A Diversified Image Annotation and Retrieval Method Based on the Ensemble of Multiple RBFNN Classifiers

Abstract

The invention discloses a method for labeling and searching for diversified pictures based on the integration of multiple classifiers. The method mainly comprises the following four steps: (1) constructing and studying a plurality of different RBFNN integrated classifier molds; (2) utilizing optimized a plurality of different RBFNN integrated classifier molds to conduct diversified labeling for the pictures in a searching picture library; (3) conducting diversified searching for the searching picture library according to searching key words and labeling results obtained in step (2): firstly, searching all pictures labeled with searching key words and ordering according to the similarity of concepts, and then ordering the pictures which belong to different sub-concepts from high to low according to the similarity of the concepts to obtain searching results; and (4) outputting the searching results. The method improves the accuracy of image searching, meanwhile, greatly improves the diversity for the image searching results, saves the searching time, and has higher robustness and practicability.

Description

technical field [0001] The invention relates to a diversified image labeling and retrieval system and multi-classifier integration ideas, in particular to a diversified image labeling and retrieval method based on the integration of multiple RBFNN classifiers. Background technique [0002] Image retrieval is a science and technology that emerged and developed with the rapid development of computer science and technology. It has very important application prospects in the fields of national defense, social security, remote sensing, medicine, and business information. In recent years, with the rapid development and popularization of various electronic devices such as scanners, digital cameras, digital video cameras, etc., especially the improvement of multimedia technology and the rapid development and popularization of the Internet, the image data presents a geometric progression. As a result, large-capacity image and massive video databases appeared. However, the scale and ...

AI Technical Summary

Problems solved by technology

This method not only solves the problem that traditional correlation and diversity cannot be learned in parallel, but also solves the problem of unbalanced data learning, the problem that a single RBFNN is difficult to obtain more image "concepts" and "sub-concepts" and the problem that a single RBFNN is difficult to handle high Dimensional and complex data problems, so that the accuracy and efficiency of image diverse labeling and retrieval are improved

Images