Image retrieval method based on decomposable word pack model

Abstract

The invention provides an image retrieval method based on a decomposable word pack model. The method comprises the following four portions: first, extracting a plurality of features of an image, and separately establishing an index for each feature; second, in view of the indexes in the features, organizing each feature data via the word pack model, clustering the feature data, and using a clustering center as an entry in the word pack model; third, establishing a linear judgment function for the retrieval of the plurality of features, learning significant weights of the features by the least-mean-square-error criterion in a pre-retrieval process, and using the significant weights as coefficients in the linear judgment function; and fourth, independently providing a candidate set of each feature in a retrieval process. The final retrieval results of the plurality of features are clustered by the linear judgment function by using the significant weights of the features. By adoption of the method, high retrieval accuracy can be obtained, and the method is suitable for actual large-scale image retrieval applications.

Description

technical field [0001] The present application relates to an image retrieval method, in particular to an image retrieval method based on a decomposable word bag model, belonging to the fields of computer vision and pattern recognition. Background technique [0002] With the development of multimedia technology, digital images are widely used in the Internet, satellite systems, information management and various monitoring systems because of their intuitive and vivid forms. Under the background of large-scale application of digital images, their number is increasing rapidly. Therefore, in the face of such a huge, real-time expanding, and constantly changing image database, how to effectively organize and manage it, and how to find the desired image in the vast image database has become a research hotspot in related fields. [0003] Aiming at the limitation that the traditional image retrieval based on this article is inefficient and unable to retrieve images at the image con...

AI Technical Summary

Problems solved by technology

For example, the method based on statistical ranking does not consider the retrieval effect of the feature itself, and only uses the simple median as the final retrieval result

[0011] (2) The traditional bag-of-words model cannot adapt to changes in feature types

However, the traditional bag-of-words model cannot cope with the needs of changing feature types.

Images