System and method for associating images with semantic entities
View Patent ↗A system and computer-implemented method for associating images with semantic entities and providing search results using the semantic entities. An image database contains one or more source images associated with one or more images labels. A computer may generate one or more documents containing the labels associated with each image. Analysis may be performed on the one or more documents to associate the source images with semantic entities. The semantic entities may be used to provide search results. In response to receiving a target image as a search query, the target image may be compared with the source images to identify similar images. The semantic entities associated with the similar images may be used to determine a semantic entity for the target image. The semantic entity for the target image may be used to provide search results in response to the search initiated by the target image.
1. A computer-implemented method comprising:
receiving, using one or more computing devices, an input image as a search query;
determining, using the one or more computing devices, reference images that are identified as matching the input image, each image of the reference images being associated with at least one entity including text information related to that image;
selecting, using the one or more computing devices, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image;
identifying, using the one or more computing devices, a particular entity from amongst the one or more particular entities based on a number of the reference images that are associated with one or more entities that include the text information of the identified particular entity, wherein the text information of the identified particular entity is configured to disambiguate from other different entities that include common text information; and
storing, using the one or more computing devices, data that associates the input image with the identified particular entity.
2. The method of claim 1 , wherein determining, using the one or more computing devices, reference images that are identified as matching the input image comprises:
identifying reference images that are visually similar to the input image.
3. The method of claim 1 , wherein selecting, using the one or more computing devices, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting entities of the multiple entities that are associated with the reference images that describe a concept or topic associated with a particular ontology.
4. The method of claim 1 , wherein selecting, using the one or more computing devices, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting a given entity of the multiple entities based on a confidence score representing a likelihood the given entity is associated with a particular reference image.
5. The method of claim 1 , wherein selecting, using the one or more computing devices, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting a given entity of the multiple entities based on a similarity score representing a similarity of a particular reference image associated with the given entity with the input image.
6. The method of claim 1 , wherein storing data, using the one or more computing devices, comprises generating a results page indicating an association between the input image and the identified particular entity.
7. The method of claim 1 , wherein the text information associated with each image of the reference images describes a concept or topic related to that image.
8. The method of claim 1 , further comprising generating the text information associated with each image of the reference images from a source webpage for that image.
9. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
receiving an input image as a search query;
determining reference images that are identified as matching the input image;
selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image, each image of the reference images being associated with at least one entity including text information related to that image;
identifying, using the one or more computing devices, a particular entity from amongst the one or more particular entities based on a number of the reference images that are associated with one or more entities that include the text information of the identified particular entity, wherein the text information of the identified particular entity is configured to disambiguate from other different entities that include common text information; and
storing data that associates the input image with the identified particular entity.
10. The system of claim 9 , wherein determining reference images that are identified as matching the input image comprises:
identifying reference images that are visually similar to the input image.
11. The system of claim 9 , wherein selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting entities of the multiple entities that are associated with the reference images that describe a concept or topic associate with a particular ontology.
12. The system of claim 9 , wherein selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting a given entity of the multiple entities based on a confidence score representing a likelihood the given entity is associated with a given reference image.
13. The system of claim 9 , wherein selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting a given entity of the multiple entities based on a similarity score representing a similarity of a particular reference image associated with the given entity with the input image.
14. The system of claim 9 , wherein storing data comprises generating a results page indicating an association between the input image and the identified particular entity.
15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
receiving an input image as a search query;
obtaining reference images that are identified as matching the input image;
selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image, each image of the reference images being associated with at least one entity including text information related to that image;
identifying, using the one or more computing devices, a particular entity from amongst the one or more particular entities based on a number of the reference images that are associated with one or more entities that include the text information of the identified particular entity, wherein the text information of the identified particular entity is configured to disambiguate from other different entities that include common text information; and
storing data that associates the input image with the identified particular entity.
16. The medium of claim 15 , wherein obtaining reference images that are identified as matching the input image comprises:
identifying reference images that are visually similar to the input image.
17. The medium of claim 15 , wherein selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting a given entity of the multiple entities based on a confidence score representing a likelihood the given entity is associated with a particular reference image.
18. The medium of claim 15 , wherein selecting, from among multiple entities that are collectively associated with the reference images, one or more particular entities to associate with the input image comprises:
selecting a given entity of the multiple entities based on a similarity score representing a similarity of a particular reference image associated with the given entity with the input image.