SYSTEMS AND METHODS FOR MOBILE IMAGE CAPTURE AND PROCESSING

• US 20140328520A1
• Filed: 07/17/2014
• Published: 11/06/2014
• Est. Priority Date: 01/12/2012
• Status: Active Grant

• Current Assignee: Kofax Incorporated
• Original Assignee: Kofax Incorporated
• Inventors: Macciola, Anthony, Shustorovich, Alexander, Thrasher, Christopher W.
• Granted Patent: US 8,971,587 B2
• Time in Patent Office: Days
• US Class Current: 382/112
• CPC Class Codes: G06F 17/40 Data acquisition and logging for input to computer G06F3/00
• CPC Class Codes: G06F 3/005 Input arrangements through a video camera
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 50/18 Legal services
• CPC Class Codes: G06T 1/0007 Image acquisition
• CPC Class Codes: G06T 11/20 Drawing from basic elements, e.g. lines or circles
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20164 Salient point detection; Corner detection
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 3/02 Affine transformations for image registration G06T3/147; for image mosaicing G06T3/4038
• CPC Class Codes: G06T 3/10 Selection of transformation methods according to the characteristics of the input images
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/143 : involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06T 7/194 : involving foreground-background segmentation
• CPC Class Codes: G06V 10/247 : by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 10/25 : Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 30/413 : Classification of content, e.g. text, photographs or tables
• CPC Class Codes: G06V 30/414 : Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: H04N 1/00116 : of multimedia information
• CPC Class Codes: H04N 1/00251 : with an apparatus for taking photographic images, e.g. a camera
• CPC Class Codes: H04N 1/00403 : Voice input means, e.g. voice commands
• CPC Class Codes: H04N 1/387 : Composing, repositioning or otherwise geometrically modifying originals
• CPC Class Codes: H04N 1/3872 : Repositioning or masking
• CPC Class Codes: H04N 1/3878 : Skew detection or correction
• CPC Class Codes: H04N 1/40 : Picture signal circuits H04N1/387 takes precedence
• CPC Class Codes: H04N 2201/0081 : Image reader H04N2201/0091 - H04N2201/0094 take precedence
• CPC Class Codes: H04N 2201/0096 : Portable devices

Abstract

In various embodiments, methods, systems, and computer program products for processing digital images captured by a mobile device are disclosed. Myriad features enable and/or facilitate processing of such digital images using a mobile device that would otherwise be technically impossible or impractical, and furthermore address unique challenges presented by images captured using a camera rather than a traditional flat-bed scanner, paper-feed scanner, or multifunction peripheral. Particularly advantageous features include robustly detecting edges of one or more documents depicted in the digital image data, and defining/locating document pages at least partially on this basis. The statistical approaches employed enable robust yet computationally efficient techniques to accomplish page detection, and associated functions, using hardware typically included in mobile devices and within practical (especially temporal) limits imposed by device manufacturers, users, associated and/or downstream computational and/or business processes.

Claims

1. A method, comprising:

capturing one or more of image data depicting a digital representation of a document and audio data relating to the digital representation of the document;

defining a plurality of candidate edge points within the image data; and

defining four sides of a tetragon based on the plurality of candidate edge points,

wherein each side of the tetragon corresponds to a different side of the document, and

wherein the tetragon bounds the digital representation of the document.

2. The method as recited in claim 1, wherein defining the plurality of candidate edge points comprises, for each of a plurality of portions of the image data:

calculating one or more statistics corresponding to the portion;

estimating one or more distributions of statistics corresponding to the portion;

determining whether a statistically significant difference exists between one or more of the statistics calculated for the portion and the distribution of statistics estimated for the portion; and

designating a point corresponding to the statistically significant difference as a candidate edge point in response to determining the statistically significant difference exists.

3. The method as recited in claim 2, wherein the statistics calculated for each portion comprise one or more of:

a minimum brightness value;

a maximum brightness value; and

a brightness value range; and

wherein the distributions of statistics estimated for each portion comprise one or more of;

a distribution of color channel value minima;

a distribution of color channel value maxima; and

a distribution of color channel value ranges.

4. The method as recited in claim 2, wherein at least one portion comprises a corner region of the image.

5. The method as recited in claim 2, wherein each portion is defined along a path proceeding from an outer region of the image toward a center of the image.

6. The method as recited in claim 5, wherein the path proceeds along one or more of rows and columns of the digital image.

7. The method as recited in claim 2, wherein portion is characterized by a substantially rectangular shape, and

wherein each small analysis window is characterized by a substantially rectangular shape.

8. The method as recited in claim 2, wherein each portion is characterized by a single center pixel, and

wherein the center pixel is designated as a candidate edge point upon determining the statistically significant difference exists.

9. The method as recited in claim 1, further comprising bypassing one or more variations in a texture of a background of the digital image.

10. The method as recited in claim 1, further comprising:

removing one or more outlier candidate edge points from the plurality of candidate edge points; and

defining a second plurality of candidate edge points excluding the one or more outlier candidate edge points.

11. The method as recited in claim 1, wherein each side of the tetragon is characterized by a polynomial equation, and

wherein the defining comprises determining one or more coefficients for each polynomial equation.

12. The method as recited in claim 1, further comprising defining one or more corners of the tetragon, the defining comprising:

calculating one or more intersections between two adjacent sides; and

designating an appropriate intersection from the one or more calculated intersections.

13. The method as recited in claim 1, wherein a corner of the tetragon comprises an intersection of two adjacent sides of the tetragon, wherein the two adjacent sides are selected from:

one substantially straight line and one substantially curved line;

one substantially straight line and one substantially parabolic curve; and

two substantially parabolic curves.

14. The method as recited in claim 1, further comprising defining one or more tetragon corners, the defining comprising solving one or more of:

a first degree polynomial equation;

a second degree polynomial equation;

a third degree polynomial equation; and

a fourth degree polynomial equation.

15. The method as recited in claim 1, wherein an area of the tetragon comprises at least a threshold percentage of a total area of the digital image.

16. The method as recited in claim 1, wherein a first line connects a calculated top left corner of the tetragon to a calculated bottom right corner of the tetragon,

wherein a second line connects a calculated top right corner of the tetragon and a calculated bottom left corner of the tetragon, and

wherein the first line and the second line intersect inside the tetragon.

17. The method as recited in claim 1, further comprising:

determining whether the tetragon satisfies one or more quality control metrics; and

rejecting the tetragon upon determining the tetragon does not satisfy one or more of the quality control metrics,

wherein the quality control metrics comprise one or more of;

a Least Mean Squares (LMS) support metric,

a minimum tetragon area metric,

a tetragon corner location metric; and

a tetragon diagonal intersection location metric.

18. The method as recited in claim 1, further comprising outputting the digital representation of the document and the tetragon to a display of a mobile device.

19. A system, comprising:

a processor configured to execute logic; and

logic configured to cause the processor executing the logic to;

capture one or more of image data depicting a digital representation of a document and audio data relating to the digital representation of the document;

define a plurality of candidate edge points within the image data,

define four sides of a tetragon based on the plurality of candidate edge points, wherein each side of the tetragon corresponds to a different side of the document; and

output the digital representation of the document and the tetragon to a display of a mobile device, wherein the tetragon bounds the digital representation of the document.

20. A computer program product comprising a computer readable storage medium having computer readable program code stored thereon, the computer readable program code comprising:

computer readable program code configured to cause a processor to;

capture one or more of image data depicting a digital representation of a document and audio data relating to the digital representation of the document;

define a plurality of candidate edge points within the image data,

define four sides of a tetragon based on the plurality of candidate edge points, wherein each side of the tetragon corresponds to a different side of the document; and

output the digital representation of the document and the tetragon to a display of a mobile device, wherein the tetragon bounds the digital representation of the document.