Method and system for classifying scanned-media

• US 20050271265A1
• Filed: 06/04/2004
• Published: 12/08/2005
• Est. Priority Date: 06/04/2004
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Eschbach, Reiner, Wang, Shen-Ge, Sharma, Gaurav
• Granted Patent: US 7,272,261 B2
• Time in Patent Office: Days
• US Class Current: 382/157
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

A method for automatically classifying a printed image, includes scanning the printed image; selecting an n by n block of pixels from the scanned image; calculating an array of DCT coefficients of the pixel block, wherein the array of calculated DCT coefficients are representative of spatial frequency and spatial orientation of the pixel block; comparing the DCT coefficients with an array of predetermined values, wherein the array of predetermined values are indicative of different image marking processes used to produce printed images; and determining an image marking process used to create the printed image based on the comparison of the DCT coefficients with the array of predetermined values. The array of DCT coefficients may be sampled into a feature set and the feature set provided to a neural network to output the determined image marking process.

Claims

1. A method for automatically classifying a printed image, comprising:

scanning the printed image;

selecting an n by n block of pixels from the scanned image;

calculating an array of DCT coefficients of the pixel block, wherein the calculated DCT coefficients are representative of spatial frequency and spatial orientation of the pixel block;

inputting the array of DCT coefficients into a classifier which has been configured to identify different image marking processes used to produce printed images using DCT coefficients; and

determining an image marking process used to create the printed image based on the array of DCT coefficients.

2. The method of claim 1, wherein inputting the array of DCT coefficients into a classifier comprises comparing the array of DCT coefficients with an array of predetermined values, wherein the array of predetermined values are indicative of different image marking processes used to produce printed images.

3. The method of claim 1, further comprising:

sampling the array of DCT coefficients to produce a feature set of the pixel block; and

inputting the feature set to the classifier to determine the image marking process used to create the printed image.

4. The method of claim 3, wherein the sampling step comprises:

grouping the array of DCT coefficients into a DC term, segments of DCT coefficients having similar radial spatial frequencies, and segments of DCT coefficients having similar spatial orientations; and

for each segment, calculating a sum of absolute values of all DCT coefficient in the segment to produce a feature of the pixel block, wherein the feature set includes the DC term and all segments features.

5. The method of claim 1, wherein the classifier comprises a neural network.

6. The method of claim 5, further comprising training the neural network with known examples of printed images.

7. The method of claim 1, wherein the determined image marking process comprises a photographic image marking process.

8. The method of claim 1, wherein the determined image marking process comprises a lithographic image marking process.

9. The method of claim 1, wherein the determined image marking process comprises a Xerographic image marking process.

10. The method of claim 1, wherein the determined image marking process comprises an inkjet image marking process.

11. The method of claim 3, wherein the n=8 and the feature set comprises the DC term, 7 spatial frequency terms and 5 spatial orientation terms.

12. The method of claim 1, further comprising selecting a color calibration profile for the printed image based on the determined image marking process.

13. The method of claim 1, further comprising:

selecting an n by n block of pixels from the scanned image in each color channel;

for each channel'"'"'s pixel block;

calculating DCT coefficients of the pixel block, wherein the calculated DCT coefficients are representative of spatial frequency and spatial orientation of the pixel block;

grouping the array of DCT coefficients into a DC term, segments of DCT coefficients having similar radial spatial frequencies, and segments of DCT coefficients having similar spatial orientations; and

for each segment, calculating a sum of absolute values of all DCT coefficient in the segment to produce a feature of the pixel block, wherein the feature set includes the DC term and all segments features; and

inputting the feature sets from all color channels and the array of predetermined values to a neural network.

14. The method of claim 13, wherein n=8 and wherein the color channels comprise red, green and blue.

15. The method of claim 13, wherein n=8 and the color channels comprise luminance, chrominance1 and chrominance2.

16. A system for automatically classifying a printed image, comprising:

a scanner for scanning the printed image;

a memory for storing the scanned image and for storing an array of predetermined values, wherein the array of predetermined values are indicative of different image marking processes used to produce printed images; and

a processor for selecting an n by n block of pixels from the scanned image, for calculating an array of DCT coefficients of the pixel block, wherein the calculated DCT coefficients are representative of spatial frequency and spatial orientation of the pixel block, for comparing the array of DCT coefficients with the array of predetermined values, wherein the array of predetermined values are indicative of different image marking processes used to produce printed images, and for determining an image marking process used to create the printed image based on the comparison of the DCT coefficients with the array of predetermined values.

17. The system of claim 16, wherein the processor, for sampling the array of DCT coefficients to produce a feature set of the pixel block;

and for comparing the feature set with the array of predetermined values to determine the image marking process used to create the printed image.

18. The system of claim 17, wherein the sampling comprises:

grouping the array of DCT coefficients into a DC term, segments of DCT coefficients having similar radial spatial frequencies, and segments of DCT coefficients having similar spatial orientations; and

for each segment, calculating a sum of absolute values of all DCT coefficient in the segment to produce a feature of the pixel block, wherein the feature set includes the DC term and all segments features.

19. The system of claim 18, wherein processor includes a neural network, responsive to the feature set and the array of predetermined values for determining an image marking process used to create the printed image.

20. The system of claim 19, wherein the neural network has been trained with known examples of printed images.