Systems and methods for image archaeology

• US 8,849,058 B2
• Filed: 08/23/2010
• Issued: 09/30/2014
• Est. Priority Date: 04/10/2008
• Status: Expired due to Fees

• Current Assignee: Trustees Of Columbia University In The City Of New York (Columbia University)
• Original Assignee: Trustees Of Columbia University In The City Of New York (Columbia University)
• Inventors: Kennedy, Lyndon, Chang, Shih-Fu
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US12/861,377
• Publication Number:
  US 20110025710A1
• Time in Patent Office: 1,499 Days
• Field of Search: 382/286, 382/284, 382/294, 382/305, 382/195, 345/629
• US Class Current: 382/274
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85

Abstract

Systems and methods are described for determining manipulation history among a plurality of images. The described techniques include selecting a pair of images from the plurality of images, detecting one or more manipulations operable to transform one of the images to the other, and based on the manipulations detected, determining a parent-child relationship between the pair or pairs of images. The described techniques can further include repeating the selecting two images, detecting manipulations, and determining the parent-child relationship for each pairs of images in the plurality of images, constructing a visual migration map for the images, and presenting the visual migration map in a user readable format.

Claims

1. A method for determining manipulation history among a plurality of images, comprising:

a) selecting a first image and a second image from the plurality of images;

g) detecting if one or more manipulation are operable to transform the first image to the second image or the second image to the first image;

e) determining an existence of a parent-child relationship between the first image and the second image based on the detection of the one of more manipulations, if any;

g) presenting the determined existence of the parent-child relationship in a user readable format;

e) determining the existence of a parent-child relationship for each pair of images in the plurality of images, and

f) constructing a visual migration map for the plurality of images based on the determined existence of the parent-child relationship for each pair of images in the plurality of images prior to the presenting the determined parent-child relationship, wherein the presenting comprises presenting the visual migration map.

2. The method of claim 1, further comprising obtaining the plurality of images by manual collection.

3. The method of claim 1, further comprising obtaining the plurality of images by web-crawling.

4. The method of claim 1, further comprising obtaining the plurality of images by using an internet search engine.

5. The method of claim 1, further comprising obtaining a subset of images that are edited copies of one image from the plurality of images before selecting the first image and the second image, wherein selecting the first image and the second image is from the subset of images.

6. The method of claim 5, wherein obtaining a subset of images comprises using a copy detection technique, the copy detection technique comprising using a scale invariant feature transform descriptor.

7. The method of claim 1, wherein detecting if the one or more manipulations are operable to transform the first image to the second image or the second image to the first image comprises using one or more detectors selected from the group consisting of one or more context-independent detectors, one or more context-dependent detectors, and a combination thereof.

8. The method of claim 7, wherein the context-independent detectors are selected from the group consisting of a scaling detector, a grayscale detector, and a combination thereof.

9. The method of claim 7, wherein the context-dependent detectors are selected from the group consisting of a cropping detector, an insertion detector, an overlay detector, and a combination thereof.

10. The method of claim 7, wherein detecting if the one or more manipulations are operable to transform the first image to the second image or the second image to the first image further comprises using a copy detector.

11. The method of claim 10, wherein using the one or more context-dependent detectors comprises:

constructing a composite image for each of the first image and the second image;

obtaining a residual image for each of the first image and the second image based on differences between each of the first image and the second image and its corresponding composite image;

using the obtained residue images to determine if the one or more manipulations are operable to transform the first image to the second image or the second image to the first image.

12. The method of claim 1, wherein the parent-child relationship is determined to be non-existent when no manipulations are detected.

13. The method of claim 1, wherein the parent-child relationship between the first image and the second image is determined to exist when only one manipulation is detected operable to transform the first image to the second image, the first image being identified as the parent and the second image being identified as the child.

14. The method of claim 1, wherein the parent-child relationship between the first image and the second image is determined to exist when a plurality of manipulations are detected, and each of the plurality of manipulations is operable to transform the first image to the second image, the first image being identified as the parent and the second image being identified as the child.

15. The method of claim 1, wherein the parent-child relationship between the first image and the second image is determined to be non-existent, when a plurality of manipulations are detected, and wherein at least one of the plurality of manipulations is operable to transform the first image to the second image, and wherein at least another of the plurality of manipulations is operable to transform the second image to the first image.

16. A non-transitory computer-readable medium comprising at least one software component that, when executed, performs a method comprising:

selecting a first image and a second image from a plurality of images;

detecting if one or more manipulations, are operable to transform the first image to the second image or the second image to the first image;

determining an existence of a parent-child relationship between the first image and the second image based on the detection of one of more manipulations, if any;

presenting the determined existence of the parent-child relationship, if any, in a user readable format;

determining the existence of a parent-child relationship for each pair of images in the plurality of images; and

constructing a visual migration map for the plurality of images based on the determined existence of the parent-child relationship for each pair of images in the plurality of images prior to the presenting the determined parent-child relationship, wherein the presenting comprises presenting the visual migration map.

17. A system for determining image manipulation history, comprising:

a) an input device for receiving at least a first image and a second image;

b) one or more processing devices, at least one of which operably coupled with the input device, for detecting if one or more manipulations are operable to transform the first image to the second image or the second image to the first image;

for determining an existence of a parent-child relationship between the first image and the second image based on the detection of the one of more manipulations, if any; and

for constructing a visual migration map based on the detection of the one or more manipulations for each pair of images in the plurality of images; and

c) a display device, operably coupled with one or more of the processing devices, for presenting the visual migration map in a user readable format.