Method and apparatus for imaging, image processing and data compression

• US 5,748,780 A
• Filed: 06/14/1994
• Issued: 05/05/1998
• Est. Priority Date: 04/07/1994
• Status: Expired due to Term

• Current Assignee: Lot 19 Acquisition Foundation LLC (Intellectual Ventures LLC)
• Original Assignee: Salvatore J. Stolfo
• Inventors: Stolfo, Salvatore J.
• Primary Examiner(s): Couso, Jose L.
• Application Number:
  US08/259,527
• Time in Patent Office: 1,421 Days
• Field of Search: 382/135, 382/137, 382/138, 382/139, 382/218, 382/232, 382/317, 358/435, 358/436
• US Class Current: 382/232
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G06V 2201/01 Solutions for problems related to non-uniform document background

Abstract

A method for processing an image, consisting of a foreground and a background, to produce a highly compressed and accurate representation of the image, including the steps of scanning the image to create a digital image of the image, comparing the digital image against a codebook of stored digital images; matching the digital image with one of the stored digital images of the codebook; producing an index code identifying the background of the stored digital image as having matched the digital image; subtracting the stored digital image from the digital image to produce a second digital image representing the foreground of the stored digital image; and storing the second digital image with the index code. An apparatus is also provided for compressing images having a foreground and a background, consisting of an image scanner, a template image storage device for storing background templates, a processor system for matching a scanned image of the image with one of the background templates, resulting in a template identifier, a processor system for compensating the scanned image for the matched template to produce a foreground image, and a data compression system for compressing the foreground image.

Claims

1. A method for processing an image from a document, said method comprising the steps of:

(a) scaning the document, said scanning including creating a first digital image corresponding to said image on said document;

(b) searching a codebook comprising a plurality of stored digital images for one of said stored digital images which is present in at least a portion or portions of said first digital image;

(c) producing and storing an electronic index code that identifies said one of said stored digital images as being present in said at least a portion or portions of said first digital image;

(d) generating a second digital image comprising the portion or portions of said first digital image that are not present in said one of said stored digital images by separating said stored digital image from said first digital image; and

(e) preserving said second digital image, said stored electronic index code, and said codebook in a form such that said first digital image can be reproduced from the combination of said second digital image and said stored digital image.

2. The method according to claim 1, wherein said stored digital images in said codebook are clustered into a logical collection of related digital images.

3. The method according to claim 1, wherein said scanning step employs optical raster scanning.

4. The method according to claim 1, wherein said document comprises a document selected from the group consisting of a check, bank deposit or withdrawal slip, coupon, travelers'"'"' cheque, letter of credit, monetary instrument, food stamp, insurance form, medical form, real estate form, an inventory form, real estate document, official government form, brochures, instructional form, questionnaire form, laboratory data form, tax form, computer screen, stock certificate and bond certificate.

5. The method according to claim 1, wherein said document is a check.

6. The method according to claim 1, wherein said stored digital images in said codebook are clustered into a logical collection of related digital images.

7. A method according to claim 1, wherein said searching of said codebook of stored digital images is performed in parallel by distributing said first digital image to a plurality of processing means.

8. The method according to claim 7, wherein said stored digital images in said codebook are clustered into a logical collection of related digital images.

9. The method of claim 1 wherein said preserving of said second digital image includes compressing said second digital image and generating therefrom a compressed digital image.

10. The method of claim 9, and further comprising:

decompressing said compressed digital image image to yield a third digital image;

using said index code record to identify and access a fourth digital image;

combining said third digital image record with said fourth digital image record to yield a restored digital image.

11. The method of claim 10 and further comprising:

displaying the restored digital image in a form in which said restored digital image may be viewed.

12. A method for recording an image from a document, said method comprising the steps of:

(a) scanning the document, said scanning including creating a first digital image corresponding to said image on said document;

(b) searching a codebook comprising a plurality of stored digital images for one of said digital images which is present in at least a portion or portions of said first digital image; and

(c) on a determination that none of said stored digital images are present in said first digital image, creating a partial digital image representing said at least a portion or portions of the first digital image; and

(d) inserting said at least a portion or portions of said partial digital image into said codebook.

13. The method according to claim 12, wherein said stored digital images in said codebook are clustered into a logical collection of related digital images.

14. A method for recording an image from a document, said method comprising the steps of:

(a) scanning the document, said scanning including creating a first digital image corresponding to said image on said document;

(b) searching a codebook comprising a plurality of stored digital images for at least one of said stored digital images which are present in said first digital image;

(c) locating said at least one of said plurality of stored digital images in said codebook which are present in said first digital image;

(d) selecting one of said at least one of said plurality of stored digital images;

(e) producing an electronic index code identifying said one of said at least one of said plurality of stored digital images as being present in said first digital image;

(f) generating a second digital image comprising the portion or portions of said first digital image that are not present in said one of said at least one of said plurality of stored digital images; and

(g) preserving said second digital image, said electronic index code, and said codebook in a form such that said first digital image can be reproduced from a combination of said second digital image and said one of said at least one of said plurality of stored digital images.

15. The method according to claim 14, wherein said stored digital images in said codebook are clustered into a logical collection of related digital images.

16. The method of claim 14 wherein said preserving of said second digital image includes compressing said second digital image.

17. The method of claim 16, and further comprising:

decompressing said compressed digital image image to yield a third digital image;

using said index code to identify and access a fourth digital image;

combining said third digital image record with said fourth digital image record to yield a restored digital image.

18. The method of claim 17 and further comprising:

displaying the restored digital image in a form in which said restored digital image may be viewed.

19. An apparatus for recording an image from a document, said apparatus comprising:

(a) an input device for receiving said image from said document as an input and creating as an output a first digital image corresponding to the image;

(b) a database storage device storing a codebook comprising a plurality of stored digital images;

(c) at least one processor having a predetermined program, said processor performing the steps of

(i) comparing said first digital image with said stored digital images of said codebook;

(ii) identifying one of said stored digital images which constitutes a part of said first digital image;

(iii) producing an electronic index code indexed for said codebook, said electronic index code identifying said stored digital image as constituting part of said first digital image;

(iv) removing said stored digital image from said first digital image, said removing including producing a second digital image constituting the portion of said first digital image which is different from said stored digital image; and

(d) a memory receiving and preserving an input of said second digital image and said electronic index code.

20. The apparatus according to claim 19, further comprising a plurality of processors operating in parallel.

21. The apparatus according to claim 19, wherein said codebook comprises said stored digital images clustered in a logical collection of related digital images.

22. The method of claim 19 wherein said preserving of said second digital image includes compressing said second digital image.

23. The method of claim 22, and further comprising:

decompressing said compressed digital image image to yield a third digital image;

using said index code record to identify and access a fourth digital image;

combining said third digital image record with said fourth digital image record to yield a restored digital image.

24. The method of claim 23 and further comprising:

displaying the restored digital image in a form in which said restored digital image may be viewed.

25. A method for recording an image from a document, said method comprising the steps of:

(a) scanning the document, said scanning including creating a first digital image corresponding to said image on said document;

(b) searching a codebook comprising a plurality of stored digital images for one of said digital images which is present in said first digital image;

(c) producing an electronic index code identifying said one of said stored digital images as being present in said first digital image;

(d) generating a second digital image comprising the portion or portions of said first digital image that are not present in said stored digital image;

(e) deriving an indication from said second digital image whether said document is authentic; and

(f) in the absence of said indication, generating a notification that said document is not authentic.

26. The method according to claim 25, wherein said stored digital images in said codebook are clustered into a logical collection of related digital images.

27. A method for recording an image from a document, said method comprising the steps of:

(a) scanning the document, said scanning including creating a first digital image corresponding to said image on said document;

(b) searching a codebook comprising a plurality of stored digital images for one of said digital images which is present in said first digital image;

(c) creating a second digital image from said first digital image;

(d) storing said second digital image in said codebook;

(e) producing an electronic index code identifying said one of said stored digital images as being present in said first digital image;

(f) generating a second digital image comprising the portion or portions of said first digital image that are not present in said one of said stored digital images; and

(g) preserving said second digital images said electronic index code, and said codebook in a form such that said first digital image can be regenerated therefrom.

28. The method of claim 27 wherein said preserving of said second digital image includes compressing said second digital image.

29. The method of claim 28, and further comprising:

decompressing said compressed digital image image to yield a third digital image;

using said index code record to identify and access a fourth digital image;

combining said third digital image record with said fourth digital image record to yield a restored digital image.

30. The method of claim 29 and further comprising:

displaying the restored digital image in a form in which said restored digital image may be viewed.

31. A method for storing a document image of a document, said method comprising:

optically processing said document and generating a first electronic record corresponding to said document image;

generating second and third electronic records from said first electronic record,

said second electronic record identifying at least one of a plurality of image records stored in an electronic codebook of image records, said identified image record matching a portion of said first electronic record,

said third electronic record representing a portion of said first electronic record which is not present in said identified image record,

said second and third electronic records and said codebook being in a form such that said first electronic record can be recreated therefrom.

32. The method according to claim 31, wherein said third electronic record is in a compressed form.

33. The method of claim 32 and further comprising;

decompressing said third electronic record to yield a decompressed digital image;

using said index code record to identify and access a fourth electronic record;

combining said decompressed digital image with said fourth electronic record to yield a restored digital image.

34. The method of claim 33 and further comprising;

displaying the restored digital image in a form in which said restored digital image may be viewed.