Image processing system with automatic image cropping and skew correction

• US 6,430,320 B1
• Filed: 04/10/2000
• Issued: 08/06/2002
• Est. Priority Date: 04/09/1998
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Company (HP Inc.)
• Inventors: Sansom-Wai, Cindy, Jia, Charles Chi, Woodson, Anne-Marie, Tretter, Daniel R
• Primary Examiner(s): Tran, Phuoc
• Assistant Examiner(s): Alavi, Amir
• Application Number:
  US09/546,110
• Time in Patent Office: 848 Days
• Field of Search: 382/288, 382/289, 382/290, 382/291, 382/292, 382/293, 382/294, 382/295, 382/199, 382/282, 382/299, 382/300, 382/283, 382/205, 382/240, 382/190, 382/195, 382/298, 382/275, 358/496, 358/497, 358/490, 358/486, 358/487, 358/488, 358/474, 358/429
• US Class Current: 382/289
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: H04N 1/38 Circuits or arrangements for blanking or otherwise eliminating unwanted parts of pictures H04N1/387 takes precedence
• CPC Class Codes: H04N 1/387 Composing, repositioning or otherwise geometrically modifying originals
• CPC Class Codes: H04N 1/3873 defined only by a limited number of coordinate points or parameters, e.g. corners, centre; for trimming
• CPC Class Codes: H04N 1/3878 Skew detection or correction

Abstract

A system and method is described for automatically determining in a scanned document image the presence of unwanted extraneous information caused by an extraneous device and scanner background information. Once the presence of this information is determined, the system and method of the present invention can compute, for instance, skew and crop statistics. From this, the image can be automatically deskewed and cropped appropriately without the background and extraneous information. The system and method accomplishes this by first determining the presence of unwanted extraneous and background information and then appropriately processing the document image. The extraneous information is ignored during deskew and crop computations. Also, the scanner background and the extraneous information are prevented from being included in the final digital representation of the image.

Claims

1. A method of processing a document image inside a scan image having a plurality of scan lines of pixels, comprising:

(a) applving at least one scan processing simulation to a portion of the scan image to produce a first processed simulation in a first resolution mode;

(b) providing a visual preview of the first processed simulation for approval;

(c) reversing the applied simulation to return the scan image to its original state and then either returning to step (a) to allow application of another scan processing simulation if the preview is disapproved or continuing to step (d) if the preview is approved; and

(d) secondarily applying the approved scan processing simulation to the portion of the scan image in a second resolution mode that is higher than the first resolution mode.

2. The method of claim 1 wherein the simulation includes automatically comparing a neighborhood of pixels located around a group of successively received scan lines from the scan image with predetermined background pixels to define image boundaries for each group of scan lines, forming an edge segment during receipt of the scan lines by extending an image boundary between successive groups of scan lines and determining a skew angle by calculating an aggregate slope of all edge segments longer than a predetermined length value, and further comprising searching for predefined known characteristics within the document image and ignoring the predefined known characteristics if found.

3. The method of claim 1, wherein the scan image includes document image pixels of the document image and background pixels of the scan image, wherein comparing a neighborhood of pixels further comprises:

receiving a neighborhood of pixels located around a group of scan lines; and

comparing the group of scan lines of the scan image with corresponding background pixels to define left and right image boundaries for each group of scan lines.

4. The method of claim 3, further comprising:

comparing color of the group of scan lines with color of the corresponding background pixels;

comparing color of adjacent pixels of the group of scan lines with color of the corresponding background pixels; and

confirming the location of an image boundary when the color of the group of scan lines is different from that of the corresponding background pixels and the color of the adjacent pixels are different from that of the corresponding background pixels.

5. The method of claim 4, wherein the simulation includes at least one of cropping, skewing and rotating the scan image.

6. The method of claim 1, further comprising ending the edge segment and generating a new edge segment that extends from an end scan line of the group of scan lines if the group of scan lines do not continue the edge segment.

7. A computer apparatus, comprising:

a computer executable program stored on a storage medium. the computer executable program, when executed, processes a document image inside a scan image having a plurality of scan lines of pixels by;

sending a portion of the scan image in a first resolution mode to a digital processor. applying and storing at least one scan processing simulation to a portion of the scan image, allowing approval or disapproval of the simulation, reversing the applied simulation, if the simulation is approved, sending a portion of the scan image in a second resolution mode higher than the first resolution mode to the digital processor without the simulation and applying the stored simulation to the portion of the scan image in the second resolution mode.

8. The apparatus of claim 7, wherein the scan image includes image pixels of the document image and background pixels of the scan image, further comprising,

receiving a neighborhood of pixels located around a group of scan lines;

comparing color of the group of scan lines with color of corresponding background pixels;

comparing color of adjacent pixels of the group of scan lines with color of the corresponding background pixels; and

confirming the location of an image boundary when the color of the group of scan lines is different from that of the corresponding background pixels and the color of the adjacent pixels are different from that of the corresponding background pixels.

9. The apparatus of claim 8, further comprising a first set of instructions that receives and examines a neighborhood of pixels located around a group of scan lines of pixels of the scan image, a second set of instructions that compares a neighborhood of pixels located around a group of scan lines with predetermined background pixels to define image boundaries for each group of scan lines, a third set of instructions that forms an edge segment by extending an image boundary between continuous groups of scan lines and a fourth set of instructions that determines the skew angle by calculating the slope of all edge segments longer than a predetermined length value.

10. The apparatus of claim 7, further comprising a first subset of the third set of instructions that ends the edge segment and generates a new edge segment that extends from an end scan line of the group of scan lines if the group of scan lines do not continue the edge segment.

11. The apparatus of claim 9, further comprising

a first subset of the fourth set of instructions that determines if the document image has a rectangular shape by determining the geometrical relationship to previous edge segments and if the edge segment is longer than a predetermined length value;

and

a second subset of the fourth set of instructions that sets the skew angle to zero if the document image is not within predefined limits of the rectangular shape.

12. The apparatus of claim 7, further comprising a fifth set of instructions that searches for predefined known characteristics within the document image and ignores the known characteristics if found.