Spectrum inverter apparatus and method

• US 6,647,140 B1
• Filed: 05/18/1999
• Issued: 11/11/2003
• Est. Priority Date: 05/18/1999
• Status: Expired due to Fees

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Bank One Insurance Holdings Incorporated (JP Morgan Chase & Co)
• Inventors: Wang, Shen-Ge, Sharma, Gaurav
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): Alavi, Amir
• Application Number:
  US09/313,735
• Time in Patent Office: 1,638 Days
• Field of Search: 356/326-330, 356/351, 356/354, 356/356, 356/428-430, 235/380-386, 235/462.01, 235/462.02, 235/472.01, 235/472.03, 358/1.9, 358/515, 358/518, 358/523, 358/524, 358/525, 358/487, 382/156, 382/155, 382/157, 382/158, 382/162, 382/167, 382/164, 706/20, 706/25, 706/26, 706/23
• US Class Current: 382/162
• CPC Class Codes: H04N 1/60 Colour correction or control H04N1/54 takes precedence
• CPC Class Codes: H04N 1/6094 depending on characteristics of the input medium, e.g. film type, newspaper

Abstract

A spectrum inverter receives optical values from a scanning device and applies a spectrum inversion method to the optical values. The spectrum inversion method is selected based on a medium identifier that identifies the medium upon which the scanned image is formed. The resulting spectral space values are then output and may be used by an image output device to reproduce the scanned image.

Claims

1. An apparatus that inverts the spectrum of image data, comprising:

an image data input device that inputs image data of an input image in an input color space;

a medium identification device that identifies an input image medium from which the input image data was obtained; and

a spectrum inversion device that selects one of a plurality of spectrum inversion methods to convert the input image data into output image data in a spectral space based on the identification of the input image medium, the spectrum inversion device including a neural network, wherein the neural network includes input nodes, hidden nodes and output nodes, connections between the input nodes and the hidden nodes are represented by a 3×

10 matrix, connections between the hidden nodes and the output nodes are represented by a 10×

36 matrix, entries of the 3×

10 matrix and the 10×

36 matrix are determined to minimize a merit function, the merit function is a weighted root-mean-square (RMS) spectral error defined as;

$\sum <br><br>\underset{i=1}{\overset{36}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>w<br><br>\left(\mathrm{\lambda <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>i\right)*{\left(R_{\mathrm{desired}}<br><br>\left(\mathrm{\lambda <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>i\right)-R_{\mathrm{output}}<br><br>\left(\mathrm{\lambda <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>i\right)\right)}^2$

 

where λ

i, i=1, 2, . . . , 36 are sampling wavelengths, R_desired (λ

i) and R_output (λ

i) are the spectral reflectance of desired output and actual output, and w(λ

i) is a weight factor.

2. The apparatus of claim 1, wherein the image data input device includes at least one of a scanning device, a photocopying device, a digital camera and a node of a distributed network.

3. The apparatus of claim 1, wherein the medium identification device includes at least one of a switch and a user interface.

4. The apparatus of claim 1, wherein the medium identification device outputs to the spectrum inversion device a medium identifier that identifies the input image medium.

5. The apparatus of claim 4, wherein the medium identifier is a hierarchical identifier representing categories and sub-categories of the identified input image medium.

6. The apparatus of claim 5, wherein the medium identifier further includes sub-categories representing effects that are to be applied to the input image data.

7. The apparatus of claim 5, wherein the medium identifier further includes calibration data identification.

8. The apparatus of claim 1, wherein the spectrum inversion device selects a spectrum inversion method from a plurality of spectrum inversion methods based on the identification of the input image medium.

9. The apparatus of claim 8, wherein the spectrum inversion method includes at least one of a look-up table, a set of rules for an expert system, a set of weights for a neural network, a program, and a series of programs.

19. The apparatus of claim 1, wherein the spectrum inversion device selects a spectrum inversion method from a plurality of spectrum inversion methods based on the identification of the input image medium.

21. The apparatus of claim 1, wherein the input image data contains a 3-dimensional input color space, and the output image data contains a 36-dimensional spectral space.

10. A method for inverting the spectrum of image data, comprising:

inputting image data of an input image, the image data being in an input color space;

identifying an input image medium from which the image data was obtained;

selecting one of a plurality of spectrum inversion methods based on the identification of the input image medium; and

converting the input image data into output image data using a neural network, the output image data being in a spectral space, wherein the neural network includes input nodes, hidden nodes and output nodes, connections between the input nodes and the hidden nodes are represented by a 3×

10 matrix, connections between the hidden nodes and the output nodes are represented by a 10×

36 matrix, entries of the 3×

10 matrix and the 10×

36 matrix are determined to minimize a merit function, the merit function is a weighted root-mean-square (RMS) spectral error defined as;

$\sum <br><br>\underset{i=1}{\overset{36}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>w<br><br>\left(\mathrm{\lambda <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>i\right)*{\left(R_{\mathrm{desired}}<br><br>\left(\mathrm{\lambda <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>i\right)-R_{\mathrm{output}}<br><br>\left(\mathrm{\lambda <br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>i\right)\right)}^2$

 

where λ

i, i=1, 2, . . . , 36 are sampling wavelengths, R_desired (λ

i) and R_output (λ

i) are the spectral reflectance of desired output and actual output, and w(λ

i) is a weight factor.

11. The method of claim 10, wherein the input image data are input from at least one of a scanning device, a photocopying device, a digital camera, and a node of a distributed network.

12. The method of claim 10, wherein identifying the input image medium includes at least one of the setting a switch to a particular input image medium setting and selecting an input image medium using a user interface.

13. The method of claim 10, wherein identifying an input image medium includes determining a medium identifier that identifies the input image medium.

14. The method of claim 13, wherein the medium identifier is a hierarchical identifier representing categories and sub-categories of medium.

15. The method of claim 14, wherein the medium identifier further includes sub-categories representing effects that are to be applied to the input image data.

16. The method of claim 14, wherein the medium identifier further includes calibration data identification.

17. The method of claim 10, wherein converting the input image data into output image data includes selecting a spectrum inversion method from a plurality of spectrum inversion methods based on the identification of the input image medium.

18. The method of claim 17, wherein the spectrum inversion method includes at least one of a look-up table, a set of rules for an expert system, a set of weights for a neural network, a program, and a series of programs.

20. The method of claim 10, further comprising:

selecting a spectrum inversion method from a plurality of inversion methods based on the identification of the input image medium.