Back to results
US 10,032,091 B2Granted
Spatial organization of images based on emotion face clouds
AssigneeEmotient, Inc.
InventorsJavier Movellan, Joshua Susskind, Ken Denman
Life of this patent
Estimating the term…
Abstract
A collection of photos is organized by arranging a limited number of clusters of the photos on a predefined topology, so that similar photos are placed in the same cluster or a nearby cluster. Similarity is measured in attribute space. The attributes may include automatically recognized facial expression attributes.
Claims20
A computer-implemented method of spatially organizing a collection of images, the method comprising steps of:
- obtaining a collection of images that include human faces;
- obtaining an attribute vector for each image of the collection of images, wherein each attribute vector includes attribute values for an associated image of the collection of images;
- obtaining an indication of one or more attributes of interest, wherein the one or more attributes of interest are associated with attribute values included in each attribute vector;
- obtaining scaling factors for each of the one or more attributes of interest;
- determining an organizational structure for mapping the collection of images;
- determining a maximum number of image clusters to be displayed in the organizational structure;
- sorting the collection of images based on the respective attribute values and the respective scaling factors for the attribute values;
- clustering the collection of images by similarity of the attribute values for each image of the collection of images, such that images in the collection of images are placed in the organizational structure based, at least in part, on the attribute values, thereby creating a plurality of image clusters, the plurality of image clusters including no more image clusters than the maximum number;
- picking a representative image for each image cluster;
- and
- displaying the representative images and, when a particular representative image is selected by a user, displaying the images in the image cluster represented by the particular representative image.
8 more elements
A computing device configured to spatially organize a collection of images, the computing device comprising:
- one or more processors;
- and
- a memory coupled to the one or more processors and comprising computer readable instructions that, when executed by the one or more processors, cause the computing device to:
- obtain a collection of images that include human faces;
- obtain an attribute vector for each image of the collection of images, wherein each attribute vector includes attribute values for an associated image of the collection of images;
- obtain an indication of one or more attributes of interest, wherein the one or more attributes of interest are associated with attribute values included in each attribute vector;
- obtain scaling factors for each of the one or more attributes of interest;
- determine an organizational structure for mapping the collection of images;
- determine a maximum number of image clusters to be displayed in the organizational structure;
- sort the collection of images based on the respective attribute values and the respective scaling factors for the attribute values;
- cluster the collection of images by similarity of the attribute values for each image of the collection of images, such that images in the collection of images are placed in the organizational structure based, at least in part, on the attribute values, thereby creating a plurality of image clusters, the plurality of image clusters including no more image clusters than the maximum number;
- pick a representative image for each image cluster;
- and
- output for display the representative images and, when a particular representative image is selected by a user, output for display the images in the image cluster represented by the particular representative image.
11 more elements
A non-transitory computer readable medium containing instructions that, when executed, cause one or more processors to:
- obtain a collection of images that include human faces;
- obtain an attribute vector for each image of the collection of images, wherein each attribute vector includes attribute values for an associated image of the collection of images;
- obtain an indication of one or more attributes of interest, wherein the one or more attributes of interest are associated with attribute values included in each attribute vector;
- obtain scaling factors for each of the one or more attributes of interest;
- determine an organizational structure for mapping the collection of images;
- determine a maximum number of image clusters to be displayed in the organizational structure;
- sort the collection of images based on the respective attribute values and the scaling factors for the attribute values;
- cluster the collection of images by similarity of the attribute values for each image of the collection of images, such that images in the collection of images are placed in the organizational structure based, at least in part, on the attribute values, thereby creating a plurality of image clusters, the plurality of image clusters including no more image clusters than the maximum number;
- pick a representative image for each image cluster;
- and
- output for display the representative images and, when a particular representative image is selected by a user, output for display the images in the image cluster represented by the particular representative image.
8 more elements
Dependencies are inferred from the claim text.