Method for image modification

• US 8,391,601 B2
• Filed: 04/30/2009
• Issued: 03/05/2013
• Est. Priority Date: 04/30/2009
• Status: Active Grant

• Current Assignee: Innovation Asset Collective
• Original Assignee: Tandent Vision Science, Inc.
• Inventors: Friedhoff, Richard Mark, Smith, Casey Arthur, Maxwell, Bruce Allen, Alldrin, Neil, Bushell, Steven Joseph, Rodgers, Timothy King Jr.
• Primary Examiner(s): Zarka, David
• Assistant Examiner(s): Thomas, Mia M
• Application Number:
  US12/387,258
• Publication Number:
  US 20100278448A1
• Time in Patent Office: 1,405 Days
• Field of Search: 382/164, 382/165, 382/173, 382/199, 382/203, 382/224, 382/258, 382/260, 382/266, 382/274, 382/282, 348/148
• US Class Current: 382/173
• CPC Class Codes: G06T 2207/20012 Locally adaptive
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/90 Dynamic range modification of images or parts thereof
• CPC Class Codes: G06T 7/187 involving region growing; involving region merging; involving connected component labelling

Abstract

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, in a computer memory, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsic images according to a set of preselected operations and merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

Claims

1. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting an image, in a computer memory;

performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, wherein the step of performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image is carried out according to a spatio-spectral operator/constraint/solver model, and wherein each one of the set of intrinsic images comprises a representation of one of material or illumination, expressed as a separate, multi-band representation for the one of material or illumination, independent of the other of the material or illumination, wherein each band corresponds to a segment of the electro-magnetic spectrum;

modifying a preselected one of the set of intrinsic images according to a set of preselected operations, wherein the set of preselected operations includes one of an intensity adjustment, a color change, shadow manipulation, geometric editing, cut and paste editing and combinations thereof; and

merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

2. The method of claim 1 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying the illumination image.

3. The method of claim 1 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying the material image.

4. The method of claim 1 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying both the material image and the illumination image, separately, for an overall modification of the image.

5. The method of claim 4 wherein the step of modifying both the material image and the illumination image, separately, for an overall modification of the image is carried out to perform a geometric editing of the image.

6. The method of claim 4 wherein the step of modifying both the material image and the illumination image, separately, for an overall modification of the image is carried out by modifying the material image and the illumination image in a preselected order.

7. The method of claim 1 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying the illumination image in a dynamic range compression.

8. The method of claim 7 wherein the dynamic range compression is a gamma correction.

9. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting an image, in a computer memory;

utilizing a spatio-spectral operator/constraint/solver model to perform an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, wherein each one of the set of intrinsic images comprises a representation of one of material or illumination, expressed as a separate, multi-band representation for the one of material or illumination, independent of the other of the material or illumination, wherein each band corresponds to a segment of the electro-magnetic spectrum;

modifying a preselected one of the set of intrinsic images; and

merging the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

10. The method of claim 9 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying the illumination image.

11. The method of claim 9 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying the material image.

12. The method of claim 9 wherein the step of modifying a preselected one of the set of intrinsic images is carried out by modifying both the material image and the illumination image, separately, for an overall modification of the image.

13. The method of claim 12 wherein the step of modifying both the material image and the illumination image, separately, for an overall modification of the image is carried out by modifying the material image and the illumination image in a preselected order.

14. A computer system which comprises:

a CPU; and

a memory storing an image file containing an image;

the CPU arranged and configured to execute a routine to perform an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, wherein the step to perform an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image is carried out according to a spatio-spectral operator/constraint/solver model, and wherein each one of the set of intrinsic images comprises a representation of one of material or illumination, expressed as a separate, multi-band representation for the one of material or illumination, independent of the other of the material or illumination, wherein each band corresponds to a segment of the electro-magnetic spectrum, to modify a preselected one of the set of intrinsic images according to a set of preselected operations, wherein the set of preselected operations includes one of an intensity adjustment, a color change, shadow manipulation, geometric editing, cut and paste editing and combinations thereof and to merge the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

15. A computer system which comprises:

a CPU; and

a memory storing an image file containing an image;

the CPU arranged and configured to execute a routine to utilize a spatio-spectral operator/constraint/solver model to perform an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, wherein each one of the set of intrinsic images comprises a representation of one of material or illumination, expressed as a separate, multi-band representation for the one of material or illumination, independent of the other of the material or illumination, wherein each band corresponds to a segment of the electro-magnetic spectrum, modify a preselected one of the set of intrinsic images, and merge the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.

16. 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, in a computer memory, utilize a spatio-spectral operator/constraint/solver model to perform an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, wherein each one of the set of intrinsic images comprises a representation of one of material or illumination, expressed as a separate, multi-band representation for the one of material or illumination, independent of the other of the material or illumination, wherein each band corresponds to a segment of the electro-magnetic spectrum, modify a preselected one of the set of intrinsic images, and merge the modified one of the set of intrinsic images relative to the set of intrinsic images to provide a modified output image.