SCALING MOBILE CHECK PHOTOS TO PHYSICAL DIMENSIONS

• US 20150161765A1
• Filed: 12/19/2013
• Published: 06/11/2015
• Est. Priority Date: 12/06/2013
• Status: Abandoned Application

• Current Assignee: EMC Corporation (Dell Technologies Inc.)
• Original Assignee: EMC Corporation (Dell Technologies Inc.)
• Inventors: Kota, Rao, Flament, Arnaud, Koch, Guillaume, Ng, Ben
• Application Number:
  US14/135,516
• Publication Number:
  US 20150161765A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 3/40 Scaling of whole images or parts thereof, e.g. expanding or contracting
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 30/1478 of characters or characters lines

Abstract

A digital photo of an object is received. The digital photo is transformed to an image. A dimension for an anchor line is calculated based at least in part on the image. The image is scaled based at least in part on the dimension. A confidence value is calculated based at least in part on the scaled image.

Claims

1. A method, comprising:

receiving a digital photo of an object;

transforming the digital photo to an image;

calculating a dimension for an anchor line based at least in part on the image;

scaling the image based at least in part on the dimension; and

calculating a confidence value based at least in part on the scaled image.

2. The method of claim 1, wherein the digital photo is taken by a mobile device.

3. The method of claim 1, wherein the object is a check.

4. The method of claim 1, wherein transforming comprises quantizing the digital photo.

5. The method of claim 4. wherein quantizing comprises quantizing the digital photo to one bit per pixel.

6. The method of claim 1, wherein transforming comprises orienting the image from upside-down.

7. The method of claim 1, wherein transforming comprises correcting for distortion.

8. The method of claim 7, wherein correcting comprises one or more of the following:

perspective correction, keystone correction, radial distortion correction, cylindrical distortion correction, spherical distortion correction, barrel distortion correction, pincushion distortion correction, fisheye distortion correction, lighting distortion, shadow distortion, image geometry correction, translational correction, rotational correction, and trapezoidal correction.

9. The method of claim 1, wherein transforming comprises passing the digital photo to an optical character recognition (“

OCR”

) engine.

10. The method of claim 1, wherein calculating comprises calculating the dimension based at least in part on a dimension of a box bounding the anchor line.

11. The method of claim 1, wherein calculating comprises calculating the dimension based at least in part on a dimension of a box bounding a character on the anchor line.

12. The method of claim 1, wherein the dimension is a height.

13. The method of claim 1, wherein the anchor line is a line with known and precise height.

14. The method of claim 13, wherein the anchor line is a magnetic ink character recognition (“

MICR”

) line.

15. The method of claim 14, wherein the MICR line is encoded by one or more of the following:

MICR E-13B and CMC-7 MICR.

16. The method of claim 15, wherein the object is a document that was not originally intended for transforming to an image.

17. The method of claim 1, wherein calculating a confidence value comprises passing the scaled image to an OCR engine.

18. The method of claim 1, further comprising iterating the steps of calculating the dimension, scaling the image, and calculating the confidence value a plurality of iterations.

19. A system, comprising:

a processor configured to;

receive a digital photo of an object;

transform the digital photo to an image;

calculate a dimension for an anchor line based at least in part on the image;

scale the image based at least in part on the dimension; and

calculate a confidence value based at least in part on the scaled image; and

a memory coupled to the processor and configured to provide the processor with instructions.

20. A computer program product, the computer program product being embodied in a tangible computer readable storage medium and comprising computer instructions for:

receiving a digital photo of an object;

transforming the digital photo to an image;

calculating a dimension for an anchor line based at least in part on the image;

scaling the image based at least in part on the dimension; and

calculating a confidence value based at least in part on the scaled image.