Image registration method based on mutual information and Harris corner point detection

Abstract

The invention discloses an image registration method based on improved mutual information and Harris corner point features. The method mainly solves the problems that through a traditional method, registration consumes much time and registration accuracy is low. The method includes the implementation steps that firstly, an image F to be registered and a reference image R are input; secondly, rectangular frames are placed in any position of the image F to be registered and any position of the reference image R, and most similar rectangular frames are obtained; thirdly, corner point features of the most similar rectangular frames are extracted, and matching points in the similar rectangular frames are obtained; fourthly, the similar rectangular frames on which the matching points are extracted are registered after mismatching points are deleted, and registered transformation parameters are recorded; fifthly, affine transformation is conducted on the image F to be registered through the transformation parameters; sixthly, the image obtained after affine transformation is fused with the reference image R, and then a registered image is obtained. The image registration method has the advantages of being short in consumed registration time and high in registration accuracy, and can be used for registration of medical images, natural images and synthetic aperture radar images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to an image registration method based on improved mutual information and Harris corner detection in the technical field of image registration, which can be used for the purpose of target recognition. Background technique [0002] Intelligent information processing, especially automatic target recognition technology, is a technology for real-time processing of various precision guidance seekers and background signal interference, and is an important symbol of the intelligence of precision guidance weapons. The target recognition of a single image often has a certain degree of randomness and interference, and its reliability and stability are poor, which leads to a decrease in the recognizability and accuracy of the target. Images acquired at different times or locations are registered. [0003] At present, people mostly use image registration methods based on mutual i...

AI Technical Summary

Problems solved by technology

The target recognition of a single image often has a certain degree of randomness and interference, and its reliability and stability are poor, which leads to a decrease in the recognizability and accuracy of the target. Registration of images acquired at different times or locations

[0003] At present, people mostly use image registration methods based on mutual information. This method mainly uses the gray information of the image for registration. This type of method usually has certain defects. For example, the image to be registered contains a large number of In the same area, such as sky, desert, ocean, grassland, etc., no matter how such images are matched, the mutual information value obtained is the largest, and it is difficult to achieve accurate registration

Some existing researchers have proposed an image registration method that combines image feature information with grayscale information. Although this type of method has some improvements over the method of simply using grayscale information for registration, such a method needs to be further improved. Global parameter optimization search, its convergence speed is slow, and the obtained features are greatly affected by noise, resulting in inaccurate registration results and reducing the accuracy of target recognition

Images