图像算法之三：特征提取算子之SIFT

SIFT（Scale-invariant feature transform）是一种检测局部特征的算法，该算法通过求一幅图中的特征点（interest points,or corner points）及其有关scale 和 orientation 的描述子得到特征并进行图像特征点匹配，获得了良好效果，详细解析如下：

1、算法描述

SIFT特征不只具有尺度不变性，即使改变旋转角度，图像亮度或拍摄视角，仍然能够得到好的检测效果。整个算法分为以下几个部分：

（1）构造尺度空间：DoG尺度空间

（2）检测DoG尺度空间极值点

（3）去除不好的特征点

（4）给特征点赋值一个128维的方向参数。每个关键点都包含三个信息：位置、尺度和方向。

（5）关键点描述子的生成：

首先将坐标轴旋转为关键点的方向，以确保旋转不变性。以关键点为中心取8×8的窗口。

（6）最后进行特征匹配。当两幅图像的SIFT特征向量（128维）生成后，采用关键点特征向量的欧式聚类来作为相似性判定度量。

取图像1中的某个关键点，并找出其与图像2中欧式距离最近的前两个关键点，在这两个关键点中，如果最近的距离除以次近的距离少于某个比例阈值，则接受这一对匹配点。降低这个比例阈值，SIFT匹配点数目会减少，但更加稳定。

2、算法实现：

（一） SIFT的Matlab代码实现：

% [image, descriptors, locs] = sift(imageFile)
%
% This function reads an image and returns its SIFT keypoints.
%   Input parameters:
%     imageFile: the file name for the image.
%
%   Returned:
%     image: the image array in double format
%     descriptors: a K-by-128 matrix, where each row gives an invariant
%         descriptor for one of the K keypoints.  The descriptor is a vector
%         of 128 values normalized to unit length.
%     locs: K-by-4 matrix, in which each row has the 4 values for a
%         keypoint location (row, column, scale, orientation).  The
%         orientation is in the range [-PI, PI] radians.
%
% Credits: Thanks for initial version of this program to D. Alvaro and
%          J.J. Guerrero, Universidad de Zaragoza (modified by D. Lowe)

function [image, descriptors, locs] = sift(imageFile)

% Load image
image = imread(imageFile);

% If you have the Image Processing Toolbox, you can uncomment the following
%   lines to allow input of color images, which will be converted to grayscale.
% if isrgb(image)
%    image = rgb2gray(image);
% end

[rows, cols] = size(image);

% Convert into PGM imagefile, readable by "keypoints" executable
f = fopen('tmp.pgm', 'w');
if f == -1
error('Could not create file tmp.pgm.');
end
fprintf(f, 'P5\n%d\n%d\n255\n', cols, rows);
fwrite(f, image', 'uint8');
fclose(f);

% Call keypoints executable
if isunix
command = '!./sift ';
else
command = '!siftWin32 ';
end
command = [command ' <tmp.pgm >tmp.key'];
eval(command);

% Open tmp.key and check its header
g = fopen('tmp.key', 'r');
if g == -1
error('Could not open file tmp.key.');
end
[header, count] = fscanf(g, '%d %d', [1 2]);
if count ~= 2
error('Invalid keypoint file beginning.');
end
num = header(1);
len = header(2);
if len ~= 128
error('Keypoint descriptor length invalid (should be 128).');
end

% Creates the two output matrices (use known size for efficiency)
locs = double(zeros(num, 4));
descriptors = double(zeros(num, 128));

% Parse tmp.key
for i = 1:num
[vector, count] = fscanf(g, '%f %f %f %f', [1 4]); %row col scale ori
if count ~= 4
error('Invalid keypoint file format');
end
locs(i, :) = vector(1, :);

[descrip, count] = fscanf(g, '%d', [1 len]);
if (count ~= 128)
error('Invalid keypoint file value.');
end
% Normalize each input vector to unit length
descrip = descrip / sqrt(sum(descrip.^2));
descriptors(i, :) = descrip(1, :);
end
fclose(g);

使用方法：

1.寻找图像中的sift特征：

[image,descrips,locs] = sift('scene.pgm');
showkeys(image,locs);

scene.pgm



book.pgm

2、对两幅图中的sift特征进行匹配



match(‘scene.pgm’,’book.pgm’);

由于scene和book两幅图中有相同的一本书，但是方向和尺度都不同，从匹配结果可以看出去sift特征匹配检测效果非常好滴！

关于SIFT的其他讲解：

http://blog.csdn.net/abcjennifer/article/details/7639681

http://blog.csdn.net/abcjennifer/article/details/7372880

http://blog.csdn.net/abcjennifer/article/details/7365882

（二）SIFT的Python实现：

import cv2
import numpy as np
import pdb
pdb.set_trace()#turn on the pdb prompt

#read image
img = cv2.imread('E:\OpenCV\Picture\sky.jpg',cv2.IMREAD_COLOR)
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
cv2.imshow('origin',img);

#SIFT
detector = cv2.SIFT() #调用SIFT特征描述子
keypoints = detector.detect(gray,None)#检测兴趣点
img = cv2.drawKeypoints(gray,keypoints)#画出兴趣点
#img = cv2.drawKeypoints(gray,keypoints,flags = cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv2.imshow('test',img);
cv2.waitKey(0)
cv2.destroyAllWindows()

测试：

实验结果：



（三）SIFT的OpenCV实现

#include <opencv2/opencv.hpp>
#include <opencv2/core/core.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
#include <opencv2/features2d/features2d.hpp>
#include <opencv2/legacy/legacy.hpp>
#include <opencv2/nonfree/nonfree.hpp>
#include <vector>
using namespace std;
using namespace cv;
int main(void)
{
cout << "当前使用的OpenCV版本：" << CV_VERSION << endl;
Mat image = imread("scene.pgm");
Mat image2 = imread("book.pgm");
if (image.empty())
{
fprintf(stderr, "Cannot load image %s \n", "scene.pgm");
return -1;
}
if (image2.empty())
{
fprintf(stderr, "Cannot load image %s \n", "book.pgm");
return -1;
}
//显示图像
imshow("image before", image);
waitKey(10);
imshow("image2 before", image2);
waitKey(10);
//sift特征点检测
SiftFeatureDetector siftdtc;
vector<KeyPoint> kp1, kp2;
siftdtc.detect(image, kp1);
Mat outimg1;
drawKeypoints(image, kp1, outimg1);
imshow("image1 keypoints", outimg1);
siftdtc.detect(image2, kp2);
Mat outimg2;
drawKeypoints(image2, kp2, outimg2);
imshow("image2 keypoints", outimg2);
//生成描述子
SiftDescriptorExtractor ext;
Mat descp1, descp2;
BruteForceMatcher<L2<float>> matcher;
vector<DMatch> matches;
Mat img_matches;
ext.compute(image, kp1, descp1);
ext.compute(image2, kp2, descp2);
imshow("desc", descp1);
waitKey(10);
//cout << endl << descp1 << endl;
matcher.match(descp1, descp2, matches);

drawMatches(image, kp1, image2, kp2, matches, img_matches);
imshow("matches", img_matches);
waitKey(10);
//namedWindow("My Image");
//imshow("My Image",image);
//waitKey(0);
//Mat result,image2,image3;
//result = image;
//image2 = result;
//result.copyTo(image3);
//flip(image, result, 1);//正数水平翻转，0表示垂直翻转，负数表示既有水平也有垂直翻转
//namedWindow("Output window");
//imshow("Output window", result);
//namedWindow("1");
//imshow("1", image2);
//namedWindow("2");
//imshow("2", image3);
waitKey(0);
return 0;
}