1. 源由

Blob是图像中的一组连接像素，它们共享一些共同特性（例如灰度值）。

在下图中，暗连接区域是斑点，斑点检测旨在识别和标记这些区域。

OpenCV提供了一种基于不同特征检测和过滤斑点的简单方法。

2. blob应用Demo

010_blob_detection是OpenCV通过设置blob参数过滤图像的示例程序。

2.1 C++应用Demo

C++应用Demo工程结构：

010_blob_detection/CPP$ tree . -L 1
.
├── blob.cpp
├── blob.jpg
└── CMakeLists.txt

0 directories, 3 files

确认OpenCV安装路径：

$ find /home/daniel/ -name "OpenCVConfig.cmake"
/home/daniel/OpenCV/installation/opencv-4.9.0/lib/cmake/opencv4/
/home/daniel/OpenCV/opencv/build/OpenCVConfig.cmake
/home/daniel/OpenCV/opencv/build/unix-install/OpenCVConfig.cmake


$ export OpenCV_DIR=/home/daniel/OpenCV/installation/opencv-4.9.0/lib/cmake/opencv4/

C++应用Demo工程编译执行：

$ mkdir build
$ cd build
$ cmake ..
$ cmake --build . --config Release
$ cd ..
$ ./build/blob

2.2 Python应用Demo

Python应用Demo工程结构：

010_blob_detection/Python$ tree . -L 1
.
├── blob.jpg
└── blob.py

0 directories, 2 files

Python应用Demo工程执行：

$ workoncv-4.9.0
$ python blob.py

3. 重点分析

下面是通过params过滤以后，显示blob的代码：

C++:

	// Storage for blobs
	vector<KeyPoint> keypoints;


#if CV_MAJOR_VERSION < 3   // If you are using OpenCV 2

	// Set up detector with params
	SimpleBlobDetector detector(params);

	// Detect blobs
	detector.detect( im, keypoints);
#else 

	// Set up detector with params
	Ptr<SimpleBlobDetector> detector = SimpleBlobDetector::create(params);   

	// Detect blobs
	detector->detect( im, keypoints);
#endif 

	// Draw detected blobs as red circles.
	// DrawMatchesFlags::DRAW_RICH_KEYPOINTS flag ensures
	// the size of the circle corresponds to the size of blob

	Mat im_with_keypoints;
	drawKeypoints( im, keypoints, im_with_keypoints, Scalar(0,0,255), DrawMatchesFlags::DRAW_RICH_KEYPOINTS );

	// Show blobs
	imshow("keypoints", im_with_keypoints );

Python:

# Create a detector with the parameters
ver = (cv2.__version__).split('.')
if int(ver[0]) < 3 :
	detector = cv2.SimpleBlobDetector(params)
else : 
	detector = cv2.SimpleBlobDetector_create(params)


# Detect blobs.
keypoints = detector.detect(im)

# Draw detected blobs as red circles.
# cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS ensures
# the size of the circle corresponds to the size of blob

im_with_keypoints = cv2.drawKeypoints(im, keypoints, np.array([]), (0,0,255), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)

# Show blobs
cv2.imshow("Keypoints", im_with_keypoints)

3.1 Threshold

采样值阈值过滤，在[minThreshold, maxThreshold]之间采用thresholdStep步进方式过滤。

C++:

// Change thresholds
params.minThreshold = 10;
params.maxThreshold = 200;

Python:

# Change thresholds
params.minThreshold = 10
params.maxThreshold = 200

3.2 Area

面积过滤，小于当前面积时，被过滤掉。

C++:

// Filter by Area.
params.filterByArea = true;
params.minArea = 1500;

Python:

# Filter by Area.
params.filterByArea = True
params.minArea = 1500

3.3 Circularity

圆形度过滤，低于阈值被过滤掉(越接近圆的时候，为1)。

C++:

// Filter by Circularity
params.filterByCircularity = true;
params.minCircularity = 0.1;

Python:

# Filter by Circularity
params.filterByCircularity = True
params.minCircularity = 0.1

3.4 Convexity

blob面积和凸包的面积之比(不凹陷的图形该值为1)，因此，凸包越厉害越接近0。

C++:

// Filter by Convexity
params.filterByConvexity = true;
params.minConvexity = 0.87;

Python:

# Filter by Convexity
params.filterByConvexity = True
params.minConvexity = 0.87

3.5 Inertia Ratio

惯性率，通常圆(1)，椭圆(0, 1)，过滤惯性率小于该值的物体。

C++:

// Filter by Inertia
params.filterByInertia = true;
params.minInertiaRatio = 0.01;

Python:

# Filter by Inertia
params.filterByInertia = True
params.minInertiaRatio = 0.01

4. 总结

本文通过对图像进行SimpleBlobDetector操作，从而对blob物体进行过滤，主要目的是理解该对象（SimpleBlobDetector）参数的含义。

• detect(images,keypoints))

• images Image set.
• keypoints The detected keypoints. In the second variant of the method keypoints[i] is a set of keypoints detected in images[i] .

5. 参考资料

【1】ubuntu22.04@laptop OpenCV Get Started
【2】ubuntu22.04@laptop OpenCV安装
【3】ubuntu22.04@laptop OpenCV定制化安装

6. 补充

学习是一种过程，对于前面章节学习讨论过的，就不在文中重复了。

有兴趣了解更多的朋友，请从《ubuntu22.04@laptop OpenCV Get Started》开始，一个章节一个章节的了解，循序渐进。