Ensuring image integrity using document characteristics

• US 8,639,062 B2
• Filed: 10/09/2007
• Issued: 01/28/2014
• Est. Priority Date: 10/09/2007
• Status: Active Grant

• Current Assignee: Bank of America Corp.
• Original Assignee: Bank of America Corp.
• Inventors: Calman, Matthew A., Gibson, Lisa, Huff, Lowell R., Ronca, James G.
• Primary Examiner(s): Chu, Randolph I
• Assistant Examiner(s): BLOOM, NATHAN J
• Application Number:
  US11/869,123
• Publication Number:
  US 20090092309A1
• Time in Patent Office: 2,303 Days
• Field of Search: 382/100, 382/101, 382135-141, 382/173, 382/175, 382/181, 382305-306, 382/190, 705/50, 705/1.1, 707821-831, 711/100, 713150-181
• US Class Current: 382/305
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06T 1/0028 Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking
• CPC Class Codes: G06T 2201/0201 whereby only tamper or origin are detected and no embedding takes place
• CPC Class Codes: G06V 10/987 with the intervention of an operator
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: H04N 1/32128 attached to the image data, e.g. file header, transmitted message header, information on the same page or in the same computer file as the image for information embedded in the image H04N1/32144
• CPC Class Codes: H04N 1/32144 embedded in the image data, i.e. enclosed or integrated in the image, e.g. watermark, super-imposed logo or stamp
• CPC Class Codes: H04N 2201/3235 Checking or certification of the authentication information, e.g. by comparison with data stored independently
• CPC Class Codes: H04N 2201/3236 Details of authentication information generation
• CPC Class Codes: H04N 2201/327 which are undetectable to the naked eye, e.g. embedded codes
• CPC Class Codes: H04N 2201/3281 Encryption; Ciphering

Abstract

Image integrity in an archive can be verified using document characteristics. Embodiments of the invention provide a way to verify the integrity of a stored document image by determining document characteristics, which can also be embedded in the image file. Before allowing access to the image file by an application, the characteristics data from an image analysis can be compared to either or both of, characteristics information otherwise stored, or embedded characteristics data. The embedded data can optionally be encrypted. In example embodiments the data can include a result of an optical character recognition of contents of the document, a length of data describing the image, a percentage of a specified color of pixels in the image, or a checksum. Example embedding techniques can include those making use of a tagged image file format (TIFF) header, a steganographic watermark, or an image artifact.

Claims

1. A computer-implemented method of ensuring integrity of a plurality of images in a document archive, the method comprising:

receiving, by an image management platform, a captured image of a document, wherein the image comprises image characteristics;

analyzing, by an image analysis module functionally connected to the image management platform, the captured image of the document to determine the image characteristics associated with the image and storing the captured image of the document as an image file;

storing, by the image management platform, the one or more image characteristics associated with the image in an index, separate from the image file;

receiving, at the image management platform and from an application, a request to access the image file associated with the captured image of the document;

comparing, by the image management platform and in response to the request by the application to access the image file associated with the captured image of a document, the image characteristics stored in the index with image characteristics embedded in the image file to verify the integrity of the image file prior to granting the request by the application to access the image file;

in response to the image management platform determining that the image characteristics stored in the index match the image characteristics embedded in the image file, sending the image to the application that requested access to the image file;

analyzing, by the application, the image file to determine the image characteristics associated with the image;

extracting, by the application, embedded characteristics data from the image file;

comparing, by the application the image characteristics determined by the application with the characteristics data extracted from the image file by the application; and

in response to determining that the image characteristics determined by the application match the characteristics data extracted from the image file by the application, verifying, by the application, the integrity of the image file.

2. The computer-implemented method of claim 1 further comprising:

embedding the image characteristics in form of characteristics data in the image file; and

subsequently comparing the characteristics data from the image file to one or more of the image characteristics stored in the index to verify the integrity of the image.

3. The computer-implemented method of claim 2 further comprising encrypting the image characteristics prior to embedding the image characteristics.

4. The computer-implemented method of claim 2 further comprising determining a confidence score expressing the likelihood that stored codeline data matches a codeline in the image prior to embedding image characteristics in the image file.

5. The computer-implemented method of claim 2 wherein the image characteristics for the image is embedded in at least one of a tagged image file format (TIFF) header, a steganographic watermark, and an image artifact.

6. The computer-implemented method of claim 1 wherein the at least one image characteristic comprises at least one of, a result of an optical character recognition of contents of the document, a length of data describing the image, a percentage of a specified color of pixels in the image, and a checksum.

7. A non-transitory, computer-readable medium for ensuring integrity of a plurality of images in a document archive, the computer-readable medium having computer program code embodied therein, the computer program code comprising:

instructions for analyzing, using an image management platform, captured images of documents to determine at least one image characteristic for each of the plurality of images, wherein the image is stored as an image file;

instructions for storing, using the image management platform, the at least one image characteristics for each of the plurality of images in an index, separate from the image file; and

instructions for comparing, using the image management platform and in response to a request to access the image file by an application, the at least one image characteristic for each of the plurality of images stored in the index with the image stored as the image file in order to verify the integrity of the image file prior to granting the request to access the image file;

instructions for, using the image management platform and in response to determining that the at least one image characteristic for each of the plurality of images stored in the index matches the image stored as the image file, sending at least one of the images to the application that requested access to the at least one image file;

instructions for analyzing, using the application, the at least one image file to determine the image characteristics associated with the at least one image;

instructions for extracting, using the application, embedded characteristics data from the at least one image file;

instructions for comparing, using the application, the image characteristics determined by the application with the characteristics data extracted from the at least one image file by the application; and

instructions for, using the application and in response to determining that the image characteristics determined by the application match the characteristics data extracted from the at least one image file by the application, verifying the integrity of the at least one image file.

8. The computer-readable medium of claim 7 wherein the computer program code further comprises instructions for encrypting the at least one image characteristic.

9. The computer-readable medium of claim 7 wherein the documents comprise checks.

10. The computer-readable medium of claim 7 further wherein the computer program code further comprises instructions for embedding the at least one image characteristic in form of characteristics data in the image file using at least one of a tagged image file format (TIFF) header, a steganographic watermark, and an image artifact.

11. The computer-readable medium of claim 7 wherein the at least one image characteristic comprises at least one of, a result of an optical character recognition of contents of the document, a length of data describing the image, a percentage of a specified color of pixels in the image, and a checksum.

12. The computer-readable medium of claim 9 wherein the computer program code further comprises instructions for determining a confidence score expressing the likelihood that stored codeline data matches a codeline in a check prior to embedding characteristics data in the image file.

13. A system for ensuring integrity of a plurality of images in a financial document archive, the system comprising:

an image management platform configured to obtain image files corresponding to images, analyze the images in the image files to obtain image characteristics, store the image characteristics in an index separate from the image files, and compare stored image characteristics for the index with characteristics data from the image files prior to granting a request to access the image file;

an image analysis module functionally connected to the image management platform and configured to determine the image characteristics;

at least one executable application configured to request access to the image file and to access the image file subject to the image management platform comparing stored image characteristics for the index with the characteristics data and subject to the application comparing image characteristics determined by the application with extracted characteristics data;

wherein the at least one executable application is configured to;

in response to receiving the image file from the image management platform, analyze the image file to determine the image characteristics associated with the image;

extract embedded characteristics data from the image file;

compare the image characteristics determined by the application with the characteristics data extracted from the image file by the application; and

in response to determining that the image characteristics determined by the at least one executable application match the characteristics data extracted from the image file by the at least one executable application, verify the integrity of the image file; and

a messaging facility connected between the image management platform and the at least one application.

14. The system of claim 13 further comprising a short-term image archive to supply the image files to the image management platform.

15. The system of claim 14 further comprising a long term image archive connected to the messaging facility.

16. The system of claim 15 further comprising a long term image archive index.

17. The system of claim 13 wherein the image characteristics includes at least one of, a result of an optical character recognition of contents of the document, a length of data describing the image, a percentage of a specified color of pixels in the image, and a checksum.

18. The system of claim 13 wherein the image management platform further embeds the image characteristics for the image in the image file using at least one of a tagged image file format (TIFF) header, a steganographic watermark, and an image artifact.