Image matching method based on SIFT features and distortion-preserving mapping

Abstract

The invention discloses an image matching method based on SIFT (scale invariant feature transform) features and distortion-preserving mapping, which belongs to the field of computer image processing and comprises the following steps of: acquiring corresponding feature points between a source image and a target image by using an SIFT algorithm, and taking the corresponding feature points as a candidate matching set; establishing triangular mesh mapping between a source image and a target image according to corresponding feature points in the candidate matching set; adding a distortion-maintaining constraint condition in the triangular mesh mapping; and optimizing an objective function formed by corresponding feature points in the candidate matching set under a distortion-maintaining constraint condition to realize matching between the source image and the target image. According to the invention, the accuracy of image matching is improved.

Description

technical field [0001] The invention relates to the field of computer image processing, in particular to an image matching method based on SIFT features and distortion-preserving mapping. Background technique [0002] Image matching is one of the classic problems in computer vision, and its goal is to find the best feature point correspondence between images. Many existing algorithms are dedicated to solving the problem of image matching, such as image matching methods based on classical descriptors and geometric topological relations, among which methods based on classical descriptors are widely used, including scale-invariant feature transformation algorithms (Scale InvariantFeature Transform, SIFT), Fast Robust Feature Algorithm (Speeded Up Robust Features, SURF), SIFT-based methods and SURF-based methods. [0003] SIFT provides multi-scale matching between images, so that the features remain unchanged when the image is translated, scaled, and rotated. This method is mor...

AI Technical Summary

Problems solved by technology

[0006] However, the feature points detected by the image matching method based on classical descriptors or geometric topological relations are only identifiable feature points in an ideal state. When affected by conditions such as illumination and perspective changes, it is easy to appear a The problem that the feature points in the image are not always uniquely matching the feature points in another image

This defect often leads to suboptimal matching or even wrong matching

Moreover, due to the constraints of image sources and image quality, the performance of these methods and improved methods is not the same for different images, and cannot be suitable for specific application requirements.

Images