Global feature descriptor polymerization method

Abstract

The invention provides a global feature descriptor polymerization method. The global feature descriptor polymerization method includes the steps of obtaining local feature descriptors of a to-be-processed image, according to according to the significance of the local feature descriptors, ranking all the local feature descriptors, and obtaining the ranked local feature descriptors; according to interceptive values, selecting a plurality of local feature descriptors used for global feature descriptor polymerization from the ranked local feature descriptors; conducting polymerization on the multiple local feature descriptors through the adoption of a Gaussian mixture model so as to obtain a global feature descriptor of the to-be-processed image, wherein the interceptive values are obtained by training retrieved results of images in a preset image data set. By means of the method, the time complexity in the global feature descriptor polymerization process in the prior art can be reduced, and the discriminability and the robustness of the global feature descriptor are improved.

Description

technical field [0001] The invention relates to computer technology, in particular to an aggregation method of global feature descriptors. Background technique [0002] At present, there are more and more mobile visual search applications, and people in the industry aggregate local feature descriptors into global feature descriptors for image retrieval or image classification. Fisher Vector is a commonly used global feature descriptor aggregated from local feature descriptors, and Fisher Vector has achieved better performance in image retrieval and classification. [0003] In the prior art, the Fisher vector is obtained by extracting local feature descriptors of an image, and aggregating all the local feature descriptors into a Fisher vector. However, the time complexity of descriptor aggregation in the prior art is relatively high, and the obtained Fisher vector will be disturbed by some noisy local points. For example, generally, the number of local feature descriptors o...

AI Technical Summary

Problems solved by technology

However, the time complexity of descriptor aggregation in the prior art is high, and the obtained Fisher vector will be disturbed by some noisy local points

For example, generally, the number of local feature descriptors of an image is not less than 1000. If all the local feature descriptors are directly used to participate in the aggregation process, the time complexity of aggregation is very high; in addition, the local feature descriptor There is still some noise in , if it participates in the aggregation of Fisher vectors, it will affect the discriminative ability of the global feature descriptor, resulting in the lack of good robustness of the global feature descriptor, thus affecting the performance of image retrieval or classification

Images