A Hierarchical Visual Feature Extraction Method Based on Geographical Information

Abstract

The invention discloses a geographic information based hierarchical visual feature extracting method. The geographic information based hierarchical visual feature extracting method comprises the following steps of 1 compiling crawlers, downloading pictures and sharing images and geographic information on websites, 2 utilizing image word bag models to express image features, 3 applying a semi-supervised theme modeling method to organize image visual words in visual themes form according to the geographic information; 4 excavating hierarchical features of the visual themes and obtaining visual features describing specific geographic information at different dimensions and on side faces, and 5 utilizing the obtained hierarchical visual features to cluster, classify and retrieve the images. According to the geographic information based hierarchical visual feature extracting method, hierarchical theme modeling and semi-supervised learning are integrated, the image high-dimensional visual words are compacted into the representative visual themes, the geographic information is introduced into the theme modeling process, the hierarchical visual theme model is obtained through learning, the images are expressed in a multi-visual-theme distribution mode and accordingly the hierarchical visual features having semantic expression capacity are obtained.

Description

technical field [0001] The invention relates to image feature extraction and hierarchical topic modeling, in particular to a method for extracting hierarchical visual features based on geographical information. Background technique [0002] In recent years, with the rapid development of the Internet, telecommunication networks and mobile smart terminals, more and more image sharing websites have emerged, and hundreds of millions of photos taken from all over the world are being uploaded to the Internet every day. The rapid growth of image data not only provides Internet users with the experience of traveling around the world without leaving home and provides more samples for image analysis applications, but also brings the challenge of how to automatically cluster and classify large-scale data. In order to meet this challenge, many studies have focused on how to extract the most representative and distinguishable image features that can reflect image semantic information fro...

AI Technical Summary

Problems solved by technology

Although this type of method obtains the expression of documents and images at different granularities through a hierarchical topic structure, because it is still an unsupervised method, the obtained topics are difficult to correspond to real semantics.

Some researchers have proposed supervised topic models, such as supervised topic modeling (Supervised LDA), etc., but this type of method fails to solve the problem of multi-scale and multi-granularity expression, and the training of this type of model requires a lot of Manually labeled data brings difficulties to model training

Images