Cross-media searching method based on discrimination correlation analysis

Abstract

The invention discloses a cross-media searching method based on discrimination correlation analysis. The method comprises the following steps of establishing a cross-media training database, carrying out feature extraction, mean-value pretreatment and linear projection transformation sequentially for different modal samples, and setting a target function according to a projection space; solving the target function to acquire a linear projection vector; establishing a cross-media test database; sequentially performing the feature extraction and mean-value pretreatment for a target to be searched; utilizing the linear projection vector to perform the linear projection transformation for the feature data after the mean-value pretreatment; and calculating an Euclidean distance between two modal data projection vectors, listing the Euclidean distance in ascending order, and acquiring a cross-media searching result. Due to the adoption of the method, dimensional reduction can be effectively performed for the feature data, so that the feature data can be widely applied to other multi-modal work, for example the multi-modal biological feature recognition.

Description

technical field [0001] The invention relates to the field of pattern recognition and machine learning, in particular to a cross-media retrieval method based on discriminant correlation analysis. Background technique [0002] In recent years, a large amount of multimedia data has shown two obvious characteristics: high dimensionality and multi-source. For example, the same semantic concept can be represented by various contents such as text, pictures, and videos on the Internet. In addition, Internet users mainly search for the information they need through text keywords. This is mainly because search engines cannot understand the relationship between different modal media, thus limiting the development of search engines. Feature dimensionality reduction reveals the manifold structure of high-dimensional data in low-dimensional space and the correlation between different modal data, and plays an important role in information retrieval, pattern classification, information visu...

AI Technical Summary

Problems solved by technology

Some research work pointed out that although nonlinear methods have good performance in processing simulated data, they are not necessarily better than traditional principal component analysis methods for real data, and these methods mentioned above cannot be directly applied to multi-modal cross-media retrieval.

Images