点击下方卡片,关注“机器视觉与AI深度学习”
视觉/图像重磅干货,第一时间送达!
导 读
本文主要介绍如何在OpenCV中使用EdgeDrawing模块查找圆(详细步骤 + 代码)。
背景介绍
从OpenCV4.5.2开始,Contrib模块中封装了开源库ED_Lib用于查找图像中的直线、线段、椭圆和圆。Github地址:
https://github.com/CihanTopal/ED_Lib
算法原理简介:
边缘绘制(ED)算法是一种解决边缘检测问题的主动方法。与许多其他遵循减法方法的现有边缘检测算法相比(即在图像上应用梯度滤波器后,根据多种规则消除像素,例如 Canny 中的非极大值抑制和滞后),ED 算法通过加法策略工作,即逐一选取边缘像素,因此称为“边缘绘制”。然后我们处理这些随机形状的边缘段以提取更高级别的边缘特征,即直线、圆、椭圆等。从阈值梯度幅度中提取边缘像素的流行方法是非极大值抑制,它测试每个像素是否具有最大值沿其梯度方向的梯度响应,如果没有则消除。然而,此方法不检查相邻像素的状态,因此可能会导致低质量(在边缘连续性、平滑度、薄度、定位方面)边缘片段。ED 不是非极大值抑制,而是指向一组边缘像素,并通过最大化边缘段的总梯度响应来将它们连接起来。因此,它可以提取高质量的边缘片段,而不需要额外的滞后步骤。
OpenCV中使用介绍文档:
https://docs.opencv.org/4.5.2/d1/d1c/classcv_1_1ximgproc_1_1EdgeDrawing.html
使用步骤
EdgeDrawing类是在Contrib的ximgproc模块中,C++中使用它需要满足以下条件:
① OpenCV >= 4.5.2
② CMake编译Contrib模块
③ 包含edge_drawing.hpp头文件
Python中使用需要安装opencv-python-contrib >=4.5.2
【1】Python中使用演示:
#公众号--OpenCV与AI深度学习
'''
This example illustrates how to use cv.ximgproc.EdgeDrawing class.
Usage:
ed.py [<image_name>]
image argument defaults to board.jpg
'''
# Python 2/3 compatibility
from __future__ import print_function
import numpy as np
import cv2 as cv
import random as rng
import sys
rng.seed(12345)
def main():
try:
fn = sys.argv[1]
except IndexError:
fn = 'board.jpg'
src = cv.imread(cv.samples.findFile(fn))
gray = cv.cvtColor(src, cv.COLOR_BGR2GRAY)
cv.imshow("source", src)
ssrc = src.copy()*0
lsrc = src.copy()
esrc = src.copy()
ed = cv.ximgproc.createEdgeDrawing()
# you can change parameters (refer the documentation to see all parameters)
EDParams = cv.ximgproc_EdgeDrawing_Params()
EDParams.MinPathLength = 50 # try changing this value between 5 to 1000
EDParams.PFmode = False # defaut value try to swich it to True
EDParams.MinLineLength = 20 # try changing this value between 5 to 100
EDParams.NFAValidation = True # defaut value try to swich it to False
ed.setParams(EDParams)
# Detect edges
# you should call this before detectLines() and detectEllipses()
ed.detectEdges(gray)
segments = ed.getSegments()
lines = ed.detectLines()
ellipses = ed.detectEllipses()
#Draw detected edge segments
for i in range(len(segments)):
color = (rng.randint(0,256), rng.randint(0,256), rng.randint(0,256))
cv.polylines(ssrc, [segments[i]], False, color, 1, cv.LINE_8)
cv.imshow("detected edge segments", ssrc)
#Draw detected lines
if lines is not None: # Check if the lines have been found and only then iterate over these and add them to the image
lines = np.uint16(np.around(lines))
for i in range(len(lines)):
cv.line(lsrc, (lines[i][0][0], lines[i][0][1]), (lines[i][0][2], lines[i][0][3]), (0, 0, 255), 1, cv.LINE_AA)
cv.imshow("detected lines", lsrc)
#Draw detected circles and ellipses
if ellipses is not None: # Check if circles and ellipses have been found and only then iterate over these and add them to the image
for i in range(len(ellipses)):
center = (int(ellipses[i][0][0]), int(ellipses[i][0][1]))
axes = (int(ellipses[i][0][2])+int(ellipses[i][0][3]),int(ellipses[i][0][2])+int(ellipses[i][0][4]))
angle = ellipses[i][0][5]
color = (0, 0, 255)
if ellipses[i][0][2] == 0:
color = (0, 255, 0)
cv.ellipse(esrc, center, axes, angle,0, 360, color, 2, cv.LINE_AA)
cv.imshow("detected circles and ellipses", esrc)
cv.waitKey(0)
print('Done')
if __name__ == '__main__':
print(__doc__)
main()
cv.destroyAllWindows()
执行指令:ed.py [<image_name>]
实例1: edge_drawing.py 1.png
实例2: edge_drawing.py 2.png
实例3: edge_drawing.py 3.png
上述图中,绿色表示找到的椭圆,红色表示找到的圆。当然,EdgeDrawing还可以获取边缘信息和查找直线,效果如下:
【2】C++中使用演示:
//公众号--OpenCV与AI深度学习
using namespace std;
using namespace cv;
using namespace ximgproc;
int main()
{
Mat src = imread("./imgs/11.bmp");
if (src.empty())
{
cout << "src image is empty, check again!" << endl;
return -1;
}
//resize(src, src, Size(), 0.2, 0.2);
imshow("src", src);
Mat gray;
cvtColor(src, gray, COLOR_BGR2GRAY);
double start = static_cast<double>(getTickCount()); //计时开始
Ptr<EdgeDrawing> ed = createEdgeDrawing();
ed->params.EdgeDetectionOperator = EdgeDrawing::PREWITT;
ed->params.MinPathLength = 50; // try changing this value between 5 to 1000
ed->params.PFmode = false; //defaut value try to swich it to true
ed->params.MinLineLength = 10; // try changing this value between 5 to 100
ed->params.NFAValidation = false; // defaut value try to swich it to false
ed->params.GradientThresholdValue = 20;
实例1:
实例2:
实例3:
简单总结
总体来说EdgeDrawing提供的找圆和直线的方法简单易用且效果好,简单情况下使用默认参数即可。参数调整可以参考文档自己尝试,这里挑几个常用简单说明一下。
Ptr<EdgeDrawing> ed = createEdgeDrawing();
ed->params.EdgeDetectionOperator = EdgeDrawing::LSD;
ed->params.MinPathLength = 50; // try changing this value between 5 to 1000
ed->params.PFmode = false; //defaut value try to swich it to true
ed->params.MinLineLength = 10; // try changing this value between 5 to 100
ed->params.NFAValidation = true; // defaut value try to swich it to false
ed->params.GradientThresholdValue = 20;
【1】算法使用的梯度算子,可选4种,默认是PREWITT,大家可以设置不同的梯度算子尝试效果。
【2】梯度阈值GradientThresholdValue,值越小,更能找到对比度低的圆。比如下面分别是梯度阈值为100和50的效果:
【3】NFAValidation:默认值为true。指示是否将NFA(错误警报数)算法用于直线和椭圆验证。设置为false时,能找到更多圆或直线。
【4】MinPathLength:最小连接像素长度处理以创建边缘段。在梯度图像中,为创建边缘段而处理的最小连接像素长度。具有高于GradientThresholdValue的值的像素将被处理,默认值为10。比如下面分别是比如下面分别是梯度阈值为50和10的效果(值越小,更小的圆被找到):