System and method of organizing images
First Claim
Patent Images
1. A method comprising:
- receiving scene description information associated with an image, the scene description information comprising semantic data for a plurality of objects within the image;
assigning a weight to each object in the plurality of objects based on the semantic data, the weight being independent of a geographic location, to yield weighted scene description information;
organizing, via a processor, the image and the weighted scene description information into a data structure, wherein the data structure comprises, for each object in the plurality of objects, a storage array as an infinite array of the each object;
classifying the image based on the data structure to, yield a classified image;
modifying the weight of a specific object in the plurality of objects based on user search preferences and repeated searching for the specific object, to yield a modified object weight;
storing the modified object weight for the specific object in the infinite array for the specific object; and
upon receiving a search query, responding to the search query by returning matching images in the image database based on a comparison of the search query to the data structure using the modified object weight.
1 Assignment
0 Petitions
Accused Products
Abstract
Disclosed are a system, method and computer-readable medium for organizing images. A method aspect relates to receiving an image into a device, receiving incidental information associated with the image, organizing the image and the incidental information into a data structure such as a sparse array, classifying the received image with an image classifier and storing the classified image in an image database, receiving a search query and responding to the search query by searching for and retrieving matching images in the image database based on a comparison of the image search query to the data structure.
95 Citations
19 Claims
-
1. A method comprising:
-
receiving scene description information associated with an image, the scene description information comprising semantic data for a plurality of objects within the image; assigning a weight to each object in the plurality of objects based on the semantic data, the weight being independent of a geographic location, to yield weighted scene description information; organizing, via a processor, the image and the weighted scene description information into a data structure, wherein the data structure comprises, for each object in the plurality of objects, a storage array as an infinite array of the each object; classifying the image based on the data structure to, yield a classified image; modifying the weight of a specific object in the plurality of objects based on user search preferences and repeated searching for the specific object, to yield a modified object weight; storing the modified object weight for the specific object in the infinite array for the specific object; and
upon receiving a search query, responding to the search query by returning matching images in the image database based on a comparison of the search query to the data structure using the modified object weight. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system comprising:
-
a processor; and a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising; receiving scene description information associated with an image, the scene description information comprising semantic data for a plurality of objects within the images; assigning a weight to each object in the plurality of objects based on the semantic data, the weight being independent of a geographic location, to yield weighted scene description information; organizing the image and the weighted scene description information into a data structure, wherein the data structure comprises, for each object in the plurality of objects, a storage array as an infinite array of the each object; classifying the image based on the data structure to, yield a classified image; modifying the weight of a specific object in the plurality of objects based on user search preferences and repeated searching for the specific object, to yield a modified object weight; storing the modified object weight for the specific object in the infinite array for the specific object; and upon receiving a search query, responding to the search query by returning matching images in the image database based on a comparison of the search query to the data structure using the modified object weight. - View Dependent Claims (10, 11, 12, 13)
-
-
14. A computer-readable storage device having instructions stored therein, which, when executed by a computing device, cause the computing device to perform operations comprising:
-
receiving scene description information associated with an image, the scene description information comprising semantic data for a plurality of objects within the image; assigning a weight to each object in the plurality of objects based on the semantic data, the weight being independent of a geographic location, to yield weighted scene description information; organizing the image and the weighted scene description information into a data structure, wherein the data structure comprises, for each object in the plurality of objects, a storage array as an infinite array of the each object; classifying the image based on the data structure to, yield a classified image; modifying the weight a specific object in the plurality of objects based on user search preferences and repeated searching for the specific object, to yield a modified object weight; storing the modified object weight for the specific object in the infinite array for the specific object; and upon receiving a search query, responding to the search query by returning matching images in the image database based on a comparison of the search query to the data structure using the modified object weight. - View Dependent Claims (15, 16, 17, 18, 19)
-
Specification