Query image search

A system, comprising:

• a communications interface configured to receive a query image;
• and
• a data retrieval apparatus including one or more processors configured to:
• obtain, based on the query image, a set of ordered search results identifying web pages that each include an image a near duplicate of the query image, the search results being ordered in a first arrangement in which one of the search results that identifies a web page that includes a near-duplicate image is at a set position, and
• obtain text labels for the query image;
• compare one or more of the text labels to text of a web page identified by one of the search results;
• determine, based on the comparison, that the text of the web page identified by the one of the search results matches at least one of the text labels for the query image;
• and
• re-order, based on the determination, the set of ordered search results into a second arrangement in which the one of the search results is at a higher position than the set position.

A non-transitory computer readable media storing software comprising instructions executable by a processing device and upon such execution cause the processing device to perform operations comprising:

• receiving a query image;
• obtaining, based on the query image, a set of ordered search results identifying one or more web pages that each include an image that is a near-duplicate of the query image, the search results being ordered in a first arrangement in which one of the search results that identifies a web page that includes a near-duplicate image is at a set position;
• obtaining text labels associated with the query image;
• comparing one or more of the text labels to text of a web page identified by one of the search results;
• determining, based on the comparison, that the text of the web page identified by the one of the search results matches at least one of the text labels for the query image;
• and
• re-ordering, based on the determination, the set of ordered search results into a second arrangement in which the one of the search results is at a higher position than the set position.