A system and method for superimposing images

• US 5,060,171 A
• Filed: 07/27/1989
• Issued: 10/22/1991
• Est. Priority Date: 07/27/1989
• Status: Expired due to Fees

• Current Assignee: Principal Mutual Life Insurance Company
• Original Assignee: Clearpoint Research Corporation
• Inventors: Wells, ASllen K. A., Steir, Stephen C.
• Primary Examiner(s): Herndon, Heather R.
• Application Number:
  US07/386,581
• Time in Patent Office: 817 Days
• Field of Search: 364/518, 364/521, 364/522, 358/93, 358/903, 340/723, 340/724
• US Class Current: 345/630
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 19/006 Mixed reality object pose determination, tracking or camera calibration for mixed reality G06T7/00

Abstract

An image enhancement system and method includes means for superimposing a second image, such as a hair style image, over portions of a first image, such as an image of a person'"'"'s face. The system or method further automatically marks locations along the boundary between the first and second images and automatically calls a graphic smoothing function in the vaccination of the marked locations, so the boundary between the images is automatically smoothed. Preferably, the smoothing function calculates a new color value for a given pixel in the vicinity of such a marked location in at least two smoothing steps, the first of which calculates the color value for each of a plurality of pixels adjacent to the given pixel by combining color values from pixels which are separated, respectively, from each of those plurality of pixels by a distance of more than one pixel. The second step calculates the new color value for the given pixel by combining the color value of each of the plurality of pixels. When used to superimpose hair styles, the system includes means for defining locations on the hair style image, means for defining locations on the head image, means for superimposing the hair style image on the head image so that the defined locations on the hair style image fit those on the head image; and means for altering the size of the hair style in horizontal and vertical directions without altering the fit of the defined locations on the hair style image to the defined locations on the head image. Preferably, in frontal images, both ears and the center of the hair line are used as the defined locations. In a side view, one ear and the center of the hair line are used as the defined locations.

Claims

1. An image enhancement system including:

means for storing a representation of a first image;

means for creating a superimposed image by superimposing a second image over portions of the representation of the first image;

means for automatically marking a plurality of locations along the boundary in the superimposed image between portions containing part of the first image and portions containing part of the second image;

means for performing a graphic smoothing function, including means for changing the light value associated with a given picture element to be more equivalent to the light value of picture elements in its vicinity; and

means for automatically causing said means for performing a graphic smoothing function to perform said function in the vaccination of each of said marked locations, so as to automatically smooth the boundary between the first and second images in said superimposed image.

2. An image enhancement system as in claim 1 wherein:

said images are composed of an array of picture elements each having a light value;

said marked locations along the boundary in the superimposed image correspond to picture elements; and

when said smoothing function is called in the vicinity of one of said marked locations, it calculates a new light value for a given picture element in the vicinity of said marked location as a function of light values from picture elements which are separated from said given picture element by more than one picture element.

3. An image enhancement system as in claim 2, wherein said means for performing a graphic smoothing function includes a first means for calculating the light value for each of a plurality of picture elements adjacent said given picture element as a function of the light values of picture elements which are separated from each of said plurality of picture elements by more than one picture element, and second means for calculating the new light value for said given picture element as a function of the light value calculated by the first means for each of said plurality of picture elements.

4. An image enhancement system as in claim 1, wherein:

said means for storing a representation of said first image includes means for storing a representation of a person'"'"'s head; and

said means for creating a superimposed image over portions of said first image includes means for creating a superimposed image of a hair style.

5. An image enhancement system including:

means for storing a representation of a first image containing a representation of a human head;

means for storing a hair style image;

means for defining certain locations on said hair style image;

means for defining certain locations on said representation of a human head;

means for superimposing and scaling said hair style image on said image of a human head so that said defined locations on said hair style image fit on said defined locations on said representation of a human head; and

means for altering the size of said hair style in horizontal and vertical directions without altering the fit of said defined locations on said hair style image to said defined locations on said representation of a human head.

6. An image enhancement system as in claim 5, wherein:

said first image includes a frontal representation of a human head;

said hair style image is a frontal image of hair style;

said means for defining certain locations on said representation of a human head include means for marking the location of both ears and the hair line in the center of the forehead on said head; and

said means for defining certain locations on said hair style image include means for marking where both ears and the hair line in the center of the forehead belong on said hair image.

7. An image enhancement system as in claim 5, wherein:

said first image includes a side representation of a human head;

said hair style image is a side image of a hair style;

said means for defining certain locations on said representation of a human head include means for marking the ear and the hair line in the center of the forehead on said head; and

said means for defining certain locations on said hair style image include means for marking where an ear and the hair line in the center of the forehead belong on said hair image.

8. An image enhancement system as in claim 5, wherein said means for altering the size of said hair style in horizontal and vertical directions includes means for altering the relative size of said hair style independently in said horizontal and vertical directions.

9. An image enhancement system including:

means for storing a representation of a first image containing a frontal view of a human head;

means for storing a frontal image of a hair style;

means for defining locations corresponding to both ears and the hair line in the center of the forehead on said hair style image;

means for defining locations corresponding to both said ears and the hair line in the center of the forehead on said frontal view of a human head; and

means for superimposing said hair style image on said image of a human head, including means for translating and scaling the hair style image so that said defined locations on said hair style image fit on said defined locations on said representation of a human head.

10. An image enhancement system including:

means for storing a representation of a first image containing a side view of a human head;

means for storing a corresponding side image of a hair style;

means for defining locations corresponding to one ear and the hair line in the center of the forehead on said hair style image;

means for defining locations corresponding to one ear and the hair line in the center of the forehead on said side view of a human head; and

means for superimposing said hair style image on said image of a human head, including means for translating and scaling the hair style image so that said defined locations on said hair style image fit on said defined locations on said representation of a human head.

11. A method for enhancing an image including the steps of:

storing a representation of a first image;

creating a superimposed image by superimposing a second image over portions of the representation of the first image;

automatically marking a plurality of locations along the boundary in the superimposed image between portions containing part of the first image and portions containing part of the second image;

performing a graphic smoothing function which changes the light value associated with a given picture element to be more equivalent to the light value of picture elements in its vicinity; and

automatically performing said graphic smoothing function in the vicinity of each of said marked locations, so as to automatically smooth the boundary between the first and second images in said superimposed image.

12. A method for enhancing an image as in claim 11, wherein:

said images are composed of an array of picture elements each having a light value;

said marked locations along the boundary in the superimposed image correspond to picture elements; and

when said smoothing function is called in the vicinity of one of said marked locations, it calculates a new light value for a given picture element in the vicinity of said marked location as a function of light values from picture elements which are separated from said given picture element by more than one picture element.

13. A method for enhancing an image as in claim 12, wherein said smoothing function calculates a new light value for given picture element in a process having at least two smoothing steps, the first step calculating the light value for each of a plurality of picture elements adjacent said given picture element as a function of the light values of picture elements which are separated from each of said plurality of picture elements by more than one picture element, and the second step calculating the new light value for said given picture element as a function of the light value of each of said plurality of picture elements.

14. A method for enhancing an image in claim 12, wherein:

said storing of a representation of said first image includes storing a representation of a person'"'"'s head; and

said creating of a superimposed image over portions of said first image includes creating a superimposed image of a hair style.

15. A method for enhancing an image including:

storing a representation of a first image containing a representation of a human head;

storing a hair style image;

defining certain locations on said hair style image;

defining certain locations on said representation of a human head;

superimposing and scaling said hair style image on said image of a human head so that said defined locations on said hair style image fit on said defined locations on said representation of a human head; and

altering the size of said hair style in horizontal and vertical directions without altering the fit of said defined locations on said hair style image to said defined locations on said representation of a human head.

16. A method for enhancing an image as in claim 15, wherein:

said first image includes a frontal representation of a human head;

said hair style image is a frontal image of a hair style;

said defining of certain locations on said representation of a human head includes marking the location of both ears and the hair line in the center of the forehead on said head; and

said defining of certain locations on said hair style image includes marking where both ears and the hair line in the center of the forehead belong on said hair image.

17. A method for enhancing an image as in claim 15, wherein:

said first image includes a side representation of a human head;

said hair style image is a side image of a hair style;

said defining of certain locations on said representation of a human head includes marking the one ear and the hair line in the center of the forehead on said head; and

said defining of certain locations on said hair style image includes marking where one ear and the hair line in the center of the forehead belong on said hair image.

18. A method for enhancing an image as in claim 15, wherein said altering of the size of said hair style in horizontal and vertical directions includes altering the relative size of said hair style independently in said horizontal and vertical directions.

19. A method for enhancing an image including:

storing a representation of a first image containing a frontal view of a human head;

storing a frontal image of a hair style;

defining locations corresponding to both ears and the hair line in the center of the forehead on said hair style image;

defining locations corresponding to both said ears and the hair line in the center of the forehead on said frontal view of a human head; and

superimposing said hair style image on said image of a human head, including translating and scaling the hair style image so that said defined locations on said hair style image fit on said defined locations on said representation of a human head.

20. A method for enhancing an image including:

storing a representation of a first image containing a side view of a human head;

storing a corresponding side image of a hair style;

defining locations corresponding to one ear and the hair line in the center of the forehead on said hair style image;

defining locations corresponding to one ear and the hair line in the center of the forehead on said side view of a human head; and

superimposing said hair style image on said image of a human head, including translating and scaling the hair style image so that said defined locations on said hair style image fit on said defined locations on said representation of a human head.