Image registration method based on contour detection and feature matching

Abstract

The invention discloses an image registration method based on contour detection and feature matching. The image registration method comprises the following steps that firstly an image to be registered and a standard image are expanded through black/white filling; then threshold segmentation is performed on the image to be registered; then contour detection is performed on a threshold image, and the contour of the image target area is selected as a preliminary contour image; then contour detection is performed on the preliminary contour image from the top to the bottom, and a minimum enclosing rectangle is established; then the absolute value theta of the rotation inclined angle between the top rectangle and the horizontal axis of the anticlockwise direction and the coordinates pt[0], pt[1], pt[2] and pt[3] of the four vertexes are calculated; then the rotation angle is judged to be positive/negative according to pt[0] and pt[1] and then a preliminary registration image is acquired by using affine transformation according to -theta or 90 degrees-theta; and finally matching based on the feature points is performed on the standard image and the preliminary registration image so as to acquire the final registration image. Rapid and high-precision registration of the image of the rotation angle of 0-90 degrees and any translation deviator can be realized so as to meet the requirements of various markets requiring image registration.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image registration method based on contour detection and feature matching. Background technique [0002] Image registration is one of the important tasks of image processing, which is used to geometrically match two or more images acquired at different times, different sensors, different viewing angles and different shooting conditions. It is widely used in computer vision, medical image processing, remote sensing data analysis and other research fields, and has very important research significance and practical value. [0003] Image registration methods are generally divided into two categories: region-based image registration methods and feature-based image registration methods, and region-based registration can be divided into grayscale-based registration and transform domain-based registration. . For image matching with translation, rotation, and scaling types, a single f...

AI Technical Summary

Problems solved by technology

However, the disadvantages of these two algorithms are: there must be an algorithm for removing mismatches, which takes a certain amount of time, and some algorithms for removing mismatches are not effective.

However, the disadvantage of this method is that the value range of the angle must be specified in advance. If the value is only taken at an integer angle, when the rotation angle is a floating point value, the estimation of the angle will be biased. If the value range of the angle is further refinement, it is bound to increase the amount of calculation

Many improved methods based on the above two methods do not take this detail into account, resulting in average registration accuracy and correct rate.

Images