AUTOMATED ANIMATION FOR PRESENTATION OF IMAGES
An image such as a light-field image may be displayed dynamically through the use of an automatically generated animation. The image may be received in a data store. One or more attributes of the image may be automatically evaluated. Based on the one or more attributes, a first animation parameter may be selected. An animation of the image may be automatically generated such that the animation possesses the first animation parameter. On a display device, the animation may be displayed. The one or more attributes may optionally include coloration of the image, presence of a computer-recognizable feature in the image, presence of a computer-recognizable human face in the image, a gaze direction of a person appearing in the image, and/or a depth, relative to the camera, of an object appearing in the image.
1 . A method for animating presentation of an image, the method comprising:
in a data store, receiving the image;
in a processor, automatically evaluating one or more attributes of the image;
in the processor, based on the one or more attributes, automatically selecting a first animation parameter;
in the processor, generating an animation of the image such that the animation possesses the first animation parameter; and
on a display device, displaying the animation.
2 . The method of claim 1 , wherein the one or more attributes comprise a coloration of the image.
3 . The method of claim 2 , wherein automatically evaluating the one or more attributes comprises:
dividing the image into a plurality of regions; and
assessing coloration of each of the regions.
4 . The method of claim 1 , wherein the one or more attributes comprise presence of a computer-recognizable feature in the image.
5 . The method of claim 4 , wherein automatically evaluating the one or more attributes comprises:
dividing the image into a plurality of regions; and
using at least one of color, texture, shape, and position of a first region of the plurality of regions to identify the computer-recognizable feature in the first region.
6 . The method of claim 1 , wherein the one or more attributes comprise presence of a computer-recognizable human face in the image.
7 . The method of claim 6 , wherein automatically evaluating the one or more attributes comprises analyzing the computer-recognizable human face to assess an emotion expressed by the computer-recognizable human face.
8 . The method of claim 1 , wherein the one or more attributes comprise a gaze direction of a person appearing in the image.
9 . The method of claim 8 , wherein automatically evaluating the one or more attributes comprises:
identifying a pupil of the person; and
based on a location of the pupil relative to one or more other facial features of the person, assessing the gaze direction.
10 . The method of claim 1 , wherein the one or more attributes comprise a depth, relative to a camera used to capture the image, of an object appearing in the image.
11 . The method of claim 10 , wherein the image comprises a light-field image;
and wherein automatically evaluating the one or more attributes comprises using a depth map for the image, the depth map comprising the depth, to identify at least one significant spatial feature of the object.
12 . The method of claim 1 , wherein automatically selecting the first animation parameter comprises:
generating an emotion index indicative of an emotion conveyed by the image; and
using the emotion index to select the first animation parameter.
13 . The method of claim 12 , wherein the first animation parameter comprises a tempo of the animation.
14 . The method of claim 1 , wherein generating the animation comprises generating a view of the image through a virtual camera.
15 . The method of claim 14 , where the first animation parameter is selected from the group consisting of a change in an attribute of the virtual camera, and motion of the virtual camera.
16 . The method of claim 1 , wherein the image comprises a light-field image;
wherein generating the animation of the image comprises, for each frame of the image, generating a projection of the light-field image.
17 . A non-transitory computer-readable medium for animating presentation of an image, comprising instructions stored thereon, that when executed by a processor, perform the steps of:
causing a data store to receive the image;
automatically evaluating one or more attributes of the image;
based on the one or more attributes, automatically selecting a first animation parameter;
generating an animation of the image such that the animation possesses the first animation parameter; and
causing a display device to display the animation.
18 . The non-transitory computer-readable medium of claim 17 , wherein the one or more attributes comprise a coloration of the image;
and wherein automatically evaluating the one or more attributes comprises:
dividing the image into a plurality of regions; and
assessing coloration of each of the regions.
19 . The non-transitory computer-readable medium of claim 17 , wherein the one or more attributes comprise presence of a computer-recognizable feature in the image;
and wherein automatically evaluating the one or more attributes comprises:
dividing the image into a plurality of regions; and
using at least one of color, texture, shape, and position of a first region of the plurality of regions to identify the computer-recognizable feature in the first region.
20 . The non-transitory computer-readable medium of claim 17 , wherein the one or more attributes comprise presence of a computer-recognizable human face in the image;
wherein automatically evaluating the one or more attributes comprises analyzing the computer-recognizable human face to assess an emotion expressed by the computer-recognizable human face.
21 . The non-transitory computer-readable medium of claim 17 , wherein the one or more attributes comprise a gaze direction of a person appearing in the image;
and wherein automatically evaluating the one or more attributes comprises:
identifying a pupil of the person; and
based on a location of the pupil relative to one or more other facial features of the person, assessing the gaze direction.
22 . The non-transitory computer-readable medium of claim 17 , wherein the one or more attributes comprise a depth, relative to a camera used to capture the image, of an object appearing in the image;
and wherein the image comprises a light-field image;
and wherein automatically evaluating the one or more attributes comprises using a depth map for the image, the depth map comprising the depth, to identify at least one significant spatial feature of the object.
23 . The non-transitory computer-readable medium of claim 17 , wherein automatically selecting the first animation parameter comprises:
generating an emotion index indicative of an emotion conveyed by the image; and
using the emotion index to select the first animation parameter;
and wherein the first animation parameter comprises a tempo of the animation.
24 . The non-transitory computer-readable medium of claim 17 , wherein generating the animation comprises generating a view of the image through a virtual camera;
where the first animation parameter is selected from the group consisting of a change in an attribute of the virtual camera, and motion of the virtual camera.
25 . The non-transitory computer-readable medium of claim 17 , wherein the image comprises a light-field image;
wherein generating the animation of the image comprises, for each frame of the image, generating a projection of the light-field image.
26 . A system for animating presentation of an image, the system comprising:
a data store configured to receive the image;
a processor communicatively coupled to the data store, configured to:
automatically evaluate one or more attributes of the image;
based on the one or more attributes, automatically select a first animation parameter; and
generate an animation of the image such that the animation possesses the first animation parameter; and
a display device, communicatively coupled to the processor, configured to display the animation.
27 . The system of claim 26 , wherein the one or more attributes comprise a coloration of the image;
and wherein the processor is further configured to automatically evaluate the one or more attributes by:
dividing the image into a plurality of regions; and
assessing coloration of each of the regions.
28 . The system of claim 26 , wherein the one or more attributes comprise presence of a computer-recognizable feature in the image;
wherein the processor is further configured to automatically evaluate the one or more attributes by:
dividing the image into a plurality of regions; and
using at least one of color, texture, shape, and position of a first region of the plurality of regions to identify the computer-recognizable feature in the first region.
29 . The system of claim 26 , wherein the one or more attributes comprise presence of a computer-recognizable human face in the image;
and wherein the processor is further configured to automatically evaluate the one or more attributes by analyzing the computer-recognizable human face to assess an emotion expressed by the computer-recognizable human face.
30 . The system of claim 26 , wherein the one or more attributes comprise a gaze direction of a person appearing in the image;
wherein the processor is further configured to automatically evaluate the one or more attributes by:
identifying a pupil of the person; and
based on a location of the pupil relative to one or more other facial features of the person, assessing the gaze direction.
31 . The system of claim 26 , wherein the one or more attributes comprise a depth, relative to a camera used to capture the image, of an object appearing in the image;
wherein the image comprises a light-field image;
and wherein the processor is further configured to automatically evaluate the one or more attributes by using a depth map for the image, the depth map comprising the depth, to identify at least one significant spatial feature of the object.
32 . The system of claim 26 , wherein the processor is further configured to automatically select the first animation parameter by:
generating an emotion index indicative of an emotion conveyed by the image; and
using the emotion index to select the first animation parameter;
and wherein the first animation parameter comprises a tempo of the animation.
33 . The system of claim 26 , wherein the processor is further configured to generate the animation by generating a view of the image through a virtual camera;
and wherein the first animation parameter is selected from the group consisting of a change in an attribute of the virtual camera, and motion of the virtual camera.
34 . The system of claim 26 , wherein the image comprises a light-field image, and wherein the processor is further configured to generate the animation of the image by, for each frame of the image, generating a projection of the light-field image.