Detecting overlapping images in an automatic image segmentation device with the presence of severe bleeding

• US 6,839,466 B2
• Filed: 10/04/1999
• Issued: 01/04/2005
• Est. Priority Date: 10/04/1999
• Status: Expired due to Fees

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Venable, Dennis L.
• Primary Examiner(s): Dastouri, Mehrdad
• Application Number:
  US09/411,212
• Publication Number:
  US 20030152272A1
• Time in Patent Office: 1,919 Days
• Field of Search: 382/190, 382/193, 382/195, 382/199, 382/266, 382/270, 382/289, 382/290, 382/291, 382/292, 382/176, 382/286, 382/167, 345/419, 345/634, 358/462, 358/488, 358/1.9, 358/444, 356/141.5
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/20192 Edge enhancement; Edge preservation
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Abstract

A method for processing multiple digital images using an imaging input device so as to reduce bleeding of edges of the multiple digital images by determining the boundaries of each of the digital images, including detecting a boundary of a first image; detecting a boundary of a second image; determining an overlap between the detected boundaries of the first image and second images; calculating the overlap between the first and second images and modeling a third image from the calculated overlap of the first and second images wherein the third image contains at least said first and second images and represents a depiction of said first and second images without an overlap between said first and second images.

Claims

1. A method for processing multiple structured images using an imaging input device with a smart platen so as to reduce occurrence of image orphans due to the bleeding of edges in scanning multiple digital images arranged upon the smart platen, comprising:

arranging multiple objects upon the imaging input device with a smart platen for scanning;

scanning the multiple objects with the imaging input device with a smart platen so as to produce an input image;

generating linked lists with greater than three edge pixels therein for the input image data produced in the scanning step;

generating a boundary of a first structured image from the linked lists;

generating a boundary of a second structured image from the linked lists;

identifying a first bounding box for the first structured image from its generated boundary;

identifying a second bounding box for the second structured from its generated boundary;

determining whether an overlap exists between the identified bounding boxes of the first structured image and second structured image;

merging the first structured image and the second structured image for a third structured image when an overlap of bounding boxes is determined; and

,

modeling a new bounding box for the third structured image from the merging of the first and second structured images wherein the new bounding box contains the orphaned first and second structured images and represents a depiction of the orphaned first and second structured images.

2. The method according to claim 1, comprising:

wherein the step of determining an overlap of the first and second bounding boxes uses a maximum threshold value in at least an X-axial direction for the first and second images.

3. The method according to claim 1, comprising:

wherein the step of determining an overlap of the first and second bounding boxes uses a minimum threshold value in at least an X-axial direction for the first and second bounding boxes.

4. The method according claim 1, comprising:

wherein the step of determining an overlap of the first and second bounding boxes further comprises;

determining a maximum threshold value in at least an X-axial direction for the first and second bounding boxes,

determining a minimum threshold value in at least an X-axial direction for the first and second bounding boxes, and

comparing the maximum and minimum values of the first and second bounding boxes in a manner so as to ascertain an overlap between the first and second bounding boxes.

5. The method according to claim 4, comprising:

wherein the step of comparing includes further at least determining if a minimum threshold value in the X-axial direction of the first bounding box is greater than a maximum threshold value in the X-axial direction of the second bounding box.

6. The method according to claim 4, comprising:

wherein the step of comparing includes further at least determining if a maximum threshold value in the X-axial direction of the first bounding box is greater than a minimum threshold value in the X-axial direction of the second bounding box.

7. The method according to claim 1, comprising:

wherein the step of determining an overlap of the first and second bounding boxes further comprises;

comparing a maximum value in the y-axial direction of the first bounding box with a minimum value in the y-axial direction of the second bounding box, and

comparing a minimum value in the y-axial direction of the first bounding box with a maximum value in the y-axial direction of the second bounding box.

8. A method for processing multiple structured images using an imaging input device with a smart platen so as to reduce occurrence of image orphans due to the bleeding of contour edges of multiple digital images arranged upon the smart platen by generating an object defined by contour edges of particular sets of the multiple digital images, comprising:

arranging multiple objects upon the imaging input device with a smart platen for scanning;

scanning the multiple objects with the imaging input device with a smart platen so as to produce an input image;

generating linked lists with greater than three edge points therein for the input image data produced in the scanning step;

detecting a set of edges of a first object from the linked lists;

detecting a set of edges of a second object from the linked lists;

identifying a first bounding box for the first object from its detected set of edges;

identifying a second bounding box for the second object from its detected set of edges;

determining an overlap between the identified first and second bounding boxes of the first and second objects;

calculating the overlap between the first and second bounding boxes of the first and second objects; and

,

modeling a third object by ascertaining the calculated overlap of the first and second bounding boxes wherein the third object contains at least said first and second objects when the calculated overlap ascertains that they are orphaned.

9. The method according to claim 8, comprising:

wherein the step of determining an overlap of the first and second bounding boxes uses a maximum threshold value in a horizontal direction of the set of edges of the first and second bounding boxes.

10. The method according to claim 8, comprising:

wherein the step of determining an overlap of the first and second bounding boxes uses a maximum threshold value in a horizontal direction of the set of edges of the first and second bounding boxes.

11. The method according claim 8, comprising:

wherein the step of determining an overlap of the set of edges of the first and second bounding boxes further comprises;

determining a maximum threshold value in at least a horizontal direction of the set of edges of the first and second bounding boxes,

determining a minimum threshold value in at least a horizontal direction of the set of edges of the first and second bounding boxes, and

comparing the maximum and minimum values of the set of edges of the first and second bounding boxes in a manner so as to determine if there is an overlap of the set of edges between the first and second bounding boxes.

12. The method according to claim 11, comprising:

wherein the step of comparing includes further at least determining it a minimum threshold value in the horizontal axial direction of a particular edge of the first bounding box is greater than a maximum threshold value in the horizontal direction of a particular edge of the second bounding box.

13. The method according to claim 11, comprising:

wherein the step of comparing includes further at least determining if a maximum threshold value in the horizontal direction of a particular edge of the first bounding box is greater than a minimum threshold value in the horizontal direction of a particular edge of the second bounding box.

14. The method according to claim 8, comprising:

wherein the step of determining an overlap of set of edges of the first and second bounding boxes further comprises;

comparing a maximum value in the vertical direction of the set of edges of the first bounding box with a minimum value in the vertical direction of the set of edges of the second bounding box, and

comparing a minimum value in the vertical direction of the set of edges of the first bounding box with a maximum value in the vertical direction of the set of edges of the second bounding box.