Image converting device and three dimensional image display device including the same
View Patent ↗An image converting device includes; a downscaling unit which downscales a two-dimensional image to generate at least one downscaling image, a feature map generating unit which extracts feature information from the downscaling image to generate a feature map, a visual attention calculating unit which generates a low-level attention map based on a visual attention of the feature map, and an image expansion unit which up-scales the low-level attention map, wherein an increasing gray value may be added to image data disposed on the upper portion in the low-level attention map, and 0 or a decreasing gray value may be added to the image data disposed on the lower portion.
1. An image converting device comprising:
a downscaling unit which downscales a two-dimensional image to generate at least one downscaling image;
a feature map generating unit which extracts feature information from the downscaling image to generate a feature map;
a visual attention calculating unit which generates a low-level attention map based on visual attention of the feature map; and
an image expansion unit which up-scales the low-level attention map,
wherein an increasing gray value is added to image data disposed on an upper portion of the low-level attention map, and 0 or a decreasing gray value is added to image data disposed on a lower portion of the low-level attention map.
2. The image converting device of claim 1 ,
wherein the visual attention calculating unit generates a plurality of low-level attention maps,
wherein the image converting device further comprises an image combination unit which combines the plurality of low-level attention maps, and
wherein a visual attention map is generated by combining the plurality of low-level attention maps.
3. The image converting device of claim 2 , further comprising:
an image filtering unit which filters the plurality of combined low-level attention maps.
4. The image converting device of claim 3 , wherein the feature map comprises a center area and a surrounding area, and the visual attention is determined based on a difference between a histogram of the center area and a histogram of the surrounding area.
5. The image converting device of claim 3 , wherein the feature map comprises a center area and a surrounding area, the surrounding area and the center area each comprise at least one unit-block, respectively, and the visual attention is determined based on a moment for luminance values of a plurality of pixels included in the unit-block.
6. The image converting device of claim 2 , wherein the image expansion unit expands the combined plurality of low-level attention maps.
7. The image converting device of claim 1 , further comprising:
an image filtering unit which filters the low-level attention map.
8. The image converting device of claim 7 , wherein the feature map comprises a center area and a surrounding area, the surrounding area and the center area comprise at least one unit-block each, and the visual attention is determined based on a moment for luminance values of a plurality of pixels included in the at least one unit-block.
9. The image converting device of claim 1 , wherein the downscaling image is an image wherein the two-dimensional image is downscaled in a horizontal direction, in a vertical direction, or in both the horizontal direction and the vertical direction.
10. The image converting device of claim 9 , wherein a plurality of downscaling images are generated, and the plurality of downscaling images are processed in one frame.
11. The image converting device of claim 1 , further comprising:
a parallax information generating unit which generates parallax information based on the visual attention map and the two-dimensional image; and
a three-dimensional image rendering unit which renders the three-dimensional image based on the parallax information and the two-dimensional image.
12. An image converting method comprising:
downscaling a two-dimensional image using an image converting device to generate at least one downscaling image;
extracting feature information from the downscaling image using the image converting device to generate a feature map;
generating a low-level attention map using the image converting device based on a visual attention of the feature map; and
up-scaling the low-level attention map using the image converting device,
wherein an increasing gray value is added to image data disposed on an upper portion of the low-level attention map, and 0 or a decreasing gray value is added to image data disposed on a lower portion of the low-level attention map.
13. The image converting method of claim 12 ,
wherein a plurality of low-level attention maps are generated,
wherein the method further comprises combining the plurality of low-level attention maps, and
wherein a visual attention map is generated from the combined plurality of low-level attention maps.
14. The image converting method of claim 13 , further comprising:
filtering the combined plurality of low-level attention maps.
15. The image converting method of claim 14 , wherein the feature map comprises a center area and a surrounding area, and the visual attention is determined based on a difference between a histogram of the center area and a histogram of the surrounding area.
16. The image converting method of claim 14 , wherein the feature map comprises a center area and a surrounding area, the surrounding area and the center area comprise at least one unit-block, respectively, and the visual attention is determined based on a moment for luminance values of a plurality of pixels included in the at least one unit-block.
17. The image converting method of claim 12 , wherein the downscaling image is an image wherein the 2D image is downscaled in a horizontal direction, in a vertical direction, or in both the horizontal and vertical direction.
18. The image converting method of claim 17 , wherein a plurality of downscaling images are generated, and the plurality of downscaling images are processed in one frame.
19. The image converting method of claim 12 , further comprising:
generating parallax information based on the visual attention map and the two-dimensional image; and
rendering a three-dimensional image based on the parallax information and the two-dimensional image.
20. A three-dimensional image display device comprising:
a display panel comprising a plurality of pixels; and
an image converting device which converts a two-dimensional image into a three-dimensional image,
wherein the image converting device comprises:
a downscaling unit which downscales a two-dimensional image to generate at least one downscaling image;
a feature map generating unit which extracts feature information from the downscaling image to generate a feature map;
a visual attention calculating unit which generates a low-level attention map based on visual attention of the feature map; and
an image expansion unit which up-scales the low-level attention map,
wherein an increasing gray value is added to image data disposed on an upper portion of the low-level attention map, and 0 or a decreasing gray value is added to image data disposed on a lower portion of the low-level attention map.