Providing visualizations of characteristics of an image

Patent metadata

Field	Value
Publication number	US-2016247305-A1
Application number	US-201615046206-A
Country	US
Kind code	A1
Filing date	Feb 17, 2016
Priority date	Feb 20, 2015
Publication date	Aug 25, 2016
Grant date	—

Abstract

The present disclosure is directed toward providing visualization models of image characteristics. The visualization models can allow a user to intuitively understand and optionally edit or match characteristics. For example, one or more embodiments involve generating a visualization model of colors (including their hue and saturation) within a source image. Furthermore, one or more embodiments involve enabling a user to interact with and edit the visualization model of the source image. In one or more embodiments further involve generating a transformation model based on the visualization model of the source image. A target image can be altered in accordance with the transformation model such that characteristics of the source image are matched to the target image.

First claim

What is claimed is:

1 . In a digital medium environment for editing digital images, a method of modifying visual characteristics of digital images comprising:
identifying, by one or more processors, a value of a visual characteristic for each of a plurality of pixels of an input digital image; creating groupings of the pixels of the input digital image that have values of the visual characteristic within a threshold; generating, by the one more processors, a visualization model including a plurality of visualization elements that each represent one of the groupings of the pixels; providing a display of the visualization model; receiving user input applying one or more manipulations to one or more visualization elements in the visualization model; and generating, by the one or more processors, a modified digital image by changing values of the visual characteristic of pixels associated with the one or more visualization elements based on the applied one or more manipulations.

2 . The method as recited in claim 1 , wherein generating the visualization model comprises sizing each visualization element based a number of pixels in the corresponding grouping of pixels.

3 . The method as recited in claim 2 , further comprising removing any visualization elements from the visualization model that have a size below a threshold size limit.

4 . The method as recited in claim 1 , wherein generating a visualization model comprises positioning each of the plurality of visualization elements in the visualization model based on the values of the visual characteristic of the pixels in the corresponding grouping of pixels.

5 . The method as recited in claim 1 , wherein identifying a value of a visual characteristic of pixels of an input digital image comprises identifying a color value for each pixel of the input digital image.

6 . The method as recited in claim 5 , wherein generating a visualization model comprises generating a 3D histogram with axes of red, green, and blue.

7 . The method as recited in claim 6 , further comprising:
determining an average color value of the pixels in each of the groupings of pixels; and positioning each visualization element in the 3D histogram based on the average color value of the pixels in the grouping of pixels represented by the visualization element.

8 . The method as recited in claim 7 , wherein the visualization elements comprise spheres with a color corresponding to the average color value of the pixels in the grouping of pixels represented by the visualization element.

9 . The method as recited in claim 1 , wherein the one or more manipulations comprises a resizing of a visualization element, movement of a visualization element, or a deletion of a visualization element.

10 . The method as recited in claim 1 , further comprising:
determining a distance between a pair of visualization elements is less than a threshold; and based on determining that the distance between the pair of visualization elements is less than the threshold, merging the pair of visualization elements.

11 . The method as recited in claim 1 , wherein creating groupings of the pixels of the input digital image that have similar values to the visual characteristic comprises:
subdividing a color space by a hue angle to create a bucket for each resulting hue angle; and assigning each pixel in the input digital image into one of the buckets based on a color value of the pixel.

12 . In a digital medium environment for editing digital images, a method of modifying visual characteristics of target digital images to match sources digital images comprising:
generating, by the one more processors, a visualization model of a visual characteristic of an input digital image, the visualization model including a plurality of visualization elements that each represent a grouping of pixels having values of the visual characteristic within a threshold; providing a display of the visualization model; receiving user input applying one or more manipulations to one or more visualization elements in the visualization model; generating a transformation model based on the visualization model that reflects the one or more manipulations; and modifying, using the generated transformation model, the visual characteristic of a target digital image to correspond with the visual characteristic of the input digital image.

13 . The method as recited in claim 12 , wherein generating a visualization model of the visual characteristic of the input digital image comprises:
sizing each visualization element based a number of pixels in the grouping of pixels; and positioning each visualization element in the visualization model based on the values of the visual characteristic of the pixels in the grouping of pixels.

14 . The method as recited in claim 12 , further comprising identifying a color value for each pixel of the input digital image.

15 . The method as recited in claim 12 , wherein:
the visual characteristic comprises color and the values are color values; generating a visualization model of the visual characteristic of the input digital image comprises generating a 3D histogram with axes of red, green, and blue; and the visualization elements comprise bubbles.

16 . The method as recited in claim 12 , wherein generating a transformation model based on the visualization model that reflects the one or more manipulations comprises building a look-up table, wherein each point within the look-up table comprises an original color value and an interpolation function.

17 . The method as recited in claim 16 , wherein the interpolation function at each point converts an input value of the visual characteristic to a value of the visual characteristic based on the visualization model.

18 . The method of claim 17 , wherein modifying, using the generated transformation model, the visual characteristic of a target digital image to correspond with the visual characteristic of the input digital image comprises applying an interpolation function from the look-up table to each pixel in the target digital image.

19 . A system for modifying visual characteristics of digital images comprising:
at least one processor; and at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to: extract color values from pixels of an input digital image; form groupings of pixels from the input digital image having similar color values; generate a 3D histogram including a plurality of visualization elements that each represent a grouping of pixels having similar color values; size each visualization element to indicate a dominance of the similar color values in the input digital image; apply one or more manipulations to one or more visualization elements in the 3D histogram based on user input; and generate a modified digital image by changing color values of pixels associated with the one or more visualization elements based on the one or more manipulations.

20 . The system as recited in claim 19 , further comprising instructions that, when executed by the at least one processor, cause the system to:
generate a transformation model based on the 3D histogram that reflects the one or more manipulations by building a look-up table, wherein each point within the look-up table comprises an original color value and an interpolation function that converts an input color to a color value of a visualization element in t

Assignees

• Adobe Systems Inc

Inventors

• Borg Lars
• Palmer Patrick
• Pham Duy Anh
• Gallo Michael

Classifications

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06F3/04845

  for image manipulation, e.g. dragging, rotation, expansion or change of colour · CPC title

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G06F3/048

  Interaction techniques based on graphical user interfaces [GUI] · CPC title

• G06T15/005

  General purpose rendering architectures · CPC title