Image retrieval method based on parameter-free quantum theory

Abstract

The invention provides a bran-new image retrieval framework based on parameter-free quantum estimation. According to the framework, images of a database are regarded as photons generated by a light source, and the relevance of the images of the database is estimated through querying a polarization filter during retrieval. The basic idea of the framework is as follows: firstly, images with relatively low relevance in the database are filtered out by pre-filtering, so as to reduce the computing cost; then, the relevance probability between the images with relatively high relevance and an input query image is computed by using a semi-supervised learning method; finally, the relevance of the images with higher rankings is optimized through parameter-free quantum estimation, so as to obtain a satisfactory retrieval result.

Description

technical field [0001] The invention relates to image retrieval in the field of computer technology, in particular to an image retrieval based on the non-parameter quantum theory. Background technique [0002] With the rapid development of multimedia technology, the improvement of network transmission speed and the continuous emergence of new effective image compression technologies, it has become a reality for people to share global image resources through the network. How to quickly and accurately retrieve the desired image from the massive image database has become one of the research hotspots in the multimedia field in the past ten years. [0003] The traditional image retrieval adopts the retrieval method based on keywords. Each image is first annotated manually, and then image retrieval is based on text-annotated keywords. This method has two disadvantages: one is that a large number of human annotations are required when the image set is large; the other is that it ...

AI Technical Summary

Problems solved by technology

However, a common problem in these methods is that in order to obtain those images that are semantically related to the query image, it is often necessary to implement a large number of parameter tuning based on a small number of given images.

In addition, there is a large semantic gap between the visual features of pictures and semantic concepts, so there are still many problems in content-based picture retrieval.

Images