Log-chromaticity clustering pipeline for use in an image process
View Patent ↗In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises 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, providing a set of estimates for the orientation of the bi-illuminant chromaticity plane and calculating an orientation for each one of the image locations as a function of the set of estimates for the orientation.
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;
providing a set of estimates for an orientation of the bi-illuminant chromaticity plane;
generating a plurality of normal maps, each normal map providing an indication of at least one orientation, each at least one orientation calculated as a function of the set of estimates for an orientation; and
calculating a set of log-chromaticity cluster maps, each one of the set of log-chromaticity cluster maps being based upon a corresponding one of the plurality of normal maps.
2. The method of claim 1 wherein the image locations comprise pixels.
3. The method of claim 1 wherein the image locations comprise tokens.
4. 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;
providing a set of estimates for an orientation of the bi-illuminant chromaticity plane; and
generating a plurality of normal maps, each normal map providing an indication of at least one orientation, each at least one orientation calculated as a function of the set of estimates for an orientation, wherein the step of generating a plurality of normal maps is carried out by executing a technique based upon at least one of a k-NN algorithm and a system of linear equations representing constraints between values based upon selected ones of the set of estimates for an orientation, relative to selected ones of the plurality of normal maps.
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,
provide a set of estimates for an orientation of the bi-illuminant chromaticity plan,
generate a plurality of normal maps, each normal map providing an indication of at least one orientation, each at least one orientation calculated as a function of the set of estimates for an orientation, and
calculating a set of log-chromaticity cluster maps, each one of the set of log-chromaticity cluster maps being based upon a corresponding one of the plurality of normal maps.
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,
provide a set of estimates for an orientation of the bi-illuminant chromaticity plane,
generate a plurality of normal maps, each normal map providing an indication of at least one orientation, each at least one orientation calculated as a function of the set of estimates for an orientation, and
calculate a set of log-chromaticity cluster maps, each one of the set of log-chromaticity cluster maps being based upon a corresponding one of the plurality of normal maps.
7. The computer program product of claim 6 wherein the image locations comprise pixels.
8. The computer program product of claim 6 wherein the image locations comprise tokens.
9. 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,
provide a set of estimates for an orientation of the bi-illuminant chromaticity plane, and
generate a plurality of normal maps, each normal map providing an indication of at least one orientation, each at least one orientation calculated as a function of the set of estimates for an orientation, wherein the process step to generate a plurality of normal maps is carried out by executing a technique based upon at least one of a k-NN algorithm and a system of linear equations representing constraints between values based upon selected ones of the set of estimates for an orientation, relative to selected ones of the plurality of normal maps.
10. 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,
provide a set of estimates for an orientation of the bi-illuminant chromaticity plane, the set of estimates provided by user input, calculation based upon at least one of a linear token, an x-junction and a Type B token, or combinations thereof, and
generate a plurality of normal maps, each normal map providing an indication of at least one orientation, each at least one orientation calculated as a function of the set of estimates for an orientation; and
calculate a set of log-chromaticity cluster maps, each one of the set of log-chromaticity cluster maps being based upon a corresponding one of the plurality of normal maps.
11. 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,
provide a set of estimates for an orientation of the bi-illuminant chromaticity plane, each one of the set of estimates being based upon one of a set of subsets of the image locations, execute a distance function between each one of the image locations and at least one selected one of the sub-sets of the image locations used to calculate the set of estimates to obtain a distance function result, and
for each one of the image locations, calculate an orientation based upon the set of estimates and the distance function result.
12. The computer program product of claim 11 wherein the distance function is based upon a spatial distance and a spectral distance between each one of the image locations and the at least one selected one of the sub-sets of the image locations.