Automatic typing of raster images using density slicing

• US 5,812,695 A
• Filed: 11/14/1996
• Issued: 09/22/1998
• Est. Priority Date: 08/12/1994
• Status: Expired due to Term

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Company (HP Inc.)
• Inventors: Dawe, Julie Tsai-Hsin
• Primary Examiner(s): Kelley, Christopher S.
• Application Number:
  US08/749,041
• Time in Patent Office: 677 Days
• Field of Search: 382/165, 382/176, 382/192, 382/194, 382/257, 382/259, 382/261, 382/196, 358/462, 358/469
• US Class Current: 382/176
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A system for determining the type of graphical data within a scanned image. The system scans an image to obtain grayscale image data, and then performs a density slice operation on the grayscale image data, using a predetermined grayscale range, to produce binary image data. The system erodes the binary image data, and counts the number of black pixels remaining within the image data. If the count of the black pixels within the image exceeds a maximum acceptable pixel count, the area is considered to be continuous tone, such as a photograph, otherwise, the region is considered to be bi-tonal, such as line art or text. The system can also perform multiple density slices and erosions, using different grayscale ranges, OR the results, and then analyze the result of the OR operation to determine the type of image.

Claims

1. A method for identifying a type of image contained within scanned image data, wherein said scanned image data has a tonal value for each pixel within said scanned image data, said method comprising the steps of:

(a) density slicing each pixel of said scanned image data to produce binary image data having first and second values, comprising the steps of

(a1) density slicing each pixel of said scanned image data using a first predetermined range of density slice values to produce a first set of corresponding binary image values,

(a2) density slicing each pixel of said scanned image data using a second predetermined range of density slice values to produce a second set of corresponding binary image values, and

(a3) combining said first set of corresponding binary image values with said second set of corresponding binary image values to produce binary image data having said first value or said second value for each pixel;

(b) eroding said binary image data without dilating said binary image data;

(c) counting a number of first values in said binary image data;

(d) when said number of first values counted in step (b) is greater than a predetermined number, identifying said image as a continuous tonal type of image; and

(e) when said number of first values counted in step (b) is less than or equal to said predetermined number, identifying said image as a bi-tonal type of image.

2. The method of claim 1 wherein step (b) further comprises the steps of;

(b1) for each pixel value within said scanned image data, locating each neighbor pixel value; and

(b2) when a predetermined number of neighbor pixel values are equal to said second value, setting said pixel value to said second value.

3. The method of claim 2 wherein said predetermined number of neighbor pixel values is four.

4. The method of claim 1 wherein step (a) further comprises the steps of:

(a1) comparing each pixel value within said scanned image data to a predetermined range of values;

(a2) when a pixel value is within said range of predetermined values, setting said pixel value to said first value; and

(a3) if a pixel is outside said range of predetermined values, setting said pixel value to said second value.

5. The method of claim 1 wherein said combining of step (a3) comprises a bitwise OR operation.

6. A method for determining a type of image contained on a document, said method comprising the steps of:

(a) sending a signal to a scanner device to scan said document to obtain scanned image data having a tonal value for each pixel scanned;

(b) density slicing each pixel of said scanned image data to produce binary image data having first and second values, comprising the steps of

(b1) density slicing each pixel of said scanned image data using a first predetermined range of density slice values to produce a first set of corresponding binary image values,

(b2) density slicing each pixel of said scanned image data using a second predetermined range of density slice values to produce a second set of corresponding binary image values, and

(b3) combining said first set of corresponding binary image values with said second set of corresponding binary image values to produce binary image data having said first value or said second value for each pixel;

(c) eroding said binary image data without dilating said binary image data;

(d) counting a number of first values in said binary image data;

(e) when said number of first values counted in step (c) is greater than a predetermined number, retaining said scanned image data obtained in step (a), wherein said image contained on said document is a continuous tonal image; and

(f) when said number of first values counted in step (c) is less than or equal to said predetermined number, sending a signal to said scanner device to re-scan said document to obtain image data having binary values, wherein said image contained on said document is a bi-tonal image.

7. The method of claim 6 wherein step (c) further comprises the steps of;

(c1) for each pixel value within said scanned image data, locating each neighbor pixel value; and

(c2) when a predetermined number of neighbor pixel values are equal to said second value, setting said pixel value to said second value.

8. The method of claim 7 wherein said predetermined number of neighbor pixel values is four.

9. The method of claim 6 wherein step (b) further comprises the steps of:

(b1) comparing each pixel value within said scanned image data to a predetermined range of values;

(b2) when a pixel value is within said range of predetermined values, setting said pixel value to said first value; and

(b3) if a pixel is outside said range of predetermined values, setting said pixel value to said second value.

10. The method of claim 6 wherein said combining of step (b3) comprises a bitwise OR operation.

13. The method of claim 7 wherein said predetermined number of neighbor pixel values is four.

11. A method for determining a type of image contained on a document, said method comprising the steps of:

(a) sending a signal to a scanner device to scan said document at a first predetermined resolution to obtain scanned image data having a tonal value for each pixel scanned;

(b) density slicing each pixel of said scanned image data to produce binary image data having black and white values comprising the steps of

(b1) density slicing each pixel of said scanned image data using a first predetermined range of density slice values to produce a first set of corresponding binary image values,

(b2) density slicing each pixel of said scanned image data using a second predetermined range of density slice values to produce a second set of corresponding binary image values, and

(b3) combining said first set of corresponding binary image values with said second set of corresponding binary image values to produce binary image data having said black value or said white value for each pixel;

(c) eroding said binary image data without dilating said binary image data;

(d) counting a number of black values in said binary image data;

(e) when said number of black values counted in step (c) is greater than a predetermined number, sending a signal to said scanner device to re-scan said document at a second predetermined resolution to obtain image data having a tonal value for each pixel scanned, wherein said image contained on said document is a continuous tone image; and

(f) when said number of black values counted in step (c) is less than or equal to said predetermined number, sending a signal to said scanner device to re-scan said document at a third predetermined resolution to obtain image data having binary values, wherein said image contained on said document is a bi-tonal image.

12. The method of claim 11 wherein step (c) further comprises the steps of;

(c1) for each pixel value within said scanned image data, locating each neighbor pixel value; and

(c2) when a predetermined number of neighbor pixel values are equal to said second value, setting said pixel value to said second value.

14. The method of claim 11 wherein step (b) further comprises the steps of:

(b1) comparing each pixel value within said scanned image data to a predetermined range of values;

(b2) when a pixel value is within said range of predetermined values, setting said pixel value to said black value; and

(b3) if a pixel is outside said range of predetermined values, setting said pixel value to said white value.

15. The method of claim 11 wherein said combining of step (b3) comprises a bitwise OR operation.