Image retrieval method based on CNN (Convolutional Neural Network) feature vocabulary tree

Abstract

The invention discloses an image retrieval method based on a CNN (Convolutional Neural Network) feature vocabulary tree, and aims to solve the technical problem of low accuracy in an existing vocabulary tree method. The method comprises the following implementation steps that: firstly, generating the derivative image of each image in an image library, and extracting the CNN feature of each image in the image library; according to the extracted CNN feature, constructing the CNN feature vocabulary tree; then, generating the derivative image of each image to be retrieved, and extracting the CNN feature of each image to be retrieved; comparing the path of the CNN feature of each image to be retrieved with the path of the CNN feature of the relevant image of the image to be retrieved in the CNN feature vocabulary tree; calculating a distance between the image to be retrieved and the relevant image, and combining the distance between the image to be retrieved and the relevant image with initial similarity; and finally, according to the comprehensive similarity of each image to be retrieved and the relevant image, outputting the retrieval result of each image to be retrieved. The method is high in image retrieval accuracy and can be used for a medical image computer-assisted diagnostic system and a search-by-image system.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image retrieval method, in particular to an image retrieval method based on a CNN feature vocabulary tree. It can be used in medical image computer aided diagnosis system and image search system. Background technique [0002] Image retrieval is the process of comparing the similarity between the description content input by the user and the images in the image library according to a certain similarity comparison mechanism, and returning similar images. With the development of science and technology, the number of images is increasing explosively, and the difficulty of image retrieval is also increasing. [0003] According to the different input description content, image retrieval can be divided into text-based image retrieval and content-based image retrieval. Text-based image retrieval requires a lot of manual labeling, which consumes a lot of manpower and material ...

AI Technical Summary

Problems solved by technology

This method uses the feedback information of user search results to modify the semantic mapping, which improves the accuracy of image retrieval. However, due to the lack of effective user feedback information in practical applications, the actual accuracy of this method is limited. At the same time, the SIFT feature used is a Artificially designed local image descriptors cannot fully describe the high-level semantics of images, and the retrieval accuracy for images with complex content is low

Images