaps the guiding rectangle and outputting a confirmatory audible sound as soon as the document rectangle overlaps the guiding rectangle.
18. A device, comprising:
a camera/scanner integrated into the device; and
a document detector operable to:
(i) execute on one or more hardware processors of the device,
(ii) activate the camera/scanner to capture frames from video taken of a document,
(iii) determine a document rectangle representing the document for tracking within a field of view of the camera/scanner as the frames change,
(iv) superimpose a guiding rectangle within the field of view that is substantially a size of the field of view,
(v) detect when the document rectangle aligns with the guiding rectangle within the field of view, and
(vi) remove the guiding rectangle and activate the camera/scanner to capture an optimal document image for the document as soon as the document rectangle aligns with the guiding rectangle within the field of view, including when a top leftmost corner of two intersecting edges is within a predefined pixel distance of a top leftmost corner of the guiding rectangle.
19. The device of claim 18 , wherein the device is one of: a phone, a tablet, a wearable processing device, a laptop, an Automated Teller Machine (ATM), a network camera, a desktop computer, a kiosk, a standalone printer/scanner, and a Point-Of-Sale (POS) terminal.