Rapid and effective image retrieval method under large-scale data background

Abstract

The present invention provides a rapid and effective image retrieval method under a large-scale data background, and belongs to the technical field of computer vision, statistical learning and pattern recognition. First, local features of an image are extracted by using deep convolutional neural networks after transfer learning is performed in a specific task data set, and further the extracted image local features are modeled by using spatial mean pooling and covariance descriptors. The present invention provides an improved maximum likelihood estimation method to robustly estimate the high-dimensional covariance descriptors. The final image expression is obtained by weighted fusion of a spatial mean pooling model and the covariance descriptors. A low-rank measure learning method based on maximum margin subspace is provided to compare image expressions of two images. Dimensions of the image expressions are reduced to improve image matching efficiency, and image matching accuracy can be improved according to prior information of the specific task data set.

Description

technical field [0001] The invention relates to the technical fields of computer vision, statistical learning, and pattern recognition, and proposes a fast and effective image retrieval method applicable to real and complex scenes under the background of large-scale data. Background technique [0002] The early image retrieval technology was mainly based on keyword search. Users can find the corresponding retrieval results in the retrieval database by inputting the description of the query image. With the advent of the Internet and the era of big data, keyword-based image retrieval technology can no longer be applied to massive content and real-time expanded retrieval databases. Therefore, content-based image retrieval technology is widely used in current large-scale search engines. Content-based image retrieval refers to the retrieval technology that the user provides the query image, the retrieval algorithm calculates the image feature expression, searches the similar ima...

AI Technical Summary

Problems solved by technology

Although this method is very efficient, it ignores the spatial position distribution of image local features corresponding to image blocks, and is not robust enough for image retrieval in complex backgrounds.

In addition, simple average aggregation only uses the first-order information of features, and does not consider higher-order representations with richer information, such as second-order covariance descriptor modeling

Images