Method and apparatus for simplifying electro-optical imaging systems

1. A method of simplifying spectral/temporal data, the method comprising:

receiving spectral/temporal data;

formulating the spectral/temporal data into a vector/matrix;

performing a feature extraction analysis;

determining at least two largest principal components from the feature extraction analysis;

creating a cluster diagram from the at least two largest principal components;

evaluating a distance metric from the cluster diagram; and

selecting a largest metric based on the distance metric.

2. The method of claim 1 , further comprising:

repeating the formulating, performing, determining, creating, and evaluating steps for additional spectral/temporal data.

3. The method of claim 2 , wherein the spectral/temporal data include a plurality of wavelengths, and wherein formulating spectral/temporal data into a vector/matrix comprises:

selecting a first subset of the wavelengths in the plurality of wavelengths;

formulating the selected first subset of wavelengths into a vector/matrix.

4. The method of claim 3 , wherein repeating the formulating, performing, determining, creating, and evaluating steps comprises:

selecting a second subset of the wavelengths in the plurality of wavelengths;

repeating the formulating, performing, determining, creating, and evaluating steps for the selected second subset of wavelengths.

5. The method of claim 4 , wherein the first and second subsets of wavelengths each include 2 wavelengths.

6. The method of claim 1 , wherein the feature extraction analysis may be selected from a group consisting of independent component analysis, nonlinear prime component analysis, support vector decomposition analysis, principal component analysis, and combinations thereof.

7. The method of claim 1 , wherein the distance metric is a statistical metric.

8. The method of claim 7 , wherein the statistical metric is a standard deviation.

9. The method of claim 1 , wherein the spectral/temporal data is electro-optical imaging data.

10. An apparatus comprising:

a memory;

a processor; and

a program code resident in the memory and configured to be executed by the processor for simplifying electro-optical imaging data, the program code further configured to receive spectral/temporal data, formulate the spectral/temporal data into a vector/matrix, perform a feature extraction analysis, determine at least two largest principal components from the feature extraction analysis, create a cluster diagram from the at least two largest principal components, evaluate a distance metric from the cluster diagram, and select a largest metric based on the distance metric.

11. The apparatus of claim 10 , wherein the program code is further configured to:

repeat the formulating, performing, determining, creating, and evaluating steps for additional spectral/temporal data.

12. The apparatus of claim 11 , wherein the spectral/temporal data include a plurality of wavelengths, and wherein the program code is further configured to formulate spectral/temporal data into a vector/matrix by:

selecting a first subset of the wavelengths in the plurality of wavelengths;

formulating the selected first subset of wavelengths into a vector/matrix.

13. The apparatus of claim 12 , wherein the program code is further configured to repeat the formulating, performing, determining, creating, and evaluating steps by:

selecting a second subset of the wavelengths in the plurality of wavelengths;

repeating the formulating, performing, determining, creating, and evaluating steps for the selected second subset of wavelengths.

14. The apparatus of claim 13 , wherein the first and second subsets of wavelengths each include 2 wavelengths.

15. The apparatus of claim 10 , wherein the feature extraction analysis of the program code may be selected from a group consisting of independent component analysis, nonlinear prime component analysis, support vector decomposition analysis, principal component analysis, and combinations thereof.

16. A non-transitory computer recordable type medium storing a program code configured to simplify electro-optical imaging data and further configured, when executed on a hardware implemented processor, to receive spectral/temporal data, formulate the spectral/temporal data into a vector/matrix, perform a feature extraction analysis, determine at least two largest principal components from the feature extraction analysis, create a cluster diagram from the at least two largest principal components, evaluate a distance metric from the cluster diagram, and select a largest metric based on the distance metric.

17. The program code of claim 16 , wherein the program code is further configured to:

repeat the formulating, performing, determining, creating, and evaluating steps for additional spectral/temporal data.

18. The program code of claim 17 , wherein the spectral/temporal data include a plurality of wavelengths, and wherein the program code is further configured to formulate spectral/temporal data into a vector/matrix by:

selecting a first subset of the wavelengths in the plurality of wavelengths;

formulating the selected first subset of wavelengths into a vector/matrix.

19. The program code of claim 18 , wherein the program code is further configured to repeat the formulating, performing, determining, creating, and evaluating steps by:

selecting a second subset of the wavelengths in the plurality of wavelengths;

repeating the formulating, performing, determining, creating, and evaluating steps for the selected second subset of wavelengths.

20. The program code of claim 16 , wherein the feature extraction analysis of the program code may be selected from a group consisting of independent component analysis, nonlinear prime component analysis, support vector decomposition analysis, principal component analysis, and combinations thereof.