Systems for mobile image capture and processing of checks

• US 7,778,457 B2
• Filed: 03/03/2010
• Issued: 08/17/2010
• Est. Priority Date: 01/18/2008
• Status: Active Grant

• Current Assignee: Mitek Systems Incorporated
• Original Assignee: Mitek Systems Incorporated
• Inventors: Nepomniachtchi, Grigori, DeBello, James
• Primary Examiner(s): Mehta; Bhavesh M
• Assistant Examiner(s): MOTSINGER, SEAN T
• Application Number:
  US12/717,080
• Publication Number:
  US 20100150424A1
• Time in Patent Office: 167 Days
• Field of Search: 382137-140, 705 39- 45, 235/379
• US Class Current: 382/137
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G06Q 20/10 specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
• CPC Class Codes: G06Q 20/108 Remote banking, e.g. home banking
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: H04N 1/00204 with a digital computer or a digital computer system, e.g. an internet server programmed control between transmitter and receiver or between image input and image output device H04N1/32561
• CPC Class Codes: H04N 1/00244 with a server, e.g. an internet server fax-servers or the like for store and forward H04N1/324
• CPC Class Codes: H04N 1/00307 with a mobile telephone apparatus constructional features of portable telephone sets H04M1/0202; mobile radio systems H04W84/00
• CPC Class Codes: H04N 1/00816 Determining the reading area, e.g. eliminating reading of margins
• CPC Class Codes: H04N 1/387 Composing, repositioning or otherwise geometrically modifying originals
• CPC Class Codes: H04N 1/403 Discrimination between the two tones in the picture signal of a two-tone original
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 2201/001 Sharing resources, e.g. processing power or memory, with a connected apparatus or enhancing the capability of the still picture apparatus

Abstract

The present invention relates to automated document processing and more particularly, to methods and systems for document image capture and processing using mobile devices. In accordance with various embodiments, methods and systems for document image capture on a mobile communication device are provided such that the image is optimized and enhanced for data extraction from the document as depicted. These methods and systems may comprise capturing an image of a document using a mobile communication device; transmitting the image to a server; and processing the image to create a bi-tonal image of the document for data extraction. Additionally, these methods and systems may comprise capturing a first image of a document using the mobile communication device; automatically detecting the document within the image; geometrically correcting the image; binarizing the image; correcting the orientation of the image; correcting the size of the image; and outputting the resulting image of the document.

Claims

1. A system for image capture and processing of financial documents, comprising:

a mobile device including;

an image capture device configured to capture a color image of a financial document,

a processor configured to;

detect the financial document in the color image, and

geometrically correct the color image and generate a gray-scale image, and

a transmitter configured to transmit the gray-scale image to a server; and

a server configured to receive the gray-scale image from the mobile device and to;

binarize the gray-scale image to produce a bi-tonal image,

correct the orientation of the bi-tonal image, and

correct the size of the bi-tonal image.

2. The system of claim 1, wherein the processor is configured to detect the financial document in the color image by:

converting the color image into a smaller color image;

performing color depth reduction on the smaller color image; and

determining document corner positions for the financial document in the smaller color image.

3. The system of claim 2, wherein the processor is configured to convert the color image into a smaller color image by:

eliminating over-sharpening in the color image;

eliminating small dark objects in the color image; and

suppressing high local contrast objects in the color image.

4. The system of claim 2, wherein the processor is configured to perform color depth reduction on the smaller color image by:

dividing the smaller color image into a grid;

computing an average color for a central part of the smaller image;

computing an average color for the remainder of the smaller color image;

finding a linear transformation by mapping the central part color on white and mapping the color for the rest of the smaller image on black; and

transforming RGB values for the image into gray-shades to produce a smaller gray image.

5. The system of claim 4, wherein the processor is further configured to:

find voting points in the smaller gray image for each side of the financial document;

find side candidates for the financial document based on the voting points;

choose best side candidates from the side candidates; and

determine document corner positions for the financial document based on the best side candidates.

6. The system of claim 1, wherein the processor is configured to geometrically correct the color image to generate a geometrically corrected gray-scale image by:

reducing the color depth of the color image;

generating a gray-scale image corresponding to the color image;

applying perspective transformation to the interior of a quadrangle comprising found document corner positions included in the gray-scale image.

7. The system of claim 6, wherein the processor is configured to geometrically correct the color image to generate a geometrically corrected image by:

correcting the landscape orientation of a smaller gray-scale image based on the determined document corner positions;

building a projective transformation model of the smaller gray-scale image; and

applying perspective transformation to the interior of a quadrangle include in the smaller gray-scale image.

8. The system of claim 1, wherein the server is further configured to binarize the geometrically corrected gray-scale image to produce a bi-tonal image by:

choosing a pixel on the gray-scale image;

computing an average value and standard deviation for the chosen pixel;

determining whether the standard deviation is too small and if it is too small then converting the chosen pixel to white and if it is not too small then converting the chosen pixel to black or white based on the intensity; and

choosing another pixel an repeating the computing and determining steps until there are no more pixels to chose.

9. The system of claim 1, wherein the financial document is a check, and wherein the server is further configured to correct the orientation of the bi-tonal image by:

reading an MICR line on the bottom of the financial document;

generating a MICR confidence value for the MICR line as read;

comparing the MICR confidence value to a threshold;

when the MICR confidence value exceeds the threshold, determining that the bi-tonal image is right-side up; and

when the MICR confidence value does not exceed the threshold;

determining that the bi-tonal image is not right side up,

rotating the image 180 degrees,

re-reading the MICR line,

generating a new MICR confidence value,

comparing the new MICR confidence value to the previous MICR confidence value,

when the new MICR confidence value exceeds the first MICR confidence value, determining that the rotated, bi-tonal image is right side up, and

when the new MICR confidence value does not exceeds the first MICR confidence value, determining that the original un-rotated, bi-tonal image is right side up.

10. The system of claim 1, wherein the financial document is a check, and wherein the server is further configured to correct the size of the bi-tonal image by:

reading an MICR line on the bottom of the financial document;

computing an average width of the MICR characters;

computing a scaling factor;

when the scaling factor is not greater than a threshold, outputting the bi-tonal image; and

when the scaling factor is greater than a threshold;

repeating geometric correction and binarization using recomputed dimensions for the financial document; and

outputting the bi-tonal image.

11. A system for image capture and processing of financial documents, comprising:

a mobile device including;

an image capture device configured to capture a color image of a financial document, and

a transmitter configured to transmit the color image to a server; and

a server configured to receive the color image from the mobile device and to;

detect the financial document in the color image, wherein the server is configured to detect the financial document in the color image by;

converting the color image into a smaller color image;

performing color depth reduction on the smaller color image; and

determining document corner positions for the financial document in the smaller color image and

geometrically correct the color image and generate a grey-scale image,

binarize the gray-scale image to produce a bi-tonal image,

correct the orientation of the bi-tonal image, and

correct the size of the bi-tonal image.

12. The system of claim 11, wherein the server is configured to convert the color image into a smaller color image by:

eliminating over-sharpening in the color image;

eliminating small dark objects in the color image; and

suppressing high local contrast objects in the color image.

13. The system of claim 11, wherein the server is configured to perform color depth reduction on the smaller color image by:

dividing the smaller color image into a grid;

computing an average color for a central part of the smaller image;

computing an average color for the remainder of the smaller color image;

finding a linear transformation by mapping the central part color on white and mapping the color for the rest of the smaller image on black; and

transforming RGB values for the image into gray-shades to produce a smaller gray image.

14. The system of claim 13, wherein the server is further configured to:

find voting points in the smaller gray image for each side of the financial document;

find side candidates for the financial document based on the voting points;

choose best side candidates from the side candidates; and

determine document corner positions for the financial document based on the best side candidates.

15. The system of claim 11, wherein the server is configured to geometrically correct the color image to generate a geometrically corrected gray-scale image by:

reducing the color depth of the color image;

generating a gray-scale image corresponding to the color image;

applying perspective transformation to the interior of a quadrangle comprising found document corner positions included in the gray-scale image.

16. The system of claim 14, wherein the server is configured to geometrically correct the color image to generate a geometrically corrected gray-scale image by:

correcting the landscape orientation of a smaller gray-scale image based on the determined document corner positions;

building a projective transformation model of the smaller gray-scale image; and

applying perspective transformation to the interior of a quadrangle include in the smaller gray-scale image.

17. The system of claim 11, wherein the server is further configured to binarize the geometrically corrected image to produce a bi-tonal image by:

choosing a pixel on the gray-scale image;

computing an average value and standard deviation for the chosen pixel;

determining whether the standard deviation is too small and if it is too small then converting the chosen pixel to white and if it is not too small then converting the chosen pixel to black or white based on the intensity; and

choosing another pixel an repeating the computing and determining steps until there are no more pixels to chose.

18. The system of claim 11, wherein the financial document is a check, and wherein the server is further configured to correct the orientation of the bi-tonal image by:

reading an MICR line on the bottom of the financial document;

generating a MICR confidence value for the MICR line as read;

comparing the MICR confidence value to a threshold;

when the MICR confidence value exceeds the threshold, determining that the bi-tonal image is right-side up; and

when the MICR confidence value does not exceed the threshold;

determining that the bi-tonal image is not right side up,

rotating the image 180 degrees,

re-reading the MICR line,

generating a new MICR confidence value,

comparing the new MICR confidence value to the previous MICR confidence value,

when the new MICR confidence value exceeds the first MICR confidence value, determining that the rotated, bi-tonal image is right side up, and

when the new MICR confidence value does not exceeds the first MICR confidence value, determining that the original un-rotated, bi-tonal image is right side up.

19. The system of claim 11, wherein the financial document is a check, and wherein the server is further configured to correct the size of the bi-tonal image by:

reading an MICR line on the bottom of the financial document;

computing an average width of the MICR characters;

computing a scaling factor;

when the scaling factor is not greater than a threshold, outputting the bi-tonal image; and

when the scaling factor is greater than a threshold;

repeating geometric correction and binarization using recomputed dimensions for the financial document; and

outputting the bi-tonal image.