Image-identification random sampling consistency algorithm based on voting decision and least square method

Abstract

An image-identification random sampling consistency algorithm based on a voting decision and a least square method is disclosed. A voting decision mode is introduced so as to find out a point pair which is most possible to be right; and a least square method principle is adopted to calculate a rotation translation transformation matrix. The rotation translation transformation matrix calculated in the invention is accurate and stable, and a calculation speed is fast. Each calculation result is not fluctuated randomly. In the invention, an image comparison method is optimized and the algorithm is good for a subsequent learning function of a data processing chip, which means that characteristic information of a reference image is continuously increased; and false rejection rate is effectively improved and the data processing chip is intelligent. Through continuously updating the rotation translation transformation matrix, image splicing can be high-efficiently and accurately realized.

Description

technical field [0001] The invention relates to a data processing method, in particular to a data processing method for image comparison and image splicing. Background technique [0002] In order to achieve image comparison and image splicing according to the image comparison results, the prior art uses the base image for image comparison as a template image, the image used for comparison as the image to be tested, the template image and the feature points of the image to be tested After the descriptors of the descriptor are matched by Hamming and space de-false, a number of rough matching point pairs are obtained, and the Random Sampling Consensus algorithm, which is abbreviated as RANSAC in English, is used to remove false matches and calculate the rotation-translation transformation matrix. The idea of ​​traditional random sampling consistent RANSAC is to estimate the H matrix by arbitrarily selecting three pairs of points in the coarse matching point pair set, and then u...

AI Technical Summary

Problems solved by technology

[0003] Because the traditional random sampling consistent RANSAC algorithm randomly selects point pairs each time to estimate the H matrix, the randomness is relatively strong, the amount of calculation is large, and the efficiency is low. It needs many iterations to find a suitable H matrix, especially when the input The larger the number of error point pairs in the two matching point sets of the random sampling consistent RANSAC algorithm and the larger the proportion, the greater the number of iterations required, otherwise the H matrix may not be found, but the greater the number of iterations, the greater the number of iterations. The computing time and storage capacity will increase proportionally, and the H matrix and consistent set calculated after each random sampling consistent RANSAC algorithm are not exactly the same

Images