Automated detection of pornographic images
View Patent ↗A method of detecting pornographic images, wherein a color reference database is prepared in LAB color space defining a plurality of colors representing relevant portions of a human body. A questionable image is selected, and sampled pixels are compared with the color reference database. Areas having a matching pixel are subjected to a texture analysis to determine if the pixel is an isolated color or if other comparable pixels surround it; a condition indicating possible skin. If an area of possible skin is found, the questionable image is classified as objectionable. A further embodiment includes preparation of a questionable image reference shape database defining objectionable shapes. An image with a detected area of possible skin is compared with the shape database, and depending on the results of the shape analysis, a predefined percentage of the images are classified for manual review.
1. A method for detecting a pornographic image comprising:
(a) defining a plurality of color values prepared from selected skin image samples from a plurality of images;
(b) filtering a questionable image, said filtering including
(i) comparing a color of a questionable pixel from a questionable image with said color values;
(ii) performing a texture analysis on an area surrounding said questionable pixel if said color of said questionable pixel matches a color value, wherein said texture analysis determines a variance in color between said questionable pixel and a color of pixels in said area; and
(iii) classifying said pixel as a potential skin pixel if said texture analysis indicates that said area has a skin texture.
2. A method as recited in claim 1 further comprising
(a) preparing a shape prototype database including a plurality of prototype image shapes; and
(b) wherein said filtering further includes
(i) comparing a shape of a questionable image including a said potential skin pixel with a said prototype image shape; and
(ii) classifying said questionable image including said potential skin pixel as an objectionable image if a shape of said questionable image corresponds to a shape of a said prototype image shape.
3. A method as recited in claim 2 wherein said shape prototype database includes a plurality of distinct shape databases wherein each said distinct shape database is for use in detecting a particular shape category.
4. A method as recited in claim 3 wherein a first said distinct shape database is for use in detecting a face.
5. A method as recited in claim 3 wherein a first said distinct shape database is for use in detecting a specified body part.
6. A method as recited in claim 5 wherein said body part is genitalia.
7. A method as recited in claim 5 wherein a second said distinct shape database is for use in detecting an erotic position.
8. A method as recited in claim 1 wherein said color values are stored in a final color prototype database that includes a plurality of distinct color databases, with each said distinct color database for use in detecting a particular color type.
9. A method as recited in claim 8 wherein a first said distinct color database is configured for detecting at least one of plurality of skin colors.
10. A method as recited in claim 1 further comprising blocking said questionable image in real time from being displayed on a display system if said questionable pixel is determined to be a potential skin pixel.
11. A method as recited in claim 10 wherein said filtering is performed on a server, and said filtering is done prior to a display of said image on said display system.
12. A method as recited in claim 10 wherein said filtering is performed on a user computer.
13. A method as recited in claim 12 wherein said classifying includes preparing classification data indicating if a questionable image is determined to contain skin.
14. A method as recited in claim 13 wherein said classification data is sent from said user computer to a server.
15. A method as recited in claim 1 wherein said questionable image is one of a collection of images of digital video.
16. A method as recited in claim 1 wherein said texture analysis includes determining a variance in color in said area surrounding said questionable pixel.
17. A method as recited in claim 1 wherein said texture analysis includes determining a co-occurrence.
18. A method as recited in claim 1 wherein said texture analysis including Gabor filtering.
19. A method as recited in claim 1 wherein said texture analysis including a Fourier Transform based technique.
20. A method as recited in claim 1 wherein each said color prototype is described in a projection of a three dimensional Luminance-Chrominance space into a two dimensional chrominance space.
21. A method as recited in claim 20 wherein each said color prototype is a clusterized group of groups of pixels represented by a center value and a an ellipse defining an area of said clusterized group.
22. A method as recited in claim 21 wherein said clusterized group is prepared using a fuzzy-C-means algorithm.
23. A computer-readable medium containing program instructions for detecting a pornographic image, said program instructions for:
(a) defining a plurality of color values from selected skin image samples from a plurality of images;
(b) filtering a questionable image, said filtering including
(i) comparing a color of a questionable pixel from a questionable image with said color prototype values;
(ii) performing a texture analysis on an area surrounding said questionable pixel if said color of said questionable pixel matches a color of a color value, wherein said texture analysis determines a variance in color between said questionable pixel and a color of pixels in said area; and
(iii) classifying said pixel as a potential skin pixel if said texture analysis indicates that said area has a skin texture.
24. A computer-readable medium as recited in claim 23 further comprising
(a) preparing a shape prototype database including a plurality of prototype image shapes; and
(b) wherein said filtering further includes
(i) comparing a shape of a questionable image including a said potential skin pixel with a said prototype image shape; and
(ii) classifying said questionable image including said potential skin pixel as an objectionable image if a shape of said questionable image corresponds to a shape of a said prototype image shape.
25. A computer-readable medium as recited in claim 24 wherein said shape prototype database includes a plurality of distinct shape databases wherein each said distinct shape database is for use in detecting a particular shape category.
26. A computer-readable medium as recited in claim 25 wherein a first said distinct shape database is for use in detecting a face.
27. A computer-readable medium as recited in claim 25 wherein a first said distinct shape database is for use in detecting a specified body part.
28. A computer-readable medium as recited in claim 27 wherein said body part is genitalia.
29. A computer-readable medium as recited in claim 27 wherein a second said distinct shape database is for use in detecting an erotic position.
30. A computer-readable medium as recited in claim 23 wherein said color values are stored in a color prototype database that includes a plurality of distinct color databases, with each said distinct color database for use in detecting a particular color type.
31. A computer-readable medium as recited in claim 30 wherein a first said distinct color database is configured for detecting at least one of plurality of skin colors.
32. A computer-readable medium as recited in claim 23 further comprising blocking said questionable image in real time from being displayed on a display system if said questionable pixel is determined to be a potential skin pixel.
33. A computer-readable medium as recited in claim 32 wherein said filtering is performed on a server, and said filtering is done prior to a display of said image on said display system.
34. A computer-readable medium as recited in claim 32 wherein said filtering is performed on a user computer.
35. A computer-readable medium as recited in claim 34 wherein said classifying includes preparing classification data indicating if a questionable image is determined to contain skin.
36. A computer-readable medium as recited in claim 35 wherein said classification data is sent from said user computer to a server.
37. A computer-readable medium as recited in claim 23 wherein said questionable image is one of a collection of images of digital video.
38. A computer-readable medium as recited in claim 23 wherein said texture analysis includes determining a variance in color in said area surrounding said questionable pixel.
39. A computer-readable medium as recited in claim 23 wherein said texture analysis includes determining a co-occurrence.
40. A computer-readable medium as recited in claim 23 wherein said texture analysis including Gabor filtering.
41. A computer-readable medium as recited in claim 23 wherein said texture analysis including a Fourier Transform based technique.
42. A computer-readable medium as recited in claim 23 wherein each said color prototype is described in a projection of a three dimensional Luminance-Chrominance space into a two dimensional chrominance space.
43. A computer-readable medium as recited in claim 42 wherein each said color prototype is a clusterized group of groups of pixels represented by a center value and a an ellipse defining an area of said clusterized group.
44. A computer-readable medium as recited in claim 43 wherein said clusterized group is prepared using a fuzzy-C-means algorithm.