Image matching method based on local invariant features

Abstract

The invention provides an image matching method based on local invariant features. The image matching method comprises the steps of: solving a determinant of an integral image and a Hessian matrix foran initial image; establishing a scale spatial pyramid and positioning feature points; determining a principal direction of the feature points by means of Haar wavelets, and completing extraction ofthe feature points; calculating rotation invariant LBP features of an image region around each feature point, and constructing a feature descriptor; completing feature rough matching by utilizing a nearest neighbor method of an Euclidean distance; and eliminating remaining mismatched points after executing the rough matching method by adopting a random sampling consistency method, and completing feature precise matching. According to the image matching method based on the local invariant features, the image has certain robustness when scale, illumination and rotation variations occur in the image under the condition of ensuring the matching time and the correct rate.

Description

technical field [0001] The invention relates to an image feature extraction and image processing method, specifically an image matching method. Background technique [0002] Image matching refers to the image analysis and processing technology that aligns two images containing the same scene and determines the corresponding relationship between them. It is widely used in navigation, map and terrain matching, biometric recognition, text recognition, medical image analysis, computer fields of vision. In practical applications, the images that need to be matched are often obtained by different sensors at different times and under different conditions, and there are differences in translation, scale, rotation, illumination, noise, viewing angle, etc. between them, which give image matching methods posed enormous challenges. The disadvantage of correlation methods based on pixel gray values ​​(such as SSAD, NNPROD, etc.) is that they are sensitive to transformations such as ima...

AI Technical Summary

Problems solved by technology

The SIFT (ScaleInvariant Feature Transform) published on IJCV in 2004 and the SURF based on Hessian matrix and Haar wavelet proposed to improve the running speed of SIFT are the two most representative local feature algorithms in the field of image matching. The problem of changing images is inefficient and the accuracy rate is not very high

[0007] Due to the influence of various geometric and photometric transformations, noise, quantization errors, and similar local structures in images, there may still be wrong matches in the feature matching results based on similarity measures.

Images