System for aligning document images when scanned in duplex mode

• US 6,348,980 B1
• Filed: 04/14/2000
• Issued: 02/19/2002
• Est. Priority Date: 05/07/1997
• Status: Expired due to Term

• Current Assignee: Ricoh Company Limited, Ricoh Corporation (Ricoh Company Limited)
• Original Assignee: Ricoh Company Limited, Ricoh Corporation (Ricoh Company Limited)
• Inventors: Cullen, John F., Hull, Jonathan J., Peairs, Mark
• Primary Examiner(s): ROGERS, SCOTT A
• Application Number:
  US09/549,758
• Time in Patent Office: 676 Days
• Field of Search: 358/1.9, 358/463, 358/464, 358/448, 358/447, 358/452, 358/453, 358/537, 358/538, 358/465, 382/275, 382/260, 382/254, 382/209, 382/217, 382/218, 382/219, 382/263, 382/264
• US Class Current: 358/1.9
• CPC Class Codes: H04N 1/00572 with refeeding for double-sided scanning, e.g. using one scanning head for both sides of a sheet
• CPC Class Codes: H04N 1/00575 Inverting the sheet prior to refeeding
• CPC Class Codes: H04N 1/047 Detection, control or error compensation of scanning velocity or position H04N1/0402 and H04N1/17 take precedence
• CPC Class Codes: H04N 1/12 using the sheet-feed movement or the medium-advance or the drum-rotation movement as the slow scanning component, e.g. arrangements for the main-scanningsheet-feed movement by translatory movement of a flat picture-bearing surface H04N1/1008; main-scanning using oscillating or rotating mirrors H04N1/113; using multi-element arrays H04N1/19
• CPC Class Codes: H04N 1/32609 Fault detection or counter-measures, e.g. original mis-positioned, shortage of paper
• CPC Class Codes: H04N 1/3263 of reading apparatus or transmitter, e.g. original jam
• CPC Class Codes: H04N 1/32657 locally
• CPC Class Codes: H04N 1/40 Picture signal circuits H04N1/387 takes precedence
• CPC Class Codes: H04N 1/4095 Correction of errors due to scanning a two-sided document, i.e. show-through correction
• CPC Class Codes: H04N 2201/04703 using the scanning elements as detectors, e.g. by performing a prescan
• CPC Class Codes: H04N 2201/04743 by detecting the image directly detecting reference images H04N2201/04717
• CPC Class Codes: H04N 2201/04787 by changing or controlling the addresses or values of pixels, e.g. in an array, in a memory, by interpolation

Abstract

A system and method for handling duplex documents by exploiting bleed-through of the image on the back side of a document. The images of the back sides and front sides of documents are associated with one another to assure correct output in copying, faxing, scanning, etc. This increases reliability, eases recovery from errors including paper jams. Improved document handling capabilities also include avoiding twice duplicated and skipped pages and correcting page orientation errors.

Claims

1. A method of processing a document page comprising the steps of:

a) receiving first side image data representing at least a portion of a first side of said document page;

b) extracting a set of connected components from said first side image data;

c) erasing pixels representing said set of connected components from said first side image data; and

d) extracting a first set of features from said first side image data as processed by said c) step, whereby said first set of features represent a bleed-through image of at least a portion of a second side of said document page.

2. The method of claim 1 wherein extracting said first set of features comprises flipping said first side image data as processed by said c) step.

3. The method of claim 1 further comprising:

e) scanning said second side of said document page to capture second side image data;

f) removing pixels representing said set of connected components from said second side image data; and

g) extracting a second set of features from said second side image data as processed by said f) step.

4. The method of claim 3 further comprising:

h) verifying said second side of said document page as a match to said first side of said document page based on a match between said first set of features and said second set of features.

5. The method of claim 4 wherein a Hausdorff distance metric is used to establish a match between said first set of features and said second set of features.

6. The method of claim 4 wherein a Euclidean distance metric is used to establish a match between said first set of features and said second set of features.

7. The method of claim 1 wherein extracting said first set of features from said first side image data comprises extracting CCITT Group IV pass codes.

8. The method of claim 1 wherein extracting a set of connected components from said first side image data comprises extracting word length sequences.

9. The method of claim 1 wherein said receiving step comprises scanning in said first side of said document page.

10. A system for processing a document page, the system comprising:

a processor;

a memory coupled to the processor, the memory configured to store a plurality of code modules for execution by the processor, the plurality of code modules comprising;

a code module for receiving first side image data representing at least a portion of a first side of the document page;

a code module for extracting a set of connected components from the first side image data;

a code module for erasing pixels representing the set of connected components from the first side image data; and

a code module for extracting a first set of features from the first side image data after pixels representing the set of connected components have been erased from the first side image data, whereby the first set of features represents a bleed-through image of at least a portion of a second side of said document page.

11. The system of claim 10 wherein the code module for extracting the first set of features comprises a code module for flipping the first side image data after pixels representing the set of connected components have been erased from the first side image data.

12. The system of claim 10 wherein the plurality of code modules further comprises:

a code module for scanning the second side of the document page to capture second side image data;

a code module for removing pixels representing the set of connected components from said second side image data; and

a code module for extracting a second set of features from the second side image data after the pixels representing the set of connected components have been removed from the second side image data.

13. The system of claim 12 wherein the plurality of code modules further comprises:

a code module for verifying the second side of the document page as a match to the first side of the document page based on a match between the first set of features and the second set of features.

14. The system of claim 13 wherein a Hausdorff distance metric is used to establish a match between the first set of features and the second set of features.

15. The system of claim 13 wherein a Euclidean distance metric is used to establish a match between the first set of features and the second set of features.

16. The system of claim 10 wherein the code module for extracting the first set of features extracts CCITT Group IV pass codes.

17. The system of claim 10 wherein the code module for extracting the first set of features extracts word length sequences.

18. A computer program product stored on a computer-readable medium for extracting a bleed-through image for a document page having a first side and a second side, the computer program product comprising:

code for receiving first side image data representing at least a portion of the first side of the document page;

code for determining a set of connected components from the first side image data;

code for erasing pixels representing the set of connected components from the first side image data; and

code for extracting a set of features from the first side image data after the pixels representing the set of connected components has been erased from the first side image data, wherein the set of features represents the bleed-through image of at least a portion of the second side of the document page.