Picture retrieval clustering method facing to Web2.0 label picture shared space

Abstract

The invention discloses a retrieval result clustering method facing to a Web2.0 label picture shared space, which comprises the following steps: excavating a vocabulary relationship and an associated relationship between labels; obtaining an expanded querying label set by a query label according to the vocabulary relationship between the labels; obtaining a candidate image set relevant to query by the expanded query label set; selecting front K most relevant labels according to the relevance measurement of the labels in the query label set and the candidate image set; automatically dividing the K labels into an optimal clustering result according to the association between the K labels by a clustering algorithm based on a picture division from top to bottom; and correspondingly clusteringthe candidate image set according to clustering labels. Aiming at the problem of inconformity of label expression, the effective query expansion is realized, and the image clustering method based on most relevant label set clustering solves the problem of diversity of label semanteme. Compared with a traditional method, the invention leads a user to rapidly and effectively retrieve and browse a picture in the Web2.0 label picture shared space.

Description

technical field [0001] The invention relates to technologies related to retrieval and clustering processing of massive pictures, in particular to a picture result clustering method oriented to the shared space of Web2.0 tagged pictures. Background technique [0002] In recent years, more and more tag application systems for text and multimedia content have appeared on the Internet. For example, Del.icio.us provides joint tags for web page bookmarks. Similarly, there is CiteUlike for the field of academic paper publishing, which targets Flickr for image label sharing, and Youtube for video label sharing, etc., the success of these commercial applications also confirms that labeling is a good joint sharing approach, and label retrieval has become a common and popular method in the field of information retrieval. However, semantic deviation and certain limitations generally exist in tag-based retrieval. For example, different users use different tags (such as synonyms, singular...

AI Technical Summary

Problems solved by technology

[0002] In recent years, more and more tag application systems for text and multimedia content have appeared on the Internet. For example, Del.icio.us provides joint tags for web page bookmarks. Similarly, there is CiteUlike for the field of academic paper publishing, which targets Flickr for image label sharing, and Youtube for video label sharing, etc., the success of these commercial applications also confirms that labeling is a good joint sharing approach, and label retrieval has become a common and popular method in the field of information retrieval. However, there are semantic deviations and certain limitations in tag-based retrieval. For example, different users use different tags (such as synonyms, singular and plural, etc.) The ambiguity of the query also leads to ambiguous query semantics. How to capture this inconsistency during retrieval and quickly cluster the retrieval results to effectively distinguish ambiguity has become one of the concerns of the academic and industrial circles;

[0003] At present, there are many researches on image retrieval systems using image clustering image retrieval algorithms. Clustering algorithms are basically based on a set distance measure. The choice of distance measure determines what kind of pictures are clustered together. Pull distance, Manhattan distance, etc., but these methods are not well adapted to the highly dynamic and massive Web2.0 labeling system. Flickr mines label information to cluster image retrieval results. However, this kind of Flickr The clustering application not only does not consider the inconsistency of the label itself, but is only suitable for clustering the retrieval results of a single label;

Images