Image retrieval method for cluster-based distance direction histogram

Abstract

The invention discloses an image retrieval method for a cluster-based distance direction histogram, belongs to the technical field of mode recognition and information processing, and relates to large image retrieval in the aspect of computer vision. According to the method, distribution characteristics of local visual features extracted from a training image set are counted; a local visual feature space is divided; the local features are distributed into the nearest sub-region through the distance between descriptors of the local features of a target image and the center of a division space and the consistency between the main direction of the local features and the main direction of the division space, so as to generate an image full-effect expression; and retrieval is carried out by the image full-effect expression, so that the retrieval work of large-scale images can be efficiently finished. A lot of experiments validate that the image retrieval accuracy rate is effectively improved under the condition of a low calculation amount by means of the method; and good expandability is obtained on a large-scale image set.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition and information processing, and relates to massive image retrieval in computer vision. Background technique [0002] With the popularization and development of the Internet and digital photography equipment, images on the Internet have exploded. How to quickly and efficiently obtain images of interest from massive image data is particularly important, attracting the attention of more and more experts and scholars. As the scale of images increases, the difficulty of image retrieval also increases accordingly, which not only requires high retrieval accuracy and efficiency, but also requires as low storage overhead as possible, and at the same time, it is necessary to ensure the scalability of the image retrieval system. Therefore, the large-scale image data and the diversity of its contents increase the need for compact image representation with high recognizability. In order to obtain...

AI Technical Summary

Problems solved by technology

However, during the quantization process of VLAD descriptors, the quantization errors of local descriptors are positive and negative, and may cancel each other out.

At the same time, the VLAD descriptor only uses the descriptor information of local features, while ignoring other useful clues, such as spatial information, which affects its retrieval performance and scalability

Images