Methods and apparatus for multigeneration color image processing

Claim 2

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; and (d) remapping the color of each pixel of the image stored in the memory to the target color selected for the set including the pixel.

Claim 3

The method of claim 1, wherein the grouping step (a) comprises: (e) generating a color space histogram corresponding to the color composition of the multi-pixel image, locating local maxima of the color space histogram, and identifying points in the color space histogram that are minima located between the maxima of the color space histogram; and (f) for each set of colors, selecting as the colors of the set those colors of the multi-pixel image corresponding to the points in the color space histogram that surround a local maximum.

Claim 4

The method of claim 1, wherein the determining step (b) comprises: (e) determining the number of pixels of the multi-pixel image associated with each set of colors, each pixel having a numerical color value representing a color of the multi-pixel image; (f) adding all of the color values of the pixels associated with each set of colors to determine a color value sum for each set of colors; and (g) dividing the color value sum of each set of colors by the number of pixels associated with the set to determine an average color value for each set, the average color value of the set representing the average color of the set.

Claim 5

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color for each set of colors from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (d) determining, for each set, a difference in color between the average color of the set and the target color selected for the set; (e) remapping the color of each pixel of the image stored in the memory that has the average color of the set which includes the pixel to the target color selected for the set; and (f) remapping the color of each pixel of the image stored in the memory that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 6

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color for each set of colors from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (d) determining, for each set, a difference in color between the average color of the set and the target color selected for the set; (e) remapping the color of each pixel of the image stored in the memory that has the average color of the set which includes the pixel to the target color selected for the set; and (f) remapping the color of each pixel of the image stored in the memory that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 7

The method of claim 4, wherein the grouping step (a) comprises: (g) generating a color space histogram corresponding to the color composition of the multi-pixel image, locating local maxima of the color space histogram, and identifying points in the color space histogram that are minima located between the maxima of the color space histogram; and (h) for each set of colors, selecting as the colors of the set those colors of the multi-pixel image corresponding to the points in the color space histogram that surround a local maximum.

Claim 8

The method of claim 4, wherein the determining step (b) comprises: (g) determining the number of pixels of the multi-pixel image associated with each set of colors, each pixel having a numerical color value representing a color of the multi-pixel image; (h) adding all of the color values of the pixels associated with each set of colors to determine a color value sum for each set of colors; and (i) dividing the color value sum of each set of colors by the number of pixels associated with the set to determine an average color value for each set, the average color value of the set representing the average color of the set.

Claim 9

The method of claim 4, wherein the remapping step (f) is performed by interpolating between the color difference between the average color of the set and the target color selected for the set, and the color differences for other ones of the sets of colors.

Claim 10

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping portions of a multi-pixel image stored in the memory and having a color composition into boundary portions, located between different colored patches of the image, and non-boundary portions; (b) grouping colors of the image into sets of colors, the sets of colors including colors from the boundary portions and the non-boundary portions of the image; (c) determining the average color of each set of colors; (d) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (e) remapping the color of each non-boundary portion pixel of the image stored in the memory to the target color selected for the set which includes that non-boundary portion pixel; (f) remapping the color of each of certain ones of the boundary portion pixels of the image stored in the memory to the target color selected for the set which includes that boundary portion pixel.

Claim 11

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping portions of a multi-pixel image stored in the memory and having a color composition into boundary portions, located between different colored patches of the image, and non-boundary portions; (b) grouping colors of the image into sets of colors, the sets of colors including colors from the boundary portions and the non-boundary portions of the image; (c) determining the average color of each set of colors; (d) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (e) remapping the color of each non-boundary portion pixel of the image stored in the memory to the target color selected for the set which includes that non-boundary portion pixel; (f) remapping the color of each of certain ones of the boundary portion pixels of the image stored in the memory to the target color selected for the set which includes that boundary portion pixel.

Claim 12

The method of claim 8, wherein the remapping step (f) comprises the steps of: (g) remapping the color of each pixel in the boundary portion of the image stored in the memory that has the average color of the set which includes the pixel to the target color selected for the set; and (h) remapping the color of each pixel in the boundary portion of the image stored in the memory that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 13

The method of claim 8, wherein the grouping step (b) comprises: (g) generating a color space histogram corresponding to the color composition of the multi-pixel image, locating local maxima of the color space histogram, and identifying points in the color space histogram that are minima located between the maxima of the color space histogram; and (h) for each set of colors, selecting as the colors of the set those colors of the multi-pixel image corresponding to the points in the color space histogram that surround a local maximum.

Claim 14

The method of claim 8, wherein the determining step (c) comprises: (g) determining the number of pixels of the multi-pixel image associated with each set of colors, each pixel having a numerical color value representing a color of the multi-pixel image; (h) adding all of the color values of the pixels associated with each set of colors to determine a color value sum for each set of colors; and (i) dividing the color value sum of each set of colors by the number of pixels associated with the set to determine an average color value for each set, the average color value of the set representing the average color of the set.

Claim 15

The method of claim 9, wherein the remapping step (h) is performed by interpolating between the color difference between the average color of the set and the target color selected for the set, and the color differences for other ones of the sets of colors.

Claim 16

An image processing apparatus, in a data processing system having a memory, comprising: means for grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; means for determining the average color of each set of colors; means for selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; and means for remapping the color of each pixel of the image stored in the memory to the target color selected by the selecting means for the set including the pixel.

Claim 17

An image processing apparatus, in a data processing system having a memory, comprising: means for grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; means for determining the average color of each set of colors; means for selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; and means for remapping the color of each pixel of the image stored in the memory to the target color selected by the selecting means for the set including the pixel.

Claim 18

The apparatus of claim 13, wherein the grouping means comprises: means for generating a color space histogram corresponding to the color composition of the multi-pixel image, locating local maxima of the color space histogram, and identifying points in the color space histogram that are minima located between the maxima of the color space histogram; and means for selecting as the colors of each set those colors of the multi-pixel image corresponding to the points in the color space histogram that surround a local maximum.

Claim 19

The apparatus of claim 13, wherein the determining means comprises: means for determining the number of pixels of the multi-pixel image associated with each set of colors, each pixel having a numerical color value representing a color of the multi-pixel image; means for adding all of the color values of the pixels associated with each set of colors to determine a color value sum for each set of colors; and means for dividing the color value sum of each set of colors by the number of pixels associated with the set to determine an average color value for each set, the average color value of the set representing the average color of the set.

Claim 20

An image processing apparatus, in a data processing system having a memory, comprising: means for grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; means for determining the average color of each set of colors; means for selecting a target color for each set of colors from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; means for determining, for each set, a difference in color between the average color of the set and the target color selected for the set; means for remapping the color of each pixel of the image stored in the memory that has the average color of the set which includes the pixel to the target color selected for the set; and means for remapping the color of each pixel of the image stored in the memory that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 21

An image processing apparatus, in a data processing system having a memory, comprising: means for grouping colors of a multi-pixel image stored in the memory and having a color composition into sets of colors; means for determining the average color of each set of colors; means for selecting a target color for each set of colors from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; means for determining, for each set, a difference in color between the average color of the set and the target color selected for the set; means for remapping the color of each pixel of the image stored in the memory that has the average color of the set which includes the pixel to the target color selected for the set; and means for remapping the color of each pixel of the image stored in the memory that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 22

The apparatus of claim 16, wherein the grouping means comprises: means for generating a color space histogram corresponding to the color composition of the multi-pixel image, locating local maxima of the color space histogram, and identifying points in the color space histogram that are minima located between the maxima of the color space histogram; and means for selecting as the colors of each set those colors of the multi-pixel image corresponding to the points in the color space histogram that surround a local maximum.

Claim 23

The apparatus of claim 16, wherein the average color determining means comprises: means for determining the number of pixels of the multi-pixel image associated with each set of colors, each pixel having a numerical color value representing a color of the multi-pixel image; means for adding all of the color values of the pixels associated with each set of colors to determine a color value sum for each set of colors; and means for dividing the color value sum of each set of colors by the number of pixels associated with the set to determine an average color value for each set, the average color value of the set representing the average color of the set.

Claim 24

The apparatus of claim 16, wherein the color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors, is determined by interpolating between the color difference between the average color of the set and the target color selected for the set, and the color differences for other ones of the sets of colors.

Claim 25

An image processing apparatus, in a data processing system having a memory, comprising: means for grouping portions of a multi-pixel image stored in the memory and having a color composition into boundary portions, located between different colored patches of the image, and non-boundary portions; means for grouping colors of the image into sets of colors, the sets of colors including colors from the boundary portions and the non-boundary portions of the image; means for determining the average color of each set of colors; means for selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; first means for remapping the color of each non-boundary portion pixel of the image stored in the memory to the target color selected for the set which includes the non-boundary portion pixel; and second means for remapping the color of each of certain ones of the boundary portion pixels of the image stored in the memory to the target color selected for the set which includes the boundary portion pixel.

Claim 26

An image processing apparatus, in a data processing system having a memory, comprising: means for grouping portions of a multi-pixel image stored in the memory and having a color composition into boundary portions, located between different colored patches of the image, and non-boundary portions; means for grouping colors of the image into sets of colors, the sets of colors including colors from the boundary portions and the non-boundary portions of the image; means for determining the average color of each set of colors; means for selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; first means for remapping the color of each non-boundary portion pixel of the image stored in the memory to the target color selected for the set which includes the non-boundary portion pixel; and second means for remapping the color of each of certain ones of the boundary portion pixels of the image stored in the memory to the target color selected for the set which includes the boundary portion pixel.

Claim 27

The apparatus of claim 20, wherein the second remapping means comprises: means for remapping the color of each pixel in the boundary portion of the image stored in the memory that has the average color of the set which includes the pixel to the target color selected for the set; and means for remapping the color of each pixel in the boundary portion of the image stored in the memory that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 28

The apparatus of claim 20, wherein the color grouping means comprises: means for generating a color space histogram corresponding to the color composition of the multi-pixel image, locating local maxima of the color space histogram, and identifying points in the color space histogram that are minima located between the maxima of the color space histogram; and means for selecting as the colors of each set those colors of the multi-pixel image corresponding to the points in the color space histogram that surround a local maximum.

Claim 29

The apparatus of claim 20, wherein the average color determining means comprises: means for determining the number of pixels of the multi-pixel image associated with each set of colors, each pixel having a numerical color value representing a color of the multi-pixel image; means for adding all of the color values of the pixels associated with each set of colors to determine a color value sum for each set of colors; means for dividing the color value sum of each set of colors by the number of pixels associated with the set to determine an average color value for each set, the average color value of the set representing the average color of the set.

Claim 30

The apparatus of claim 21, wherein the color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors, is determined by interpolating between the color difference between the average color of the set and the target color selected for the set, and the color differences for other ones of the sets of colors.

Claim 31

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; and (d) remapping the color of each pixel of the image to the target color selected for the set including the pixel.

Claim 32

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; and (d) remapping the color of each pixel of the image to the target color selected for the set including the pixel.

Claim 33

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color for each set of colors from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (d) determining, for each set, a difference in color between the average color of the set and the target color selected for the set; (e) remapping the color of each pixel of the image that has the average color of the set which includes the pixel to the target color selected for the set; and (f) remapping the color of each pixel of the image that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 34

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping colors of a multi-pixel image having a color composition into sets of colors; (b) determining the average color of each set of colors; (c) selecting a target color for each set of colors from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (d) determining, for each set, a difference in color between the average color of the set and the target color selected for the set; (e) remapping the color of each pixel of the image that has the average color of the set which includes the pixel to the target color selected for the set; and (f) remapping the color of each pixel of the image that has a color of the set which includes the pixel other than the average color of the set to a color determined in accordance with the color difference between the average color of the set and the target color selected for the set, and in accordance with the color differences for other ones of the sets of colors.

Claim 35

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping portions of a multi-pixel image having a color composition into boundary portions, located between different colored patches of the image, and non-boundary portions; (b) grouping colors of the image into sets of colors, the sets of colors including colors from the boundary portions and the non-boundary portions of the image; (c) determining the average color of each set of colors; (d) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (e) remapping the color of each non-boundary portion pixel of the image to the target color selected for the set which includes the non-boundary portion pixel; and (f) remapping the color of each of certain ones of the boundary portion pixels of the image to the target color selected for the set which includes that boundary portion pixel.

Claim 36

An image processing method, the method performed by a data processing system having a memory, and comprising the steps of: (a) grouping portions of a multi-pixel image having a color composition into boundary portions, located between different colored patches of the image, and non-boundary portions; (b) grouping colors of the image into sets of colors, the sets of colors including colors from the boundary portions and the non-boundary portions of the image; (c) determining the average color of each set of colors; (d) selecting a target color, for each set of colors, from a plurality of predetermined target colors, the selected target color being the predetermined target color that is closest to the average color of the set; (e) remapping the color of each non-boundary portion pixel of the image to the target color selected for the set which includes the non-boundary portion pixel; and (f) remapping the color of each of certain ones of the boundary portion pixels of the image to the target color selected for the set which includes that boundary portion pixel.