Methods for mobile image capture and processing of documents
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.
1. A method for mobile image capture and processing of financial documents, comprising:
capturing an image of a financial document on a mobile communication device; and
geometrically correcting the image at the mobile communication device to clarify a content of the image, wherein clarifying the content of the image further comprises:
generating a color icon from the image, wherein the color icon is generated so as to suppress color contrasts within the image of the financial document and to preserve color contrasts between the financial document and a financial document background; and
generating a greyscale icon from the color icon by reducing the color of the color icon such that the color contrasts between the financial document and the financial document background are preserved.
2. The method of claim 1 , wherein geometrically correcting the image at the mobile communication device further comprises at least one of auto-rotation, de-skewing, perspective distortion correction and cropping.
3. The method of claim 1 , further comprising identifying the content on the corrected image of the financial document.
4. The method of claim 1 , further comprising extracting financial content from the corrected image.
5. The method of claim 1 , further comprising identifying corners of the financial document within the greyscale icon.
6. A method for mobile image capture and processing of financial documents, comprising:
receiving an image of a financial document captured by a mobile communication device;
geometrically correcting the image to clarify a content of the image, wherein clarifying the content of the image further comprises:
generating a color icon from the image, wherein the color icon is generated so as to suppress color contrasts within the image of the financial document and to preserve color contrasts between the financial document and a financial document background;
generating a greyscale icon from the color icon by reducing the color of the color icon such that the color contrasts between the financial document and the financial document background are preserved; and
identifying corners of the financial document within the grayscale icon;
correcting an orientation of the financial document;
identifying the content on the corrected image of the financial document; and
extracting financial content from the corrected image which is related to processing of the financial document by a financial institution.
7. The method of claim 6 , further comprising forwarding the extracted financial content to the financial institution.
8. The method of claim 7 , further comprising presenting the extracted financial content to a user on a display of the mobile communication device and requesting feedback from the user with regard to the extracted financial content.
9. The method of claim 8 , wherein the feedback includes a payment amount to pay to the financial institution.
10. The method of claim 6 , further comprising identifying a financial document type based on the identified content.
11. The method of claim 10 , wherein the financial content is extracted from the corrected image based on the identified financial document type.
12. The method of claim 10 , wherein the financial document type is identified by comparing the corrected image of the financial document with at least one stored image of a financial document.
13. The method of claim 6 , wherein the financial content is located in at least one field on the financial document, and wherein each field corresponds to a type of financial content.
14. The method of claim 13 , further comprising identifying at least one field based on the type of financial content and extracting the financial content from the identified at least one field.
15. The method of claim 6 , wherein the geometrically correcting, identifying and extracting is performed on the mobile communication device.
16. The method of claim 6 , further comprising at least one of automatic framing, perspective transformation, geometric transformation, de-warping, adaptive binarization and code-line reading of the image.
17. The method of claim 6 , wherein generating a color icon from the image of the financial document further comprises:
for a set of one or more color intensities, determining a color intensity for each target pixel of a first image by taking an average of the specified color intensity of each pixel contained within a respective window of pixels, wherein each of the respective windows of pixels is contained within the first image and comprises a central pixel, and wherein each of the target pixels is adapted to map respectively to each of the central pixels.
18. The method of claim 6 , wherein the generating a color icon from the image of the financial document further comprises:
resizing a first image; and
for a set of one or more color intensities, determining a color intensity for each target pixel of a second image by determining a maximum color intensity among each pixel contained within a respective window of pixels, wherein each of the respective windows of pixels is contained within the second image and comprises a central pixel, and wherein each of the target pixels is adapted to map respectively to each of the central pixels.
19. The method of claim 18 , wherein the resizing the first image further comprises setting a fixed width and scaled height for the first image, wherein the scaled height is equal to the fixed width times the height of the image divided by the width of the image.
20. A method for mobile image capture and processing of financial documents, comprising:
receiving an image of a financial document captured by a mobile communication device;
geometrically correcting the image to create a corrected image to to clarify a content of the image, wherein clarifying the content of the image further comprises:
generating a color icon from the image, wherein the color icon is generated so as to suppress color contrasts within the image of the financial document and to preserve color contrasts between the financial document and a financial document background;
generating a greyscale icon from the color icon by reducing the color of the color icon such that the color contrasts between the financial document and the financial document background are preserved; and
Identifying comers of the financial document within the greyscale icon;
generating a grayscale image from the image by reducing color of the image; and
identifying the content on the corrected of the financial document; and
extracting financial content from the corrected image.