Method for performing a multi-clustering merge for use in an image process

1. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting an image defined by image locations, in a computer memory;

generating a bi-illuminant chromaticity plane in a log color space for representing the image locations of the image in a log-chromaticity representation for the image;

calculating a set of log-chromaticity cluster maps, each based upon at least one estimate for an orientation of the bi-illuminant chromaticity plane selected from a set of estimates and including a cluster for each one of the image locations; and

merging the set of log-chromaticity cluster maps to obtain a single, merged log-chromaticity cluster map.

2. The method of claim 1 wherein the step of merging the set of log-chromaticity cluster maps to obtain a single, merged log-chromaticity cluster map is carried out by calculating a score for each cluster of each log-chromaticity cluster map, each score being indicative of a likelihood a respective cluster includes lit and shadowed pixels of a single material reflectance, and selecting for each one of the image locations, in the single, merged log-chromaticity cluster map, a corresponding cluster with a highest score.

3. The method of claim 1 wherein the image locations comprise pixels.

4. The method of claim 1 wherein the image locations comprise tokens.

5. A computer system which comprises:

a CPU; and

a memory storing an image file containing an image defined by image locations;

the CPU arranged and configured to execute a routine to generate a bi-illuminant chromaticity plane in a log color space for representing the image locations of the image in a log-chromaticity representation for the image, calculate a set of log-chromaticity cluster maps, each based upon at least one estimate for an orientation of the bi-illuminant chromaticity plane selected from a set of estimates and including a cluster for each one of the image locations, and merge the set of log-chromaticity cluster maps to obtain a single, merged log-chromaticity cluster map.

6. A computer program product, disposed on a non-transitory computer readable media, the product including computer executable process steps operable to control a computer to: provide an image file depicting an image defined by image locations, in a computer memory, generate a bi-illuminant chromaticity plane in a log color space for representing the image locations of the image in a log-chromaticity representation for the image, calculate a set of log-chromaticity cluster maps, each based upon at least one estimate for an orientation of the bi-illuminant chromaticity plane selected from a set of estimates and including a cluster for each one of the image locations, and merge the set of log-chromaticity cluster maps to obtain a single, merged log-chromaticity cluster map.

7. The computer program product of claim 6 wherein the process step to merge the set of log-chromaticity cluster maps to obtain a single, merged log-chromaticity cluster map is carried out by calculating a score for each cluster of each log-chromaticity cluster map, each score being indicative of a likelihood a respective cluster includes lit and shadowed pixels of a single material reflectance, and selecting for each one of the image locations, in the single, merged log-chromaticity cluster map, a corresponding cluster with a highest score.

8. The computer program product of claim 6 wherein the image locations comprise pixels.

9. The computer program product of claim 6 wherein the image locations comprise tokens.