Contextual weighting and efficient re-ranking for vocabulary tree based image retrieval

摘要

Systems and methods are disclosed to search for a query image, by detecting local invariant features and local descriptors; retrieving best matching images by quantizing the local descriptors with a vocabulary tree; and reordering retrieved images with results from the vocabulary tree quantization.

主权项

1. A method to search for a query image, comprising
detecting local invariant features and local descriptors; retrieving best matching images by incorporating one or more contexts in matching quantized local descriptors with a vocabulary tree; reordering retrieved images with results from the vocabulary tree quantization; measuring similarity of local descriptors through image specific descriptor weighting; and comprising v, where weight wiq is defined based on the node counts along the quantization path of xi, comprising determiningwiq=∑v∈T⁡(xi)⁢ω⁡(v)∑v∈T⁡(xi)⁢ω⁡(v)×nq⁡(v), where ω(v) is a weighting coefficient set to idƒ(v) empirically, where weight wiq depends on the descriptor only, and is shared for all nodes v along the path T(xi) and where nq(v) represents a number of descriptors in image q that are quantized to v.