Matlab-vision包学习-Image Registration and Geometric Transformation

在这一篇中，我们将介绍一个新的函数：estimateGeometricTransform，其它的函数都在之前介绍学习过了。

函数/Functions

函数名称：estimateGeometricTransform

功能：利用匹配的特征点对估计几何变换(Similarity,affine,projective transformations)

语法：tform = estimateGeometricTransform(matchedPoints1, matchedPoints2,transformType); 

           [tform,inlierpoints1,inlierpoints2] = estimateGeometricTransform(matchedPoints1, matchedPoints2,transformType); 

            [_,status] = estimateGeometricTransform(matchedPoints1, matchedPoints2,transformType); 

            [ _ ] = estimateGeometricTransform(matchedPoints1, matchedPoints2,transformType,Name,Value); 

其中，matchedPoints1和matchedPoints2分别表示两个图像匹配的对应点；tform是几何变换对象(affine2d object/projective2d object)；transformType是可以取值为’similarity'/'affine'/'projective'，即几何变换的类型；status为返回状态，具体取值如下表；inlierpoints1和inlierpoints2分别为两个图像对应的内点；Name为用一对单引号包含的字符串，Value为对应Name的值。

status及含义status含义0无错误1matchedPoints1 和 matchedPoints2点不足2足够的内点没有发现

Name&Value参数NameValue'MaxNumTrials'默认值为1000，范围为正整数，为了获取最大内点进行随机试验的次数，取较大的值时，能够提高估计的鲁棒性'Confidence'默认值为99，范围为(0,100)，获取最爱内点的置信度，取较大值时能够提高估计的鲁棒性'MaxDistance'默认值为1.5，范围为>0，可以衡量误差

举例：

close all; clear all; clc; % 原图像original = imread('cameraman.tif'); imshow(original); title('Base image'); % 退化图像distorted = imresize(original,0.7); distorted = imrotate(distorted,31); figure; imshow(distorted); title('Transformed image'); % 提取SURF特征点ptsOriginal = detectSURFFeatures(original); ptsDistorted = detectSURFFeatures(distorted); % 获取描述子[featuresOriginal,validPtsOriginal] = extractFeatures(original,ptsOriginal); [featuresDistorted,validPtsDistorted] = extractFeatures(distorted,ptsDistorted);% 描述子匹配index_pairs = matchFeatures(featuresOriginal,featuresDistorted); % 匹配的特征点matchedPtsOriginal = validPtsOriginal(index_pairs(:,1)); matchedPtsDistorted = validPtsDistorted(index_pairs(:,2)); %显示匹配结果figure;showMatchedFeatures(original,distorted,matchedPtsOriginal,matchedPtsDistorted);title('Matched SURF points, including outliers'); %估计几何变换矩阵[tform,inlierPtsDistorted,inlierPtsOriginal] = estimateGeometricTransform(matchedPtsDistorted,matchedPtsOriginal,'similarity'); figure;showMatchedFeatures(original,distorted,inlierPtsOriginal,inlierPtsDistorted); title('Matched inlier points'); %反变换图像 outputView = imref2d(size(original)); Ir = imwarp(distorted,tform,'OutputView',outputView); figure; imshow(Ir); title('Recovered image');