Method and apparatus for image identification and comparison

• US 6,628,824 B1
• Filed: 03/17/1999
• Issued: 09/30/2003
• Est. Priority Date: 03/20/1998
• Status: Expired due to Fees

• Current Assignee: Imagelock, Inc.
• Original Assignee: Imagelock, Inc.
• Inventors: Belanger, Ken
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): SHERALI, ISHRAT I
• Application Number:
  US09/271,112
• Time in Patent Office: 1,658 Days
• Field of Search: 382/162, 382/165, 382/305, 382/209, 382/217-220, 382/124-127, 345/700, 345/723, 707/1-7, 707/104.1, 358/500, 358/512, 358/529
• US Class Current: 382/165
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06T 2201/0201 whereby only tamper or origin are detected and no embedding takes place
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/758 Involving statistics of pixels or of feature values, e.g. histogram matching

Abstract

A method and apparatus are provided for analyzing, identifying, and comparing images. The method can be used with any visually-displayed medium that is represented in any type of color space. An identified image can be authenticated, registered, marked, compared to another image, or recognized using the method and apparatus according to the present invention. At least one characteristic of an image'"'"'s color space is selected and determined to generate a unique description of the image. This identification information is then used to compare different identified images to determine if they are identical according to a set of predetermined criteria. The predetermined criteria can be adjusted to permit the identification of images that are identical in part. In the preferred embodiment of the present invention, a software search application, such as a search engine or a spider, is used to locate and retrieve an image to be identified from an electronic network. A notification alarm is triggered when a duplicate image is located. In one embodiment, the present invention is implemented using a computer. One or more software applications, software modules, firmware, and hardware, or any combination thereof, are used to determine the identification information for the selected image characteristics, search for images, provide notification of identical images, and to generate a database of identified images.

Claims

1. A method for analyzing image information, comprising the steps of:

determining, as characteristics of a first image;

(a) the first image'"'"'s color space usage,

(b) the first image'"'"'s size,

(c) the first image'"'"'s color range distance, and

(d) the first image'"'"'s color distribution; and

using the color distribution and at least one other characteristic of the first image to compare the first image to a second image;

wherein color distribution is defined by dividing color ranges into groups of N elements, wherein N is the total number of desired discrete elements.

3. The method of claim 1, wherein the determination of the image'"'"'s color distribution further comprises the steps of:

defining all possible display ranges for a pixel of a selected color space;

dividing the ranges into groups of N elements, wherein N is the total number of desired discrete finger print elements;

determining the color value for each pixel in the image; and

determining the number of expressed color values in each group of N elements for which there is at least one pixel with a corresponding color value.

4. The method of claim 3, further comprising the step of, for each group of N elements, dividing the number of expressed color values of the group with the total number of color values for all groups.

5. The method of claim 3, further comprising the step of combining a plurality of color values as a single expressed color value.

6. The method of claim 5, wherein the plurality of color values are combined by grouping colors that cannot be visually distinguished.

7. The method of claim 5, wherein, in an RGB color space, the plurality of color values are combined by

truncating a specified number of the lower bits representing one or more component colors of a first color value;

determining the value of the component colors of the first color value after the truncation; and

combining the first color value with any other color values whose color components are equal in value to the value of the component colors of the first color value after the truncation.

8. The method of claim 1, wherein the determination of the image'"'"'s color space usage further comprises the step of for each color range defined in the image'"'"'s color space, counting the number of pixels that use a color element in the color range.

9. The method of claim 8, further comprising the step of, for each specific color range of the color space, dividing the total number of pixels using a color element in the color range by the total number of pixels used in the image to generate the percentage of usage for each specific color range of the color space.

10. The method of claim 1, wherein the determination of the image'"'"'s color space distancing further comprises the steps of:

determining the distance between the two farthest points of the color element for each color element of a color range defined in the image'"'"'s color space; and

averaging the total distances for all color elements in the color range.

11. The method of claim 1, wherein the determination of the image'"'"'s color space sizing further comprises the step of determining the width and height of the image.

12. The method of claim 1, further comprising the step of comparing at least one determined image characteristic of a first image with the determined image characteristic of at least a second image.

13. The method of claim 12, further comprising the step of determining whether the first image is identical to the compared second image.

14. The method of claim 1, wherein the determination of the selected characteristic for a displayed image is computer-implemented.

2. A method for comparing a plurality of images, comprising the steps of:

determining, as characteristics of a first image;

(a) the first image'"'"'s color space usage,

(b) the first image'"'"'s size,

(c) the first image'"'"'s color range distance, and

(d) the first image'"'"'s color distribution; and

using the color distribution and at least one other characteristic of the first image to compare the first image to a second image;

determining the color distribution and the at least one other characteristics for the second image;

comparing the determined characteristics of the first and second displayed images; and

using a set of predefined criteria to determine whether the determined characteristics of the first displayed image match the determined characteristics of the at least a second displayed image.

15. The method of claim 2, wherein the set of predetermined criteria includes the percentage of identical characteristics.