IMAGE AND WEBSITE FILTER USING IMAGE COMPARISON

• US 20100034470A1
• Filed: 08/04/2009
• Published: 02/11/2010
• Est. Priority Date: 08/06/2008
• Status: Active Grant

• Current Assignee: Obschestvo S Ogranichennoi Otvetstvennostiu "Kuznetch", Obschestvo S Ogranichennoi Otvetstvennostiu "Kuznetch\
• Original Assignee: Obschestvo S Ogranichennoi Otvetstvennostiu "Kuznetch"
• Inventors: Valencia-Campo, Alexander, Makalkin, Mikhail
• Granted Patent: US 8,718,383 B2
• Time in Patent Office: Days
• US Class Current: 382/218
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 18/2111 by using evolutionary computational techniques, e.g. genetic algorithms

Abstract

Registration and classification of non-textual information, such as digital images and video is described. Image searching and comparison of the images is also described. The digital images are indexed (i.e., each image is assigned a unique numerical parameter and/or a plurality of numerical parameters). The resulting index files are stored in a database that can be quickly searched because the index files are universal numerical files that are significantly smaller in size than their source images. Image search queries are also indexed to generate an index file, which is then compared with the stored index files. A similarity score is also calculated to rank the similar images based on the index file-to-index file comparison.

Claims

1. A computer implemented method, comprising:

providing an index of image index files representative of digital images;

scanning a webpage for a digital image;

calculating an image index file for the digital image from the webpage;

comparing the image index file for the digital image from the webpage with the image index files stored in the index; and

determining to filter the digital image based on the comparison.

2. The computer-implemented method of claim 1 wherein determining to filter comprises determining to block access to the digital image.

3. The computer-implemented method of claim 1 wherein comparing comprises generating a similarity score.

4. The computer-implemented method of claim 3 wherein determining to block access comprises determining whether the similarity score is greater than a threshold similarity score.

5. The computer-implemented method of claim 1 wherein the digital image is a pornographic image.

6. The computer-implemented method of claim 1 wherein the digital image is a trademarked image.

7. The computer-implemented method of claim 1 wherein the index of image descriptors comprises a plurality of clusters, each cluster having a plurality of image descriptors representative of digital images.

8. The computer-implemented method of claim 7 wherein one of the plurality of clusters is a pornographic cluster.

9. The computer-implemented method of claim 7 wherein one of the plurality of clusters is a trademark cluster.

10. The computer-implemented method of claim 1 wherein the index further comprises a monosemantic descriptor for each image index file and further comprising calculating a monosemantic descriptor for the digital image and comparing the monosemantic descriptor for the digital image with the monosemantic descriptor for each image index file before comparing the image index files.

11. The computer-implemented method of claim 10 wherein calculating the monosemantic descriptor comprises:

dividing the digital image into a plurality of cells;

calculating an image descriptor for each of the plurality of cells; and

aligning the image descriptor for each of the plurality of cells to calculate the monosemantic descriptor.

12. The computer-implemented method of claim 1 wherein the image index file comprises a plurality of metrics.

13. The computer-implemented method of claim 12 wherein the plurality of metrics are clustered according to a color palette of the digital image, changes in image composition of the digital image and generic representation of the digital image.

14. The computer-implemented method of claim 12 wherein the plurality of metrics comprise color metrics, texture metrics, intensity metrics and morphology metrics.

15. The computer-implemented method of claim 12 wherein the plurality of metrics comprise a 2D color histogram and a 4D color vector field.

16. A computer-implemented method comprising:

locating a digital image having filterable content;

calculating an image index file for the digital image; and

indexing the image index file.

17. The computer-implemented method of claim 16 wherein the digital image having filterable content is a pornographic image.

18. The computer-implemented method of claim 16 wherein locating the digital image having filterable content comprises analyzing the metadata of the digital image.

19. The computer-implemented method of claim 16 wherein locating the digital image having filterable content comprises determining the website on which the digital image is located is a filterable website.

20. The computer-implemented method of claim 16 further comprising calculating a monosemantic descriptor for the digital image and indexing the monosemantic descriptor with the index image file.

21. The computer-implemented method of claim 16 wherein the image index file comprises a plurality of image metrics.

22. A computer system comprising:

a data store comprising a plurality of image index files representative of digital images;

a search engine configured to receive an image query, the image query being a digital image; and

an analyzer to calculate an image index file for the image query, compare the image index file for the image query with the plurality of image index files and determine to filter the image query based on the comparison.

23. The computer system of claim 22 wherein the plurality of image index files are representative of pornographic digital images.

24. The computer system of claim 22 wherein the plurality of image index files are representative of trademarked digital images.

25. The computer system of claim 22 wherein the image query comprises a request by a user to access a webpage having the digital image.

26. The computer system of claim 25 wherein the analyzer is configured to determine to block access to the web page based on the comparison.

27. The computer system of claim 22 wherein the data store further comprises a monosemantic descriptor for each of the digital images and wherein the analyzer is configured to calculate a monosemantic descriptor for the image query and compare the monosemantic descriptor for each of the digital images with the monosemantic descriptor for the image query before comparing the image index files.