Image retrieval method, device, equipment and computer readable storage medium

Abstract

The invention discloses an image retrieval method, a device, equipment and a computer readable storage medium. The method comprises the following steps: respectively extracting contour edges of a to-be-processed image and each to-be-matched image, and equidistantly sampling a plurality of points as shape representations; calculating a shape descriptor of each image in a shape fusion multi-scale space by utilizing a multi-scale height function; wherein the scale height function sub-is a height function descriptor under the action of a morphological scale parameter and a Gaussian smooth scale parameter; based on each shape descriptor, generating a plurality of single-scale retrieval result sets by calculating the shape similarity of the to-be-processed image and each to-be-matched image in asingle-scale space; and setting a new similarity value for each to-be-matched image shape by utilizing a weight assignment function, and determining a retrieval result of the to-be-processed image according to each re-assigned single-scale retrieval result set, so that noise interference, intra-class change and even irregular change shapes can be well processed on the premise of ensuring a high retrieval rate.

Description

technical field [0001] The present invention relates to the technical field of computer vision and image processing, in particular to an image retrieval method, device, equipment and computer-readable storage medium. Background technique [0002] With the rapid development of computer science, communication technology and Internet network, the information society is rapidly popularized and spread. How to effectively acquire and store multimedia materials, and how to quickly and effectively access interesting multimedia information among massive multimedia information is particularly important in the information society. Therefore, information retrieval technology has received extensive research and attention. As the most common type of multimedia information, image information has the characteristics of large information data and low abstraction. How to effectively obtain useful information from massive image information, that is, image information retrieval, is becoming i...

AI Technical Summary

Problems solved by technology

[0006] In the research process of shape matching algorithms at home and abroad, shape contour information is one of the important clues to complete shape recognition, and based on this, a variety of representative shape descriptors are proposed, such as global shape descriptor and local shape Descriptor, the global descriptor has better robustness to local transformation, but it is difficult to obtain important local details of the shape; while the local shape descriptor can accurately represent local features, but it is insufficient in the face of strong noise and local transformation

The related technology generates a series of vectors to describe the shape through the relative spatial distribution (distance and direction) relationship between a certain point of the shape and other contour points. Although it has a strong ability to describe the contour, it is relatively complicated, has poor anti-noise ability, and has low image retrieval accuracy. high

Images