# [20190602 - Raspberry Pi](https://hackmd.io/s/SkgLJCCnV)
###### tags: `tcfst`
## Author
- Yuan < e61983@gmail.com >
- Wei < demon0303loki@gmail.com >
- Jia-Hao,Hsu < jhs.8901.3737@gmail.com >
## License
## OpenCV
### Install
```shell=
pip install opencv-python
pip install opencv-contrib-python
```
### Example
```python=
import cv2
img = cv2.imread('messi5.jpg',0)
cv2.imshow('image',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
```
### Pkg-Config
```shell=
pkg-config --cflags
pkg-config --libs
pkg-config --static
```
#### Check Version
```
pkg-config --modversion opencv
```
#### Reference
- [pkg-config 教學][pkg-conifg 教學]
## OpenCV - USB CAM
### Install
- Python library
```shell=
sudo apt install python-opencv
```
- C library
```shell=
sudo apt install libopencv-dev
```
### Example
- Using C++
```cpp=
#include "opencv2/opencv.hpp"
using namespace cv;
int main(int, char**)
{
VideoCapture cap(0); // open the default camera
if(!cap.isOpened()) // check if we succeeded
return -1;
Mat edges;
namedWindow("edges",1);
for(;;)
{
Mat frame;
cap >> frame; // get a new frame from camera
cvtColor(frame, edges, COLOR_BGR2GRAY);
GaussianBlur(edges, edges, Size(7,7), 1.5, 1.5);
Canny(edges, edges, 0, 30, 3);
imshow("edges", edges);
if(waitKey(30) >= 0) break;
}
// the camera will be deinitialized automatically in VideoCapture destructor
return 0;
}
```
- Using Python
```python=
import cv2
cap = cv2.VideoCapture(0)
while(True):
ret, frame = cap.read()
cv2.imshow('frame', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
```
#### Reference
- [Official][Official-opencv]
## Canny-Edge Detection
- Introduce
```
1. Noise Reduction
2. Finding Intensity Gradient of the Image
3. Non-maximum Suppression
4. Hysteresis Thresholding
```
- Using Python
```python=
import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('messi5.jpg',0)
edges = cv2.Canny(img,100,200)
plt.subplot(121),plt.imshow(img,cmap = 'gray')
plt.title('Original Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(edges,cmap = 'gray')
plt.title('Edge Image'), plt.xticks([]), plt.yticks([])
plt.show()
```
- Using C++
```cpp=
#include <cstdio>
#include <opencv2/opencv.hpp>
using namespace cv;
int main(){
Mat src = imread("lena.jpg", CV_LOAD_IMAGE_GRAYSCALE);
GaussianBlur(src, src, Size(3,3), 0, 0);
Mat dst1, dst2;
Canny(src, dst1, 50, 150, 3);
threshold(dst1, dst2, 128, 255, THRESH_BINARY_INV);
imshow("origin", src);
imshow("Canny_1", dst1);
imshow("Canny_2", dst2);
waitKey(0);
return 0;
}
```
## Image Filtering
### Filter2D()
OpenCV 提供 filter2D() 函式方便濾波計算，我們依濾波值定義一個核矩陣，之後呼叫 filter2D 函式時輸入此核心矩陣當參數。
- C language
```c=
void cvFilter2D( const CvArr* src, // 輸入
CvArr* dst, // 輸出
const CvMat* kernel, // 核心
CvPoint anchor=cvPoint(-1,-1) // 錨點
)
```
- python
```python=
cv.Filter2D(src, dst, kernel, anchor=(-1, -1))
```
### Kernel
本質上是固定大小的數值係數陣列以及該陣列中的錨點，其通常位於中心。
我們可以藉由此陣列來進行線性慮波。
#### Reference
- [Making your own linear filters!][opencv-kernel]
### Blurring
- Using Python
```python=
import cv2
import numpy as np
from matplotlib import pyplot as plt
img = cv2.imread('opencv_logo.png')
kernel = np.ones((5,5),np.float32)/25
dst = cv2.filter2D(img,-1,kernel)
plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(dst),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.show()
```
### Sharpen
- Using C++
```cpp=
#include <cstdio>
#include <opencv2/opencv.hpp>
using namespace cv;
void sharpen(const Mat &src, Mat &dst)
{
Mat kernel(3,3,CV_32F,Scalar(0));
kernel.at<float>(1,1) = 5.0;
kernel.at<float>(0,1) = -1.0;
kernel.at<float>(2,1) = -1.0;
kernel.at<float>(1,0) = -1.0;
kernel.at<float>(1,2) = -1.0;
filter2D(src,dst,src.depth(),kernel);
}
int main()
{
Mat src = imread("lena.jpg",CV_LOAD_IMAGE_UNCHANGED);
Mat dst;
sharpen(src, dst);
namedWindow("window1");
imshow("window1", src);
imshow("window2", dst);
waitKey(0);
return 0;
}
```
### Reference
- [Official Document - Image Filter][opencv-image-filter]
## Morphological (形態學)
- Erode (浸蝕)
```python=
import cv2
import numpy as np
img = cv2.imread('j.png',0)
kernel = np.ones((5,5),np.uint8)
erosion = cv2.erode(img,kernel,iterations = 1)
```
- Dilate (膨脹)
```python=
import cv2
import numpy as np
img = cv2.imread('j.png',0)
kernel = np.ones((5,5),np.uint8)
dilation = cv2.dilate(img,kernel,iterations = 1)
```
- open
先 Erode (浸蝕) 再 Dilate (膨脹)，用來消除噪點。
```python=
import cv2
import numpy as np
img = cv2.imread('j.png',0)
kernel = np.ones((5,5),np.uint8)
opening = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
```
- close
與 open 相反，先 Dilate (膨脹) 再 Erode (浸蝕)，用來消除物件內的噪點。
```python=
import cv2
import numpy as np
img = cv2.imread('j.png',0)
kernel = np.ones((5,5),np.uint8)
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
```
### Reference
- [opencv-morphological API]
## Color Detection
- [opencv-color API]
## Find contours
- [opencv-findContours API]
## 梗區
>高斯濾波是低通濾波
>[name= 李老師]
>> 其實沒錯啦
>> Since the Fourier transform of a Gaussian is another Gaussian, applying a Gaussian blur has the effect of reducing the image's high-frequency components; a Gaussian blur is thus a low pass filter.
>作業一: 使用openCV 設計一個追蹤三個顏色的程式~~
>[name=~~Linux Driver課程~~]
## 場外
LOL 這裡有筆記機器人 打完標題 內容就會自己產生!!
新的 人工智慧!!
太神啦!
聽他講影像辨識 讓我想起了阿烈跟世勳的好
他的教材我都還有留著XD
+1 雖然阿烈的版本沒有教材XD
> 大會廣播: 筆記機器人服務將於30分鐘後結束
> 我看成教育機器人
> 延長三小時要付費多少
其實可以先只放標題~~ 內容什麼的~~彈個手指~~就有了XD
原來是個姓薩的機器人還是姓道尼的
<img style="width:40%; height:auto;" src="https://i.imgur.com/YIJlRYc.jpg" >
>~~少三顆寶石 抓到!!!~~ 少四顆才對 大拇指不知道有沒有XD
>>所以才會暫停服務啊~XDD
>是說~~只有Tony 才有機器人啊!!
所以 老賈 是你!! 剛好還有一顆在頭上 變成三顆寶石了XD
[pkg-conifg 教學]:
https://jyhshin.pixnet.net/blog/post/26588033
[Official-opencv]:
https://docs.opencv.org/3.0-beta/modules/videoio/doc/reading_and_writing_video.html
[opencv-color API]:
https://docs.opencv.org/3.0-beta/modules/imgproc/doc/miscellaneous_transformations.html#cvtcolor
[opencv-morphological API]:
https://docs.opencv.org/3.0-beta/modules/imgproc/doc/filtering.html#dilate
[opencv-findContours API]:
https://docs.opencv.org/3.0-beta/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html?highlight=findcon#cv2.findContours
[opencv-image-filter]:
https://docs.opencv.org/2.4/modules/imgproc/doc/filtering.html
[OpenCV-Document]:
https://docs.opencv.org/3.3.1/d4/d73/tutorial_py_contours_begin.html
[opencv-kernel]:
https://docs.opencv.org/2.4/doc/tutorials/imgproc/imgtrans/filter_2d/filter_2d.html
Sign in with Wallet
Connect another wallet