Providing visual effects for images
Implementations relate to providing visual effects for images. In some implementations, a method includes detecting one or more objects in an image. The method identifies one or more important objects of the objects, where the important objects are determined to have an importance measurement satisfying a predetermined threshold indicating their importance to a viewer of the image. The method determines an application of a visual image effect to the image based on the important objects.
1. A computer-implemented method comprising:
identifying a plurality of important objects in an image, wherein the plurality of important objects are determined to individually have an importance measurement satisfying a predetermined threshold indicating importance to a viewer of the image;
determining outermost objects of the plurality of important objects;
determining a distance between the outermost objects;
determining a level of suitability of applying a visual border effect to the image based on the plurality of important objects and the distance between the outermost objects;
determining a centering location in the image to position the visual border effect based on determining an average center from the respective centers of each of the plurality of important objects;
determining a strength of the visual border effect and a radius in the image for below a minimum threshold effect; and
applying the visual border effect to the image extending to or near borders of the image, according to the level of suitability, the strength, the centering location, and the radius.
2. The method of claim 1 wherein the plurality of important objects are important faces.
3. The method of claim 1 wherein the radius is unaffected by the visual border effect.
4. The method of claim 1 wherein the visual border effect is a vignette.
5. The method of claim 1 wherein the importance measurement includes a determination of whether an object has a size greater than a predetermined size, where the predetermined size is based on a size of the image.
6. The method of claim 1 wherein the importance measurement includes a determination of whether an object has a sharpness over a predetermined threshold sharpness.
7. The method of claim 1 further comprising determining a strength of darkening of the visual border effect.
8. The method of claim 7 wherein the strength of the darkening is based on at least one of:
a location of one of more of the plurality of important objects in the image,
a combined size of the plurality of important objects in the image, and
number of the plurality of important objects in the image.
9. A computer implemented method comprising:
identifying a plurality of important objects in an image, wherein the plurality of important objects are determined to have an importance measurement satisfying a predetermined threshold indicating importance to a viewer of the image;
determining a distance between the plurality of important objects;
determining whether to apply a visual border effect to the image based on the distance between the plurality of important objects;
in response to determining that the visual border effect is to be applied, determining a centering location in the image for a center of a visual border effect to be centered, wherein the centering location is based on an average center of the plurality of important objects in the image;
determining a strength of the visual border effect and a radius in the image for below a minimum threshold effect; and
applying the visual border effect to the image extending to or near borders of the image, according to the strength, the centering location, and the radius, wherein the visual border effect is applied in greater strength closer to the borders of the image than towards the centering location.
10. A system comprising:
a storage device; and
at least one processor accessing the storage device and operative to perform operations comprising:
identifying a plurality of important objects in an image, wherein the plurality of important objects are determined to individually have an importance measurement satisfying a predetermined threshold indicating importance to a viewer of the image;
determining outermost objects of the plurality of important objects;
determining a distance between the outermost objects;
determining a level of suitability of applying a visual border effect to the image based on the plurality of important objects and the distance between the outermost objects;
determining a centering location in the image to position the visual border effect based on determining an average center from the respective centers of each of the plurality of important objects;
determining a strength of the visual border effect and a radius in the image for below a minimum threshold effect; and
applying the visual border effect to the image extending to or near borders of the image, according to the level of suitability, the strength, the centering location, and the radius.
11. The computer implemented method of claim 9 wherein the visual border effect is a vignette.
12. The system of claim 10 wherein the visual border effect is a vignette.
13. The computer implemented method of claim 9 further comprising determining a strength of darkening of the visual border effect, wherein the strength of the darkening is based on at least one of:
a location of one of more of the plurality of important objects in the image,
a combined size of the plurality of important objects in the image, and
number of the plurality of important objects in the image.
14. The system of claim 10 wherein the operations further comprise determining a strength of darkening of the visual border effect, wherein the strength of the darkening is based on at least one of:
a location of one of more of the plurality of important objects in the image,
a combined size of the plurality of important objects in the image, and
number of the plurality of important objects in the image.