An Efficient Image Retrieval Method Based on Improved SIFT Features

Abstract

The invention discloses an efficient image retrieval method based on an improved SIFT (scale invariant feature transform) feature, relates to the field of image processing and computer vision and belongs to a content-based image retrieval method. The method comprises the steps of establishing a gauss difference scale space, taking scale space detection extreme points as feature points, calculating the direction of the feature points and gradient module values in the direction, generating a global feature vector of the image feature points through a geographical statistical method, conducting global feature vector similarity matching to finish rough retrieval, generating feature descriptors on the basis of rough retrieval, and conducting feature descriptor matching to finish accurate retrieval. The novel image retrieval method is superior to a traditional SIFT algorithm, and is more suitable for requirements of image infringement examination in digital prints than an existing retrieval algorithm.

Description

Technical field [0001] The invention relates to the field of image processing and computer vision, and belongs to a content-based image retrieval method. technical background [0002] With the rapid development of high and new technology such as computer technology, communication technology, network technology, streaming media technology, and storage technology, digital publishing has flourished and has become a strategic emerging industry in the press and publishing industry and the main direction of the publishing industry. At the same time, the protection of intellectual property rights brought about by digital publishing has attracted great attention from the society. If the review of copyright issues is not comprehensive or in-depth, it will most likely lead to copyright disputes after the spread of digital publications. Therefore, the review of infringement issues before the publication of digital publications has become an important task for digital publishing houses. In ...

AI Technical Summary

Problems solved by technology

The SIFT feature satisfies the robustness requirements of image retrieval based on the copyright review of digital publications, but the SIFT feature also has many shortcomings, such as the complexity of the algorithm, the number of extracted feature points is too large, and the template is too large , takes up too much memory; a 128-dimensional feature descriptor is generated when the feature descriptor is generated, and the calculation time is long; after the SIFT algorithm matching is completed, there is a mismatch of feature points

Images