Method and system for removal of flash artifacts from digital images

Claim 3

The method of claim 1 , wherein said using a database further comprises selecting those pixels having color values for which at least one of the refernce probability distribution function exceeds a prescribed threshold confidence level.

Claim 4

The method of claim 1 wherein the reference probability distribution functions are multi-variate Gaussian distribution functions.

Claim 5

The method of claim 3 wherein the estimated parameters are the means and covariances of the multi-variate Gaussian distribution.

Claim 6

The method of claim 1 wherein said estimating uses statistical estmation based on sample color value data from the flash-corrupted reference image.

Claim 7

The method of claim 1 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels within a region of pixels selected by a user.

Claim 8

The method of claim 6 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels within the region of pixels selected by a user having a color with saturation less than a prescribed saturation threshold.

Claim 9

The method of claim 1 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels having a color with saturation less than a prescribed saturation threshold.

Claim 10

The method of claim 1 wherein pixel color values are expressed as triplets of red, green and blue color channel values, and wherein said modifying comprises adjusting eash triplet of red, green and blue values to a common gray-scale color value.

Claim 11

The method of claim 9 wherein the common gray-scale value is determined by the green and blue color values.

Claim 12

The method of claim 10 wherein the common gray-scale value is the larger of the green and blue color values.

Claim 13

The method of claim 10 wherein the common gray-scale value is the smaller of the green and blue color values.

Claim 14

The method of claim 10 wherein the common gray-scale value is the average of the green and blue color values.

Claim 17

The method of claim 14 wherein said employing said likelihoods further comprises selecting those pixels having color values for which at least one of the reference probability distribution functions exceeds a prescribed threshold confidence level.

Claim 18

The method of claim 14 wherein the reference probability distribution functions are multi-variate Gaussian distribution functions.

Claim 19

The method of claim 16 wherein the estimated parameters are the means and covariances of the multi-variate Gaussian distribution.

Claim 20

The method of claim 14 wherein said estimating uses statistical estimation based on sample color values data from flash-corrupted reference image.

Claim 21

The method of claim 14 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels within a region of pixels selected by a user.

Claim 22

The method of claim 19 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels within the region of pixels selected by a user having a color with saturation less than a prescribed saturation threshold.

Claim 23

The method of claim 14 wherein the group of pixels at which the reference probability distribution functions are evaluated composes pixels having a color with saturation less than a prescribed saturation therehold.

Claim 26

The system of claim 22 wherein said pixel processor further comprises a pixel selector selecting those pixels for which at least one of the reference probability distribution functions exceeds a prescribed threshold confidence level.

Claim 27

The system of claim 22 wherein the reference probability distribution functions are multi-variate Gaussian distribution functions.

Claim 28

The system of claim 24 wherein the estimated parameters are the means and covariances of the multi-variate Gaussian distribution.

Claim 29

The system of claim 22 wherein said statistical processor uses statistical estimation based on sample color value data from the flash-corrupted reference image.

Claim 30

The system of claim 22 wherein the group of pixels at which the reference probability distribution functions are evaluated comprise pixels within a region of pixels selected by a user.

Claim 31

The system of claim 27 wherein the group of pixels at which the reference probability distribution functions are evaluated comprise pixels within the region of pixels selected by a user having a color with saturation less than a prescribed saturation threshold.

Claim 32

The system of claim 22 wherein the group of pixels at which the reference probability distribution functions are evaluated comprise pixels having a color with saturation less than a prescribed saturation threshold.

Claim 33

The system of claim 22 wherein the pixel color values are expressed as triplets of red, green and blue color channel values, and wherein said pixel processor adjusts each triplet of red, green and blue values to a common gray-scale color value.

Claim 34

The system of claim 30 wherein the common gray-scale value is determined by the green and blue color values.

Claim 35

The system of claim 31 wherein the common gray-scale value is the larger of the green and blue color values.

Claim 36

The system of claim 31 wherein the common gray-scale value is the smaller of the green and blue color values.

Claim 37

The system of claim 31 wherein the common gray-scale value is the average of the green and blue color values.

Claim 40

The system of claim 35 wherein said pixel processor further comprises a pixel selector selecting those pixels having color values for which at least one of the reference probability distribution functions exceeds a prescribed threshold confidence level.

Claim 41

The system of claim 35 wherein the reference probability distribution functions are multi-variate Gaussian distribution functions.

Claim 42

The system of claim 37 wherein the estimated parameters are the means and covariances of the multi-variate Gaussian distribution.

Claim 43

The system of claim 35 wherein said statistical processor uses statistical estimation based on sample color value data from the flash-corrupted reference image.

Claim 44

The system of claim 35 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels within region of pixel selected by a user.

Claim 45

The system of claim 40 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels within the region of pixels selected by a user having a color with saturation less than a prescribed saturation threshold.

Claim 46

The system of claim 35 wherein the group of pixels at which the reference probability distribution functions are evaluated comprises pixels having color with saturation less than a prescribed saturation threshold.

Claim 47

A photo kiosk comprising: a touch-sensitive screen; red-eye correction apparatus, comprising: a pixel processor identifying corrupted pixels within the digital image that have been corrupted by a flash, based on a database of reference flash-corrupted images, said pixel processor comprising: a statistical estimating, for each reference flash-corrupted image, parameters of a corresponding reference probability distribution function that characterizes the pixels of the reference flash-corrupted image that are corrupted by a flash; and a computational unit evaluating, for each pixel within group of pixels from the digital image, the refernce probability distribution functions at the color value of the pixel, using the estimated parameter; and a color processor modifying the color values of each corrupted pixel of the digital image, to correct the corrupted pixel color values; and a photo printer unit.

Claim 48

A photo kiosk comprising: a touch-sensitive screen; red-eye correction apparatus, comprising: a pixel processor identifying corrupted pixels within the digital image that have been corrupted by a flash, based on a database of reference flash-corrupted images, said pixel processor comprising: a statistical estimating, for each reference flash-corrupted image, parameters of a corresponding reference probability distribution function that characterizes the pixels of the reference flash-corrupted image that are corrupted by a flash; and a computational unit evaluating, for each pixel within group of pixels from the digital image, the refernce probability distribution functions at the color value of the pixel, using the estimated parameter; and a color processor modifying the color values of each corrupted pixel of the digital image, to correct the corrupted pixel color values; and a photo printer unit.

Claim 49

A photo kiosk comprising: a touch-sensitive screen; red-eye correction apparatus, comprising: a pixel analyzer analyzing pixel color values for a group of pixels in the digital image, to determine a likelihood that each pixel of the group of pixels would be classified as flash-corrupted, based on a database of reference flash-corrupted images, said pixel analyzer comprising: a statistical processor estimating, for each reference flash-corrupted image, parameters of a corrsponding reference probability distribution function that characterizes the pixels of the referecne flash-corruted image that are corrupted by a flash; and a computational unit evaluating, for each pixel within the group of pixels in the digital image, the reference probability distribution functions for the color value of the pixel, using the estimated parameters, to determine a likelihood that the pixel would be classified as flash-corrupted based on the reference flash-corrupted images; and a pixel processor employing the likelihoods for identifying corrupted pixels within the digital image that have been corrupted by a flash; and a photo printer unit.

Claim 50

A photo kiosk comprising: a touch-sensitive screen; red-eye correction apparatus, comprising: a pixel analyzer analyzing pixel color values for a group of pixels in the digital image, to determine a likelihood that each pixel of the group of pixels would be classified as flash-corrupted, based on a database of reference flash-corrupted images, said pixel analyzer comprising: a statistical processor estimating, for each reference flash-corrupted image, parameters of a corrsponding reference probability distribution function that characterizes the pixels of the referecne flash-corruted image that are corrupted by a flash; and a computational unit evaluating, for each pixel within the group of pixels in the digital image, the reference probability distribution functions for the color value of the pixel, using the estimated parameters, to determine a likelihood that the pixel would be classified as flash-corrupted based on the reference flash-corrupted images; and a pixel processor employing the likelihoods for identifying corrupted pixels within the digital image that have been corrupted by a flash; and a photo printer unit.

Claim 51

An article of manufacture inluding one or more computer-readable media that embody a program of instructions for removal of flash arifacts from a digital image containing pixels therin, whrein the program of instruction, when exected by a processing system, causes the processing system to: use a database of reference flash-corrupted imaged for identifying corrupted pixels within the digital image that have been corrupted by a flash; estimate, for each refernce flash-corrupted image, parameters of a corresponding reference probability destibution function that characterizes the pixel of the reference flash-corrupted corrupted image that are corrupted by a flash; evaluate, for each within group of pixels from the digital image, the reference probability distribution functions for the clor value of the pixel, using the estimated parameters; and modify the color values of each corrupted pixel of the digital image, to correct the corrupted pixel color values.

Claim 52

An article of manufacture inluding one or more computer-readable media that embody a program of instructions for removal of flash arifacts from a digital image containing pixels therin, whrein the program of instruction, when exected by a processing system, causes the processing system to: use a database of reference flash-corrupted imaged for identifying corrupted pixels within the digital image that have been corrupted by a flash; estimate, for each refernce flash-corrupted image, parameters of a corresponding reference probability destibution function that characterizes the pixel of the reference flash-corrupted corrupted image that are corrupted by a flash; evaluate, for each within group of pixels from the digital image, the reference probability distribution functions for the clor value of the pixel, using the estimated parameters; and modify the color values of each corrupted pixel of the digital image, to correct the corrupted pixel color values.

Claim 53

The article of claim 45 wherein the one or more computer-readable media include one or more non-volatile storage devices.

Claim 54

The article of claim 45 wherein the one or more computer-readable media include a carrier wave modulated with a data signal.

Claim 55

An article of manufacture including one or more computer-readable media that embody a program of instructions fo detecting flash arifacts in a digial image containing pixels therein, wherein the program of instruction, whern executed by a processing system, causes the processing system to: analyze pixel color values for a group of pixels in the digital image, to determine a likelihood that each pixel of the group of pixels would be classified as flash-corrupted, based on a database of reference flash-corrupted images; estimata, for each refernce flash-corrupted image, parameters of a corresponding reference probability distribution, function that characterizes the pixels of the reference flash-corrupted image that are corrupted by a flash; evaluate, for each pixel within the group of pixels in the digital image, the refernce probability destibution functions for the color value of the pixel, using the estimated parameters, to determine a likelihood that the pixel would be classified as flash-corrupted based on the reference flash-corrupted images; and employ the likelihood for identifying corrupted pixels within the digital image that hve been corrupted by a flash.

Claim 56

An article of manufacture including one or more computer-readable media that embody a program of instructions fo detecting flash arifacts in a digial image containing pixels therein, wherein the program of instruction, whern executed by a processing system, causes the processing system to: analyze pixel color values for a group of pixels in the digital image, to determine a likelihood that each pixel of the group of pixels would be classified as flash-corrupted, based on a database of reference flash-corrupted images; estimata, for each refernce flash-corrupted image, parameters of a corresponding reference probability distribution, function that characterizes the pixels of the reference flash-corrupted image that are corrupted by a flash; evaluate, for each pixel within the group of pixels in the digital image, the refernce probability destibution functions for the color value of the pixel, using the estimated parameters, to determine a likelihood that the pixel would be classified as flash-corrupted based on the reference flash-corrupted images; and employ the likelihood for identifying corrupted pixels within the digital image that hve been corrupted by a flash.