Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining image search results. One of the methods includes receiving a query image. Multiple feature vectors from the query image are computed and quantized into one or more respective visual words. Multiple posting lists are identified, each posting list corresponding to a quantized visual word, each posting list identifying images that have the visual word, each identified image being associated with geometry data for the corresponding visual word. One or more matching images are identified that match the query image by before traversing the multiple posting lists more than once. While traversing the multiple posting lists, a score is computed for each matching image when identified as a matching image and before traversal of the multiple posting lists is complete.

Abstract: In general, in one aspect, a method includes receiving, by one or more processors, a query image, obtaining, by the one or more processors, search results responsive to the query image, each search result identifying a corresponding web page containing an image that is determined to be responsive to the query image, the search results being ordered in a first arrangement, obtaining, by the one or more processors, text labels associated with the query image, and generating, by the one or more processors a second arrangement of the search results by ordering the search results based on a presence in the respective corresponding web pages of one or more of the text labels associated with the query image. This and other implementations of this aspect can include corresponding systems, apparatus, and computer program products.

Abstract: Methods, systems, apparatus, and computer program products, including accessing first data that defines a first image, generate a first value by applying a mathematical function to the first data, generating a second image from the first data of the first image, the second image being a version of the first image and defined by second data that is different from the first data of the first image, associating the first value of the first image with the second image, generating a third image from the second data of the second image, the third image being a version of the second image and defined by third data that is different from the second data of the second image, and associating the first value of the first image with the third image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining image search results. One of the methods includes aligning each image in a collection of near duplicate images to a common coordinate frame. One or more visual words are determined in the common coordinate frame for each of the images in the collection of near duplicate images. A union of visual words is determined, wherein the union of visual words comprises determined visual words in the common coordinate frame. A posting list item that identifies the collection of near duplicate images is added to one or more corresponding posting lists, wherein each posting list identifies one or more collections of near duplicate images whose union of determined visual words have the particular visual word.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting image search results. In one aspect, a method includes receiving image search data specifying images that have been identified as responsive to a query. A set of image group identifiers are received for two or more of the images. Different image group identifiers specify different image groups to which an image belongs. A determination is made that the sets of image group identifiers for two images each include a matching image group identifier. In response to the determination the two images are determined to be near-duplicate images, and a presentation position for a search result that references one of the near-duplicate images is adjusted. Data that cause presentation of search results that reference the near-duplicate images according to the adjusted presentation position.

Abstract: Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.

Abstract: Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.