Automatic operator-induced artifact detection in document images

• US 7,864,985 B1
• Filed: 11/03/2009
• Issued: 01/04/2011
• Est. Priority Date: 09/13/2004
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Poncin, Guillaume Raphael, Khaliq, Siraj, Lefevere, Francois-Marie
• Primary Examiner(s): BHATNAGAR, ANAND P
• Application Number:
  US12/611,311
• Time in Patent Office: 427 Days
• Field of Search: 382/100, 382/103, 382/112, 382/173, 382/174, 382/176, 382/181, 382/190, 382/195, 382/275, 382/274, 382/321, 358/448, 358/461, 358/452, 358/462, 358/500, 358/520
• US Class Current: 382/112
• CPC Class Codes: G06V 10/987 with the intervention of an operator
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 40/107 Static hand or arm
• CPC Class Codes: H04N 1/00488 providing an audible output to the user
• CPC Class Codes: H04N 1/0049 providing a visual indication to the user, e.g. using a lamp H04N1/00408 takes precedence
• CPC Class Codes: H04N 1/00795 Reading arrangements details of scanning heads H04N1/024; scanning arrangements therefor H04N1/04
• CPC Class Codes: H04N 1/00801 according to characteristics of the original
• CPC Class Codes: H04N 1/00824 for displaying or indicating, e.g. a condition or state details of displaying or indicating means H04N1/00405
• CPC Class Codes: H04N 2201/0098 User intervention not otherwise provided for, e.g. placing documents, responding to an alarm
• CPC Class Codes: H04N 2201/0434 specially adapted for scanning pages of a book

Abstract

Techniques for scanning a document, such as a book, magazine, or catalog, are described in which artifacts (e.g., a hand or other body part) in the scanned image are automatically detected. When the artifact is determined to be in a critical portion of the image, a signal may be issued to re-scan the image.

Claims

1. A method performed by a computer device, comprising:

receiving an image of a scanned page of a document;

constructing a histogram based on value attributes of the image of the scanned page;

identifying a threshold point for the image of the scanned page based on a local minimum present in the histogram;

mapping the identified threshold point onto the image of the scanned page to identify a critical area and a non-critical area of the image of the scanned page;

determining whether the critical area includes an operator-induced artifact; and

issuing a signal to re-scan the scanned page based on determining that the critical area includes the operator-induced artifact.

2. The method of claim 1, where constructing the histogram based on value attributes of the image of the scanned page includes constructing the histogram based on value attributes of a hue, saturation, and value (HSV) model, where the value attributes include attributes of color, percentage of white, and brightness or intensity.

3. The method of claim 1, where constructing the histogram based on value attributes of the image of the scanned page includes constructing the histogram based on value attributes of a hue, lightness, and saturation (HLS) model.

4. The method of claim 1, where the critical area includes a text portion of the image of the scanned page, and the non-critical area includes a white space portion or a background portion of the image of the scanned page.

5. The method of claim 1, further comprising:

determining that the non-critical area includes the operator-induced artifact and the critical area does not include the operator-induced artifact; and

processing the image of the scanned page when the non-critical area includes the operator-induced artifact and the critical area does not include the operator-induced artifact.

6. The method of claim 5, where processing the image of the scanned page includes performing an operation to remove the operator-induced artifact from the non-critical area without rescanning the scanned page.

7. The method of claim 6, where performing the operation to remove the operator-induced artifact from the non-critical area includes extending an area surrounding the operator-induced artifact to cover an area occupied by the operator-induced artifact.

8. The method of claim 1, further comprising:

identifying the operator-induced artifact within the image of the scanned page based on locating a portion, of the image of the scanned page, with hue and saturation values that correspond to human skin.

9. The method of claim 1, where issuing the signal includes notifying the operator, visually or audibly, that the scanned page needs to be rescanned.

10. A scanning system, comprising:

a memory to store instructions; and

a processor to execute the instructions to;

receive an image of a scanned page of a document,

construct a histogram based on value attributes of the image of the scanned page,

identify a threshold point for the image of the scanned page based on a local minimum present in the histogram,

map the identified threshold point onto the image of the scanned page to identify a text portion and a non-text portion of the scanned page,

identify an operator-induced artifact on the image of the scanned page,

determine whether the operator-induced artifact is present in the text portion or the non-text portion,

process the image of the scanned page, without rescanning the scanned page, when the operator-induced artifact is present in the non-text portion and not in the text portion, and

generate a signal to rescan the scanned page when the operator-induced artifact is present in the text portion.

11. The scanning system of claim 10, where, when constructing the histogram based on value attributes of the image of the scanned page, the processor is to construct the histogram based on value attributes of a hue, saturation, and value (HSV) model, where the value attributes include attributes of color, percentage of white, and brightness or intensity.

12. The scanning system of claim 10, where, when constructing the histogram based on value attributes of the image of the scanned page, the processor is to construct the histogram based on value attributes of a hue, lightness, and saturation (HLS) model.

13. The scanning system of claim 10, where the non-text portion includes a white space portion or a background portion of the image of the scanned page.

14. The scanning system of claim 10, where, when processing the image of the scanned page, the processor is to perform an operation to remove the operator-induced artifact from the non-text portion without rescanning the scanned page.

15. The scanning system of claim 14, where, when performing the operation to remove the operator-induced artifact from the non-text portion, the processor is to extend an area surrounding the operator-induced artifact to cover an area occupied by the operator-induced artifact.

16. The scanning system of claim 10, where, when identifying the operator-induced artifact, the processor is to identify the operator-induced artifact within the image of the scanned page based on locating a portion, of the image of the scanned page, with hue and saturation values that correspond to human skin.

17. The scanning system of claim 10, where the signal is a visual alarm or an audible alarm.

18. A scanning system, comprising:

a memory to store instructions; and

a processor to execute the instructions to;

receive an image of a scanned page of a document,

construct a histogram based on value attributes of the image of the scanned page,

identify, from the histogram, a threshold point for the image of the scanned page, the threshold point corresponding to a transition between a text portion and a non-text portion of the scanned page,

identify an operator-induced artifact on the image of the scanned page,

determine that the operator-induced artifact is present in the non-text portion, and

process the image of the scanned page to remove the operator-induced artifact from the non-text portion, without rescanning the scanned page, when the operator-induced artifact is present in the non-text portion.

19. The scanning system of claim 18, where, when determining that the operator-induced artifact is present in the non-text portion, the processor is to determine that the operator-induced artifact is also present in the text portion, and

where the processor is further to generate a signal to rescan the scanned page when the operator-induced artifact is present in the text portion.

20. The scanning system of claim 18, where, when processing the image of the scanned page, the processor is to extend an area surrounding the operator-induced artifact to cover an area occupied by the operator-induced artifact.

21. The scanning system of claim 18, where, when identifying the operator-induced artifact, the processor is to identify the operator-induced artifact within the image of the scanned page based on locating a portion, of the image of the scanned page, with hue and saturation values that correspond to human skin.