我正在寻找一种算法来从边缘检测器的输出中修剪短线段。从下面的图像(和链接)中可以看出,检测到几个不是“长”线的小边缘。理想情况下,我希望在处理后只显示四边形的 4 个边,但如果有几条杂散线,那没什么大不了的……有什么建议吗?
7 回答
在找到边缘之前,使用打开或关闭操作(或两者)对图像进行预处理,即erode后跟dilate,或dilate后跟erode。这应该删除较小的对象,但使较大的对象大致相同。
我在网上找了一些例子,我能找到的最好的是这个PDF 的第 41 页。
我怀疑这可以通过简单的本地操作来完成。查看您要保留的矩形 - 有几个间隙,因此执行局部操作以删除短线段可能会严重降低所需输出的质量。
因此,我会尝试通过关闭间隙、拟合多边形或类似的方式将矩形检测为重要内容,然后在第二步中丢弃剩余的不重要内容。霍夫变换可能会有所帮助。
更新
我刚刚使用带有示例图像的内核霍夫变换使用此示例应用程序,并获得了适合您的矩形的四条漂亮线条。
如果有人踩到这个线程,OpenCV 2.x 会带来一个名为squares.cpp的示例 ,它基本上可以完成这项任务。
我对应用程序进行了轻微修改以改进四边形的检测
代码:
#include "highgui.h"
#include "cv.h"
#include <iostream>
#include <math.h>
#include <string.h>
using namespace cv;
using namespace std;
void help()
{
cout <<
"\nA program using pyramid scaling, Canny, contours, contour simpification and\n"
"memory storage (it's got it all folks) to find\n"
"squares in a list of images pic1-6.png\n"
"Returns sequence of squares detected on the image.\n"
"the sequence is stored in the specified memory storage\n"
"Call:\n"
"./squares\n"
"Using OpenCV version %s\n" << CV_VERSION << "\n" << endl;
}
int thresh = 70, N = 2;
const char* wndname = "Square Detection Demonized";
// helper function:
// finds a cosine of angle between vectors
// from pt0->pt1 and from pt0->pt2
double angle( Point pt1, Point pt2, Point pt0 )
{
double dx1 = pt1.x - pt0.x;
double dy1 = pt1.y - pt0.y;
double dx2 = pt2.x - pt0.x;
double dy2 = pt2.y - pt0.y;
return (dx1*dx2 + dy1*dy2)/sqrt((dx1*dx1 + dy1*dy1)*(dx2*dx2 + dy2*dy2) + 1e-10);
}
// returns sequence of squares detected on the image.
// the sequence is stored in the specified memory storage
void findSquares( const Mat& image, vector<vector<Point> >& squares )
{
squares.clear();
Mat pyr, timg, gray0(image.size(), CV_8U), gray;
// karlphillip: dilate the image so this technique can detect the white square,
Mat out(image);
dilate(out, out, Mat(), Point(-1,-1));
// then blur it so that the ocean/sea become one big segment to avoid detecting them as 2 big squares.
medianBlur(out, out, 3);
// down-scale and upscale the image to filter out the noise
pyrDown(out, pyr, Size(out.cols/2, out.rows/2));
pyrUp(pyr, timg, out.size());
vector<vector<Point> > contours;
// find squares only in the first color plane
for( int c = 0; c < 1; c++ ) // was: c < 3
{
int ch[] = {c, 0};
mixChannels(&timg, 1, &gray0, 1, ch, 1);
// try several threshold levels
for( int l = 0; l < N; l++ )
{
// hack: use Canny instead of zero threshold level.
// Canny helps to catch squares with gradient shading
if( l == 0 )
{
// apply Canny. Take the upper threshold from slider
// and set the lower to 0 (which forces edges merging)
Canny(gray0, gray, 0, thresh, 5);
// dilate canny output to remove potential
// holes between edge segments
dilate(gray, gray, Mat(), Point(-1,-1));
}
else
{
// apply threshold if l!=0:
// tgray(x,y) = gray(x,y) < (l+1)*255/N ? 255 : 0
gray = gray0 >= (l+1)*255/N;
}
// find contours and store them all as a list
findContours(gray, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);
vector<Point> approx;
// test each contour
for( size_t i = 0; i < contours.size(); i++ )
{
// approximate contour with accuracy proportional
// to the contour perimeter
approxPolyDP(Mat(contours[i]), approx, arcLength(Mat(contours[i]), true)*0.02, true);
// square contours should have 4 vertices after approximation
// relatively large area (to filter out noisy contours)
// and be convex.
// Note: absolute value of an area is used because
// area may be positive or negative - in accordance with the
// contour orientation
if( approx.size() == 4 &&
fabs(contourArea(Mat(approx))) > 1000 &&
isContourConvex(Mat(approx)) )
{
double maxCosine = 0;
for( int j = 2; j < 5; j++ )
{
// find the maximum cosine of the angle between joint edges
double cosine = fabs(angle(approx[j%4], approx[j-2], approx[j-1]));
maxCosine = MAX(maxCosine, cosine);
}
// if cosines of all angles are small
// (all angles are ~90 degree) then write quandrange
// vertices to resultant sequence
if( maxCosine < 0.3 )
squares.push_back(approx);
}
}
}
}
}
// the function draws all the squares in the image
void drawSquares( Mat& image, const vector<vector<Point> >& squares )
{
for( size_t i = 1; i < squares.size(); i++ )
{
const Point* p = &squares[i][0];
int n = (int)squares[i].size();
polylines(image, &p, &n, 1, true, Scalar(0,255,0), 3, CV_AA);
}
imshow(wndname, image);
}
int main(int argc, char** argv)
{
if (argc < 2)
{
cout << "Usage: ./program <file>" << endl;
return -1;
}
static const char* names[] = { argv[1], 0 };
help();
namedWindow( wndname, 1 );
vector<vector<Point> > squares;
for( int i = 0; names[i] != 0; i++ )
{
Mat image = imread(names[i], 1);
if( image.empty() )
{
cout << "Couldn't load " << names[i] << endl;
continue;
}
findSquares(image, squares);
drawSquares(image, squares);
imwrite("out.jpg", image);
int c = waitKey();
if( (char)c == 27 )
break;
}
return 0;
}
霍夫变换可能是一项非常昂贵的操作。
以下是可能适用于您的情况的替代方法:
分别使用水平和垂直线(由测试确定的给定长度)结构元素运行 2 个称为图像关闭(http://homepages.inf.ed.ac.uk/rbf/HIPR2/close.htm )的数学形态学运算. 这样做的目的是关闭大矩形中的所有间隙。
运行连通分量分析。如果你有效地完成了形态学,大矩形将作为一个连通分量出现。然后它只继续遍历所有连接的组件并挑选出最有可能的候选者应该是大矩形。
也许找到连接的组件,然后删除小于 X 像素的组件(根据经验确定),然后沿水平/垂直线膨胀以重新连接矩形内的间隙
可以遵循两种主要技术:
基于矢量的操作:将您的像素岛映射到集群(blob、voronoi 区域等)。然后应用一些启发式方法来纠正片段,例如 Teh-Chin 链近似算法,并对矢量元素(开始、端点、长度、方向等)进行修剪。
基于集合的操作:集群您的数据(如上)。对于每个集群,计算主成分并通过查找仅显示 1 个有效特征值的集群(或者如果您寻找可能类似于椭圆的“胖”段,则为 2 个)来从圆形或任何其他形状中检测线。检查与特征值关联的特征向量以获取有关 blob 方向的信息,然后做出选择。
使用 OpenCV 可以轻松探索这两种方式(前者确实属于算法的“轮廓分析”类别)。
这是遵循@Tom10 的简单形态过滤解决方案:
matlab中的解决方案:
se1 = strel('line',5,180); % linear horizontal structuring element
se2 = strel('line',5,90); % linear vertical structuring element
I = rgb2gray(imread('test.jpg'))>80; % threshold (since i had a grayscale version of the image)
Idil = imdilate(imdilate(I,se1),se2); % dilate contours so that they connect
Idil_area = bwareaopen(Idil,1200); % area filter them to remove the small components
这个想法是基本上连接水平轮廓以制作一个大组件,然后通过区域开口过滤器过滤以获得矩形。
结果: