Method and apparatus for image hand markup detection using morphological techniques

• US 5,201,011 A
• Filed: 11/19/1991
• Issued: 04/06/1993
• Est. Priority Date: 11/19/1991
• Status: Expired due to Term

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Bloomberg, Dan S., Dasari, Lakshmi
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): Johns, Andrew W.
• Application Number:
  US07/794,275
• Time in Patent Office: 504 Days
• Field of Search: 382/9, 382/22, 382/47, 382/48, 382/55, 358/452, 358/453
• US Class Current: 382/175
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area

Abstract

An image markup detection device and method identifies and extracts markup lines and regions marked automatically or interactively by a user with an ordinary pen or pencil. Only morphological image processing operations on a scanned source image are used, resulting in the extrapolation of markup lines and marked region. The markup lines are either extracted from the image, or the background information of the image (e.g., text) is removed, leaving only the markup lines. The marked region can then be printed, transferred or otherwise processed.

Claims

1. A method for processing a scanned first image in a digital computer to identify a location of non-transparent hand marks and hand marked regions, the method comprising the steps of:

(a) performing a plurality of morphological OPENING operations on the first image using a first set of structuring elements, each OPENING operation using a different structuring element from said first set, and taking a UNION of the results of said plurality of OPENING operations to form a second image; and

(b) creating bounding boxes around mark-up lines in the second image, said bounding boxed identifying the hand marked regions.

2. The method as recited in claim 1, further comprising decreasing the resolution of said first image prior to performing step (a).

3. The method as recited in claim 2, wherein step (a) further comprising the steps of:

reducing an intermediate image formed by taking the UNION of said plurality of OPENING operations by two times, using a threshold of 1;

performing a second plurality of morphological OPENINF operations on the intermediate using the first set of structuring elements; and

taking a UNION of the results of said second plurality of OPENING operations to form said second image.

4. The method as recited in claim 1 wherein some of the bounding boxes having less than a predetermined size are classified as small bounding boxes, and wherein the small bounding boxes are eliminated.

5. A method for processing a scanned first image in a digital computer to identify a location of non-transparent hand marks and marked regions, the method comprising the steps of:

(a) CLOSING the first image with a first horizontal structuring element, forming a second image;

(b) XORing the first image with the second image, forming a third image;

(c) DILATING the third image with a solid square structuring element, ANDing the DILATION of the third image with the first image, forming a fourth image;

(d) XORing the fourth image with the first image, forming a fifth image;

(e) performing a plurality of morphological OPENING operations on the fifth image using a first set of structuring elements, each OPENING operations using a different structuring element from said first set, and taking a UNION of the results of said plurality of OPENING operations, forming a sixth image;

(f) OPENING the sixth image with a second horizontal structuring element, forming a seventh image;

(g) reducing the seventh image by a first predetermined factor, forming an eighth image;

(h) CLOSING the eighth image with the first set of structuring elements forming a ninth image;

(i) performing a plurality of morphological OPENING operations on the ninth image using the first set of structuring elements, each OPENING operation using a different structuring element from said first set, and taking a UNION of the results of said plurality of OPENING operations, forming a tenth image;

(j) reducing the tenth image by a second predetermined factor, forming an eleventh image;

(k) filling bounding boxes of the eleventh image, forming a twelfth image;

(l) expanding the twelfth image to a full scale; and

(m) ANDing the twelfth image with the first image, extrapolating the hand marked regions.

6. A topological method for processing an image in a digital computer for extraction of regions of a document image entirely encircled by non-transparent hand marks, the method comprising the steps of:

(a) flood filling the document image from edges of said document image;

(b) bitwise inverting the flood-filled document image;

(c) flood filling the inverted document image produced in step (b) from edges of said inverted document image; and

(d) bitwise inverting the document image produced in step (c).

7. A semitopological method for processing an image in a digital computer for extracting regions of a document image entirely encircled by non-transparent hand marks, the method comprising the steps of:

(a) flood filling the document image from edges of said document image;

(b) bitwise inverting the flood-filled document image;

(c) OPENING the document image produced in step (b) using a solid structuring element of a first predetermined size;

(d) CLOSING the document image produced in step (c) using a solid structuring element of a second predetermined size; and

(e) ANDing the CLOSED document image produced in step (d) with the original document image.

8. The method as recited in claim 7 wherein the first predetermined size is a size less than a size of a character.

9. The method as recited in claim 7, wherein the second predetermined size is a size at least as large as a size of a character.

10. The method of claim 7, wherein prior to performing step (e) the CLOSED document image produced in step (d) is ERODED with a structuring element.

11. A method for processing a document image in a digital computer for identification in the document image of hand drawn lines comprising the steps of:

(a) OPENING the document image using at least one structuring element;

(b) finding bounding boxes around image units in the OPENED document image produced in step (a); and

(c) testing the document image produced in step (b) to identify bouding boxes containing hand drawn lines.

12. The method as recited in claim 11 further comprising reducing the document image prior to performing step (a).

13. The method of claim 11, wherein said at least one structuring element used in step (a) is a horizontal structuring element so that horizontal lines are identified in step (c).

14. The method of claim 11, wherein said at least one structuring element used in step (a) is a vertical structuring element so that vertical lines are identified in step (c).

15. The method of claim 11, further comprising the steps of:

(d) performing a fill operation by using a result of step (c) as a seed and the original image as a clipping mask; and

(e) XORing a result of step (d) with the original document image so as to remove hand drawn marks from the document.

16. The method of claim 11, wherein said testing performed in step (c) includes comparing an asperity ratio of said bounding boxes to a threshold asperity ratio.

17. The method of claim 11, wherein said testing performing in step (c) includes comparing a fraction of ON pixels in each bounding box with a threshold fraction.

18. A method for processing a document image in a digital computer for identifying hand drawn encircled regions of the document image, the method comprising the steps of:

(a) performing an OPENING operation on the document image;

(b) finding bounding boxes of image units in the OPENED document image produced in step (a);

(c) testing the document image produced in step (b) to identifying hand drawn lines; and

(d) performing a fill operation by using a result of step (c) as a seed and the original image as a clipping mask.

19. The method as recited in claim 18, further comprising decreasing the resolution of said document image prior to performing step (a).

20. The method as recited in claim 18 wherein the OPENING operation in step (a) uses horizontal structuring elements.

21. The method as recited in claim 18 wherein the OPENING operation in step (a) uses vertical structuring elements.

22. The method of claim 18, further comprising the steps of:

(e) finding bounding boxes of the encircled hand drawn regions produced in step (d);

(f) extracting the encircled regions from the original document image so as to identify contents of the encircled regions; and

(g) XORing a result of step (d) with a result of step (f) so as to extract the contents of the encircled regions.