Method for multi-subtree-based distributed image training and searching

Abstract

A method for multi-subtree-based distributed image training and searching comprises the following steps: step 1, selecting initial cluster central points and clustering by computational nodes, and distributing the clustered new cluster central points to each computational nodes; step 2, training task subtrees by each computational node, and taking a cluster central point as a task subtree growing point. The method for multi-subtree-based distributed image training and searching further comprises step 3, extracting feature points from the image to be searched, and transmitting the feature points to corresponding computational nodes according to cluster central point affiliation; step 4, utilizing task subtree to process and transmitting the results to management nodes by the computational nodes, and summarizing the computational results of computational nodes to acquire image searching results by the management nodes. The method can divide the training task of one vocabulary tree into the training tasks of a plurality of subtrees, enable a plurality of computational nodes to process in parallel so as to accommodate larger image training set for strong expansibility, meanwhile reduce the time cost for process of image training and searching.

Description

technical field [0001] The invention belongs to the field of computer software and relates to image processing technology, in particular to a multi-subtree-based distributed image training and retrieval method. Background technique [0002] Distributed computing is a data processing process that uses multiple computing nodes to divide tasks that require huge computing power into multiple small tasks and distribute them to multiple computing nodes, let them process in parallel, and then aggregate the results. The so-called computing nodes may be multiple computers, servers, or multiple software programs running simultaneously on one computer. [0003] Image retrieval is to compare the image to be recognized with a comparison image library containing multiple comparison images, that is, each comparison image in the training set, and find the comparison image with the highest similarity between the training set and the image to be recognized. [0004] Due to the existence of b...

AI Technical Summary

Problems solved by technology

[0005] In order to obtain better matching accuracy in the large-scale image training set, the existing vocabulary tree image processing technology including the above-mentioned public documents needs to generate a huge vocabulary tree, which is a big burden on the hardware memory overhead of the aforementioned computing nodes. Test, it takes a long time to generate a huge vocabulary tree at the same time

Images