METHOD FOR REPRESENTING IMAGES USING QUANTIZED EMBEDDINGS OF SCALE-INVARIANT IMAGE FEATURES

摘要

PROBLEM TO BE SOLVED: To allow randomized embeddings of scale-invariant image features for image search, while reducing resource consumption at a client.;SOLUTION: Scale-invariant features are extracted from an image. The features are projected to a lower dimensional random projection matrix by multiplying the features by a matrix of random entries. The matrix of random projections is quantized to produce a matrix of quantization indices. The quantization indices form a query vector for searching a database of images to retrieve metadata related to the image.;COPYRIGHT: (C)2014,JPO&INPIT