一个 Dense SIFT 算法的 matlab 实现

      Ce Liu, Jenny Yuen, Antonio Torralba,JosefSivic, andWilliam T. Freeman 版权所有。

      修改的部分函数与变量的名字，使其好懂了一些。不过这个算法由于没有salient keypoint detection和rotation normalization，所以对尺度以及旋转这些affine transform没有移不变的性质。

function [ SIFTFeatureVector, locationX, locationY ] = DenseSIFT( image, nPatchSize, nGridSpacing )

image = double( image );
image = mean( image, 3 );
image = image / max( image( : ) );

% parameters
nAngleNums = 8;
nBinNums = 4;
nSampleNums = nBinNums * nBinNums;
alpha = 9; %% parameter for attenuation of angles (must be odd)

if nargin < 5
    sigmaGuassian = 1;
end

angleStep = 2 * pi / nAngleNums;
angles = 0 : angleStep : 2 * pi;
angles( nAngleNums + 1 ) = [ ]; % bin centers

[ nRow nCol ] = size( image );

[ gaussianX, gaussianY ] = genDeltaGaussian( sigmaGuassian );
imageVerticalEd