An Image Retrieval Method Based on Deep Convolutional Features and Semantic Similarity Measure

Abstract

The invention relates to an image retrieval method based on deep convolution features and semantic similarity measurement, and belongs to related fields such as computer vision, image processing, and image understanding. First, for the image set, use the trained deep convolutional neural network model to extract the convolutional layer features of each image, aggregate and represent the proposed convolutional layer features, and then use the AFS framework to describe them semantically. On this basis, an image similarity measurement method based on semantic similarity is defined, and the image similarity in the image database is calculated accordingly, and finally the image retrieval task is completed by sorting the similarity. The invention can effectively solve the problem of lack of semantics and low accuracy in the current traditional retrieval method based on the underlying visual features, and better meet the actual needs of users for content-based image retrieval.

Description

technical field [0001] The invention relates to an image retrieval method based on deep convolution features and semantic similarity measurement, and belongs to the technical field of computer image retrieval. Background technique [0002] Content based image retrieval (Content based Image Retrieval, CBIR) has always been one of the research hotspots in the field of computer vision. With the rapid increase of multimedia information in the Internet age, how to quickly and accurately retrieve images that meet user requirements from massive image data covering various contents is a very challenging task. In CBIR, image feature extraction and image similarity measurement are two key links. [0003] In recent years, with the successful application of deep learning technology in the field of image recognition, convolutional neural networks (CNNs) have been used as a feature extraction method to obtain deep convolutional features with high-level semantics, so as to improve the acc...

AI Technical Summary

Problems solved by technology

Obviously, this method only considers the similarity relationship between two images and ignores the similarity structure inside the image, which cannot accurately and comprehensively describe the true similarity between images.

Images