Methods and apparatus for visual search

摘要

For each image of a set of images, the each image is characterized with a set of fixed-orientation texture descriptors and a set of color descriptors. The set of images is indexed in a color index and a texture index. Similarly, a query image is characterized with a set of fixed-orientation texture descriptors. The set of fixed orientation texture descriptors of the query image includes a set of fixed orientation descriptors for each of a set of rotated query images, and a set of color descriptors of the query image. A rotated local Bag-of-Features (BoF) operation is performed upon the set of rotated query images and the set of images. Each of the set of images is ranked based on the rotated local Bag-of-Features operation.

主权项

1. A method, comprising:
executing an image analysis module on one or more processors of a computing device to perform:
characterizing each image in a set of images with a set of fixed-orientation texture descriptors and a set of color descriptors;indexing the set of images in a color index comprising the set of color descriptors for each image of the set of images, and in a texture index comprising the set of fixed-orientation texture descriptors for each image of the set of images, the indexing comprising encoding spatial information in the set of color descriptors and in the set of fixed-orientation texture descriptors, the spatial information including feature location and scale as encoded in both the set of color descriptors and in the set of fixed-orientation texture descriptors;characterizing a query image with the set of fixed-orientation texture descriptors of the query image, the set of fixed-orientation texture descriptors of the query image comprising a set of fixed orientation descriptors for each of a set of rotated query images, and with the set of color descriptors of the query image;performing a rotated local Bag-of-Features (BoF) operation upon the set of rotated query images and the set of images; andranking each of the set of images based on the rotated local Bag-of-Features operation.