Discover OpenCV to enhance AI in computer vision. Learn image/video processing, editing, and basic machine learning like edge, object, and face detection with real-world projects.

Learn OpenCV from scratch with Python Cover-01.png

opencv.tar.gz

main

OpenCV is an open-source machine learning library for Python that adds enhanced artificial intelligence capabilities in computer vision and image processing.

This course is a comprehensive introduction to building applications using OpenCV, including viewing, identifying, and editing image and video files using Python. You’ll start with an introduction to the library before immediately applying the framework to view images, video, webcam input, and text. You’ll then take your image captures and apply various edits, including decolorization, cropping, resizing, and captioning with layered text and objects. You’ll continue with basic machine learning functions, including edge, object, and face detection. With the basics in hand, you’ll wrap up with real-world projects to build document scanners and object trackers.

By the end of this course, you’ll have a working knowledge of OpenCV and machine learning. You’ll be prepared to build functional applications using the principles of computer vision in Python.

Mastering Computer Vision in Python with OpenCV

Let's look at the correct code for creating the document scanner.

First, we set the size of our document after scanning. 
```
frameWidth = 480
frameHeight = 640
```
## Image Processing
We change the image to grayscale and then make it blurry. This helps us get the edges properly. To get the edges, we use the  `cv2.canny()` function of the OpenCV library:


def imageProcessing(img):
    imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    imgBlur = cv2.GaussianBlur(imgGray,(5,5),1)
    imgCanny = cv2.Canny(imgBlur,200,200)
    return imgCanny

## Get image contours
Next, we define the variable that we’ll use in this function. We define a NumPy array, `biggest`, and an integer, `bArea`. We use the `cv2.findcontours` method to find all the contours:


biggest = np.array([])
bArea = 0
contours,heirarchy = cv2.findContours(img,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)

We loop through all those contours. We use a new function, `cv2.contourArea()`, and give the contours as the parameter to calculate its area. We compare the area value with `5500` to check if it is the area of our document’s contour or not. Then we use the `cv2.arcLength()` function to get the perimeter of our contour. Next, we use the `cv2.approxPolyDP()` function to get the points of the corners of our contour. Finally, we check if the number of the corner points is `4` to assure that we detected a document. Finally, we return the points in the function:


Let's look at the correct code for creating the document scanner.

First, we set the size of our document after scanning. 
```
frameWidth = 480
frameHeight = 640
```
# Image Processing
We change the image to grayscale and then make it blurry. This helps us get the edges properly. To get the edges, we use the  `cv2.canny()` function of the OpenCV library:


# Get image contours
Next, we define the variable that we’ll use in this function. We define a NumPy array, `biggest`, and an integer, `bArea`. We use the `cv2.findcontours` method to find all the contours:


Review the steps of creating a document scanner.

Introduction to Python OpenCV

Read Images, Videos, and Webcam

Editing Images

Reading and Editing Images with OpenCV

Advanced Editings

Detection

Assessment on Advanced Editing and Detection

Real-life projects

Conclusion

Tracking Moving Objects Using Python

A Review of the Document Scanner

Image Processing

Get image contours