Iphone 利用霍夫圆检测和测量瞳孔和虹膜
我正在尝试使用OpenCV,更具体地说是它的HoughCircles来检测和测量瞳孔和虹膜,目前我一直在使用函数中的一些变量,因为它要么返回0个圆,要么返回过多的圆。下面是我正在使用的代码和测试图像 测量虹膜的代码:Iphone 利用霍夫圆检测和测量瞳孔和虹膜,iphone,ios,opencv,Iphone,Ios,Opencv,我正在尝试使用OpenCV,更具体地说是它的HoughCircles来检测和测量瞳孔和虹膜,目前我一直在使用函数中的一些变量,因为它要么返回0个圆,要么返回过多的圆。下面是我正在使用的代码和测试图像 测量虹膜的代码: eye1 = [self increaseIn:eye1 Contrast:2 andBrightness:0]; cv::cvtColor(eye1, eye1, CV_RGBA2RGB); cv::bilateralFilter(eye1, eye2, 75, 100, 1
eye1 = [self increaseIn:eye1 Contrast:2 andBrightness:0];
cv::cvtColor(eye1, eye1, CV_RGBA2RGB);
cv::bilateralFilter(eye1, eye2, 75, 100, 100);
cv::vector<cv::Vec3f> circles;
cv::cvtColor(eye2, eye1, CV_RGBA2GRAY);
cv::morphologyEx(eye1, eye1, 4, cv::getStructuringElement(cv::MORPH_RECT,cv::Size(3, 3)));
cv::threshold(eye1, eye1, 0, 255, cv::THRESH_OTSU);
eye1 = [self circleCutOut:eye1 Size:50];
cv::GaussianBlur(eye1, eye1, cv::Size(7, 7), 0);
cv::HoughCircles(eye1, circles, CV_HOUGH_GRADIENT, 2, eye1.rows/4);
eye1 = [self increaseBlackPupil:eye1];
cv::Mat eye2 = cv::Mat::zeros(eye1.rows, eye1.cols, CV_8UC3);
eye1 = [self increaseIn:eye1 Contrast:2 andBrightness:0];
cv::cvtColor(eye1, eye1, CV_RGBA2RGB);
cv::bilateralFilter(eye1, eye2, 75, 100, 100);
cv::threshold(eye2, eye1, 25, 255, CV_THRESH_BINARY);
cv::SimpleBlobDetector::Params params;
params.minDistBetweenBlobs = 75.0f;
params.filterByInertia = false;
params.filterByConvexity = false;
params.filterByCircularity = false;
params.filterByArea = true;
params.minArea = 50;
params.maxArea = 500;
cv::Ptr<cv::FeatureDetector> blob_detector = new cv::SimpleBlobDetector(params);
blob_detector->create("SimpleBlob");
cv::vector<cv::KeyPoint> keypoints;
blob_detector->detect(eye1, keypoints);
eye1=[self-increaseIn:eye1对比度:2,亮度:0];
cv::cvtColor(eye1,eye1,cv_RGBA2RGB);
cv::双边过滤器(eye1,eye2,75100100);
向量圆;
cv::cvtColor(eye2,eye1,cv_RGBA2GRAY);
cv::morphologyEx(eye1,eye1,4,cv::getStructuringElement(cv::MORPH_RECT,cv::Size(3,3));
cv::threshold(eye1,eye1,0,255,cv::THRESH_OTSU);
eye1=[自循环输出:eye1大小:50];
cv::GaussianBlur(eye1,eye1,cv::Size(7,7),0);
cv::HoughCircles(眼睛1,圆圈,cv_HOUGH_渐变,2,眼睛1.rows/4);
测量瞳孔的代码:
eye1 = [self increaseIn:eye1 Contrast:2 andBrightness:0];
cv::cvtColor(eye1, eye1, CV_RGBA2RGB);
cv::bilateralFilter(eye1, eye2, 75, 100, 100);
cv::vector<cv::Vec3f> circles;
cv::cvtColor(eye2, eye1, CV_RGBA2GRAY);
cv::morphologyEx(eye1, eye1, 4, cv::getStructuringElement(cv::MORPH_RECT,cv::Size(3, 3)));
cv::threshold(eye1, eye1, 0, 255, cv::THRESH_OTSU);
eye1 = [self circleCutOut:eye1 Size:50];
cv::GaussianBlur(eye1, eye1, cv::Size(7, 7), 0);
cv::HoughCircles(eye1, circles, CV_HOUGH_GRADIENT, 2, eye1.rows/4);
eye1 = [self increaseBlackPupil:eye1];
cv::Mat eye2 = cv::Mat::zeros(eye1.rows, eye1.cols, CV_8UC3);
eye1 = [self increaseIn:eye1 Contrast:2 andBrightness:0];
cv::cvtColor(eye1, eye1, CV_RGBA2RGB);
cv::bilateralFilter(eye1, eye2, 75, 100, 100);
cv::threshold(eye2, eye1, 25, 255, CV_THRESH_BINARY);
cv::SimpleBlobDetector::Params params;
params.minDistBetweenBlobs = 75.0f;
params.filterByInertia = false;
params.filterByConvexity = false;
params.filterByCircularity = false;
params.filterByArea = true;
params.minArea = 50;
params.maxArea = 500;
cv::Ptr<cv::FeatureDetector> blob_detector = new cv::SimpleBlobDetector(params);
blob_detector->create("SimpleBlob");
cv::vector<cv::KeyPoint> keypoints;
blob_detector->detect(eye1, keypoints);
eye1=[自增黑瞳孔:eye1];
cv::Mat eye2=cv::Mat::zero(eye1.rows,eye1.cols,cv_8UC3);
eye1=[自增强:eye1对比度:2,亮度:0];
cv::cvtColor(eye1,eye1,cv_RGBA2RGB);
cv::双边过滤器(eye1,eye2,75100100);
cv::阈值(eye2,eye1,25,255,cv_THRESH_二进制);
cv::SimpleBlobDetector::Params Params;
params.mindistweenblobs=75.0f;
params.filterByInertia=false;
params.filterByConvexity=false;
params.filterByCircularity=假;
params.filterByArea=true;
参数s.minArea=50;
参数maxArea=500;
cv::Ptr blob_检测器=新的cv::SimpleBlobDetector(参数);
blob_检测器->创建(“SimpleBlob”);
向量关键点;
斑点检测器->检测(眼睛1,关键点);
我知道这张图片很粗糙,我也一直在试图找到一种方法来清理它,使边缘更清晰
所以我的问题很简单:我能做些什么来调整函数HoughCircles中的参数或改变图像以检测虹膜和瞳孔
谢谢好的,不用做太多实验,我的理解是,在使用Hough圆检测器之前,您只对图像应用了双边过滤器 在我看来,您需要在流程中包括阈值步骤 我拍摄了您在帖子中提供的示例图像,并使其经过以下步骤:
cvCvtColor(im_rgb,im_rgb,CV_RGB2GRAY);
形态:
cv::morphologyEx(im_rgb,im_rgb,4,cv::getStructuringElement(cv::MORPH_RECT,cv::Size(size,size)));
阈值:
cv::threshold(im_rgb, im_rgb, low, high, cv::THRESH_OTSU);
霍夫圆检测:
cv::vector<cv::Vec3f> circles;
cv::HoughCircles(im_rgb, circles, CV_HOUGH_GRADIENT, 2, im_rgb.rows/4);
我得到:
"Found 1 cirlces"
希望这能有所帮助。'im_rgb'在您的例子中是'eye1'。对于形态学部分中结构元素的'size',我使用了静态值5作为大小参数。低是0,高是255。阅读本文了解大津阈值:(另请参阅关于大津的维基文章)。我用了im_gray,很抱歉命名不好,忽略这个。。。我将编辑这篇文章。有一个查找连接组件的特定算法,请检查:,从头开始编写代码非常容易。或者,您可以使用openCV作为解决方法,请参见此示例了解如何在openCV中使用CCL的泛洪填充算法:我建议的方法是:查找虹膜(hough圆)->查找虹膜中最大的斑点。