Method, apparatus and system for identifying distracting elements in an image
A method of identifying a distracting element in an image (e.g., 1100 ), is disclosed. A visual attention map (e.g., 1120 ) is determined for the image ( 1100 ), the visual attention map ( 1120 ) representing one or more regions of the image, at least one of the regions corresponding to at least a portion of a subject of the image. A salient region map (e.g., 1110 ) is determined for the image ( 1100 ), the salient region map comprising a distribution of visual attraction values defining one or more further regions of the image ( 1100 ), the one or more further regions being categorized as salient. An intersection between the visual attention map ( 1120 ) and the salient region map ( 1110 ) is determined to identify a distracting element in the image ( 1100 ). The distracting element corresponds to at least one of the salient regions.
1. A method of identifying a distracting element in an image, said method comprising:
determining a visual attention map for the image, said visual attention map representing one or more regions of the image, at least one of said regions corresponding to at least a portion of a subject of the image;
determining a salient region map for the image, said salient region map comprising a distribution of visual attraction values defining one or more further regions of the image, said one or more further regions being categorised as salient; and
identifying a distracting element in said image based on the visual attention map and the salient region map, wherein said distracting element corresponds to at least one of the salient regions.
2. The method according to claim 1 , wherein the distracting element is identified by determining an intersection between the visual attention map and the salient region map.
3. The method according to claim 1 , wherein the regions represented by the visual attention map depend on content of the image.
4. The method according to claim 1 , wherein the regions represented by the visual attention map correspond to high-level features of the image.
5. The method according to claim 1 , wherein the regions represented by the visual attention map depend on an intended observer of the image.
6. The method according to claim 1 , wherein an inverse of the visual attention map is intersected with the salient region map to determine the intersection.
7. The method according to claim 1 , wherein the salient region map and the visual attention map are binary.
8. The method according to claim 1 , further comprising performing a connected component analysis on the intersection.
9. The method according to claim 1 , wherein the visual attention map is determined using eye tracking.
10. The method according to claim 1 , wherein the salient region map is determined using eye tracking.
11. An apparatus for identifying a distracting element in an image, said apparatus comprising:
means for determining a visual attention map for the image, said visual attention map representing one or more regions of the image, at least one of said regions corresponding to at least a portion of a subject of the image;
means for determining a salient region map for the image, said salient region map comprising a distribution of visual attraction values defining one or more further regions of the image, said one or more further regions being categorised as salient; and
means for identifying a distracting element in said image based on the visual attention map and the salient region map, wherein said distracting element corresponds to at least one of the salient regions.
12. A system for identifying a distracting element in an image, said system comprising:
a memory for storing data and a computer program;
a processor coupled to said memory for executing said computer program, said computer program comprising instructions for:
determining a visual attention map for the image, said visual attention map representing one or more regions of the image, at least one of said regions corresponding to at least a portion of a subject of the image;
determining a salient region map for the image, said salient region map comprising a distribution of visual attraction values defining one or more further regions of the image, said one or more further regions being categorised as salient; and
identifying a distracting element in said image based on the visual attention map and the salient region map, wherein said distracting element corresponds to at least one of the salient regions.
13. A non-transitory computer readable medium having recorded thereon a computer program for identifying a distracting element in an image, said program comprising:
code for determining a visual attention map for the image, said visual attention map representing one or more regions of the image, at least one of said regions corresponding to at least a portion of a subject of the image;
code for determining a salient region map for the image, said salient region map comprising a distribution of visual attraction values defining one or more further regions of the image, said one or more further regions being categorised as salient; and
code for identifying a distracting element in said image based on the visual attention map and the salient region map, wherein said distracting element corresponds to at least one of the salient regions.