mil*_*n m 3 c++ opencv surf sift
我正在学习OpenCV,并开始探索用于图像匹配的SURF算法.我通过修改Microsoft Windows 7提供的默认图像创建了一个示例图像库.
每个图像在同一文件夹中都有旋转,缩放,模糊和倾斜的版本.
我找到匹配图像的代码如下所示.从代码中可以看出,距离是由行dis/objectDescriptors-> total测量的,并且进一步的相似度由100 - (dis/objectDescriptors-> total)*100计算.
不幸的是,这给了我一些奇怪的误报.例如,它将image1与完全不同的image2(85%相似度)匹配,但与image1的轻微模糊版本仅显示60%的相似度.
我如何摆脱误报？
以下代码的灵感来自网站:http://opencvuser.blogspot.in/2012/07/surf-source-code-part-2.html
#include <cv.h>
#include <highgui.h>
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <iostream>
#include <vector>
using namespace std;
static double dis=0;//For calculating the distance
IplImage *image = 0;
double
compareSURFDescriptors( const float* d1, const float* d2, double best, int length )
{
double total_cost = 0;
assert( length % 4 == 0 );
for( int i = 0; i < length; i += 4 )
{
double t0 = d1[i] - d2[i];
double t1 = d1[i+1] - d2[i+1];
double t2 = d1[i+2] - d2[i+2];
double t3 = d1[i+3] - d2[i+3];
total_cost += t0*t0 + t1*t1 + t2*t2 + t3*t3;
if( total_cost > best )
break;
}
return total_cost;
}
int
naiveNearestNeighbor( const float* vec, int laplacian,
const CvSeq* model_keypoints,
const CvSeq* model_descriptors )
{
int length = (int)(model_descriptors->elem_size/sizeof(float));
int i, neighbor = -1;
double d, dist1 = 1e6, dist2 = 1e6;
CvSeqReader reader, kreader;
cvStartReadSeq( model_keypoints, &kreader, 0 );
cvStartReadSeq( model_descriptors, &reader, 0 );
for( i = 0; i < model_descriptors->total; i++ )
{
const CvSURFPoint* kp = (const CvSURFPoint*)kreader.ptr;
const float* mvec = (const float*)reader.ptr;
CV_NEXT_SEQ_ELEM( kreader.seq->elem_size, kreader );
CV_NEXT_SEQ_ELEM( reader.seq->elem_size, reader );
if( laplacian != kp->laplacian )
continue;
d = compareSURFDescriptors( vec, mvec, dist2, length );
if( d < dist1 )
{
dist2 = dist1;
dist1 = d;
neighbor = i;
}
else if ( d < dist2 )
dist2 = d;
}
dis=dis+dist1;
/*We are finding the distance from every descriptor of probe image to every descriptor of the galley image. Finally in the findpairs function, we divide this distance with the total no. of descriptors to get the average of all the distances
*/
if ( dist1 < 0.6*dist2 )
return neighbor;
return -1;
}
void
findPairs( const CvSeq* objectKeypoints, const CvSeq* objectDescriptors,
const CvSeq* imageKeypoints, const CvSeq* imageDescriptors, vector<int>& ptpairs )
{
int i;
CvSeqReader reader, kreader;
cvStartReadSeq( objectKeypoints, &kreader );
cvStartReadSeq( objectDescriptors, &reader );
ptpairs.clear();
for( i = 0; i < objectDescriptors->total; i++ )
{
const CvSURFPoint* kp = (const CvSURFPoint*)kreader.ptr;
const float* descriptor = (const float*)reader.ptr;
CV_NEXT_SEQ_ELEM( kreader.seq->elem_size, kreader );
CV_NEXT_SEQ_ELEM( reader.seq->elem_size, reader );
int nearest_neighbor = naiveNearestNeighbor( descriptor, kp->laplacian, imageKeypoints, imageDescriptors);
//For every descriptor, we are trying to find it's nearest neighbour in the probe image
if( nearest_neighbor >= 0 )
{
ptpairs.push_back(i);
ptpairs.push_back(nearest_neighbor);
}
}
printf("\n%lf\n",(dis/objectDescriptors->total));////Here's where I am outputting the distance between the images
/*Dileep: If you are using this for recognition, write this distance to a file along with the name of the image you are matching against. After doing this for several images, you can then sort them in ascending order to find the best possible match - the one with the smallest distance. Here, I am outputting the distance to stdout
*/
}
int main(int argc, char** argv)
{
const char* object_filename = argc == 3 ? argv[1] : "box.png";
const char* scene_filename = argc == 3 ? argv[2] : "box_in_scene.png";
//Dileep:When you are excuting the object file, please write Command:./objectfile probe_image Gallery_image
/*Dileep:
Probe_image - This is the image for which you need to find the match
Gallery_image - This is one of the set of images, you use for matching
You keep the same probe image same, repeatedly changing the gallery image and outputting the distance in the format
<Gallery_name distance> into a file
Finally you can sort the distances in ascending order. And the one with the shortest distance - You can output it's name as the best possible match
It may become tedious to continually write the same command multiple times, changing the gallery file name. Try to use shell script with a for loop
*/
CvMemStorage* storage = cvCreateMemStorage(0);
IplImage* object = cvLoadImage( object_filename, CV_LOAD_IMAGE_GRAYSCALE );
IplImage* image = cvLoadImage( scene_filename, CV_LOAD_IMAGE_GRAYSCALE );
if( !object || !image )
{
fprintf( stderr, "Can not load %s and/or %s\n"
"Usage: find_obj [<object_filename> <scene_filename>]\n",
object_filename, scene_filename );
exit(-1);
}
CvSeq *objectKeypoints = 0, *objectDescriptors = 0;
CvSeq *imageKeypoints = 0, *imageDescriptors = 0;
int i;
CvSURFParams params = cvSURFParams(500, 1);
double tt = (double)cvGetTickCount();
cvExtractSURF( object, 0, &objectKeypoints, &objectDescriptors, storage, params );
printf("Object Descriptors: %d\n", objectDescriptors->total);
cvExtractSURF( image, 0, &imageKeypoints, &imageDescriptors, storage, params );
printf("Image Descriptors: %d\n", imageDescriptors->total);
tt = (double)cvGetTickCount() - tt;
printf( "Extraction time = %gms\n", tt/(cvGetTickFrequency()*1000.));
vector<int> ptpairs;
findPairs( objectKeypoints, objectDescriptors, imageKeypoints, imageDescriptors, ptpairs );
return 0;
}
请记住,通常的管道是这样的:
您已完成步骤1和2,但缺少3个.请注意,推定的对应关系非常嘈杂.你将获得许多通信,其中许多错误,但有些正确.通过绘制它们很难确定它们是否正确计算.所以,你看到很明显的对应关系是很正常的.
要做第3步,在你的情况下你可以找到与RANSAC的单应性,正如@ user3481173所说.这很容易,因为OpenCV已经提供了cvFindHomography同时完成这两件事的功能.单应性在你的情况下应该很好,因为你正在处理平面图像的透视变换.
顺便说一下,将来使用OpenCV的C++ API将会容易得多.相同的代码可能会占用你一半的行数.