```
(x1, y1)  (x2, y2)
sqrt((x2-x1)^2 + (y2-y1)^2)
```

This will take the coordinate location to measure the distance between two points. 

University of Michigan - Ann Arbor

OpenCV uses the Shi-Tomasi Good Features to Track and Corner detection algorithm. We are going to want to convert the images into a gray scale object first. This is because the algorithms work significantly better on grey scale images.

```python
img = cv2.imread(`path`)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
corners = cv2.goodFeaturesToTrack(img, N, Q, ME)
```
The N parameter will return the N best guesses of corners. The Q parameter is a cut off on how specific the corner will be. The parameter ranges from 0 to 1 and the closer to 1 the more confident the corner will have to be to be included in the final output. The ME parameter is the minimum Euclidean distance between two corners, this is to prevent it from returning two corners when they are actually the same corner.

The output will be a list of floating point values. 

Corner Detection

Euclidean Distance

Once we are given the numpy array of floating point coordinates for the corners, we would want o convert it from floating points to ints. The ravel method will flatten the array. Flattening an array will remove the interior arrays, [[0,1][2,3]] -> [0,1,2,3].
```python
corners = np.int0(corners)

for corner in corners:
        x,y = corner.ravel()
        cv2,circle(img, (x,y), 5, (255, 0, 0), -1)
```
Remember that if your img file is still in gray scaled the color parameter will not be able to display correctly when drawing the corners.

We can also make these corners more obvious by drawing lines between the corners.
```python
for i in range(len(corners)):
        for j in range(i+1, len(corners)):
                corner1 = tuple(corners[i][0])
                corner2 = tuple(corners[j][0])
                cv2.line(img, corner1, corner2, (255, 0, 0), 1)
```
We will only need the [0] indexing if we don't flatten the array. 

Learn Before

Related