Applying a segmentation engine to different mappings of a digital image

1. An image processing method, comprising:

applying a segmentation engine to different mappings of a digital image;

generating primitives by tessellating non-congruent segments of the different mappings, where the primitives are defined by boundaries of the non-congruent segments in the different mappings; and

classifying the primitives by:

assessing, using a plurality of classifiers, a quality of each non-congruent segment of each mapping; and

assigning a classification to each primitive based upon the assessing;

wherein each of applying, generating and classifying is performed by a processor programmed by machine memory encoded with data.

2. The method of claim 1 , wherein the different mappings address different image issues.

3. The method of claim 1 , wherein at least one mapping is selected according to an image attribute.

4. The method of claim 1 , wherein the different mappings include a first mapping of hue and a second mapping of saturation.

5. The method of claim 1 , wherein classifications are assigned to the non-congruent segments of the different mappings, wherein the classifications of respective non-congruent segments used to define the primitives are compared, and wherein a classification of the respective non-congruent segment having a highest quality is assigned to a corresponding one of the primitives.

6. The method of claim 5 , wherein the quality is based on a confidence level of classifying a segmented mapping.

7. The method of claim 6 , wherein the quality is the confidence level weighted by statistics for the segmented mapping.

8. The method of claim 5 , further comprising assigning emergent classifications to at least one of the primitives.

9. The method of claim 5 , further comprising performing aggregation of the primitives.

10. The method of claim 9 , wherein the aggregation is a function of precision of classification statistics.

11. The method of claim 9 , wherein a zoning engine is applied, via the processor, to the different mappings to perform generation, classification, and aggregation of the primitives.

12. The method of claim 1 , further comprising applying a second segmentation engine to the different mappings of the digital image.

13. A security method, comprising:

performing the method of claim 1 ;

extracting a segment classified as a deterrent; and

authenticating the extracted segment.

14. An image processing method, comprising sending a digital image to an image processing pipeline that includes performing the method of claim 1 .