Number Plate Detection

Hey Curious,

here comes the Third “ mini “ project.

This is a Mini project which deals with NLP and Deep Learning and helps to detect the Car Number on Number plate using opencv and imutils

> Imutils are a series of convenience functions to make basic image processing functions such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and both Python 2.7 and Python 3.

Setup instructions :

In order to run this script, You just need the following modules:

1. Opencv :

pip install opencv-python

2. Imutils :

pip install imutils

Inputing the image path

input = 'photo_of_car.png'
image = cv2.imread(input)
cv2.imshow("Input Image", image)
new_width = 500

Resizing the image

image = im.resize(image, width=new_width)

Converting bgr to gray scaling

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

Lets find the boundries of the image or say contours

cnts,hir = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
cnts=sorted(cnts, key = cv2.contourArea, reverse = True)[:10]
NumberPlateCnt = None
print(“Number of Contours found : “ + str(len(cnts)))

here comes the function of the project :

count = 0
for c in cnts:
            peri = cv2.arcLength(c, True)
            epsilon = 0.01 * peri
            approx = cv2.approxPolyDP(c, epsilon, True)
            if len(approx) == 4:
                print(approx)
                NumberPlateCnt = approx
                break

Applying detection to the Function :

cv2.imshow(“Gray scale Image”, gray)
cv2.imshow(“After Applying Bilateral Filter”, filtered_image)
cv2.imshow(“After Canny Edges”, edged)
cv2.drawContours(image, [NumberPlateCnt], -1, (255,0,0), 2)
cv2.imshow(“Output”, image) #getting output image
cv2.waitKey(0)

How to Run the Project :

For .py files:

Get Virinchi-Thinks’s stories in your inbox

Join Medium for free to get updates from this writer.

Remember me for faster sign in

open .py file and install all dependencies

open command prompt by typing cmd at adress bar of folder

type python file_name.py

check for error most of the error will be either for missing libraries or some may be of having no image in such case download similar context image.

for videocapture(0) error : it will only raise if you have another webcam and primary webcam is not working in such case place videocapture(1) and it’ll be running just fine

Output:

To Get more Insightful Content do follow my Instagram Page : click to redirect →

GitHub Code : click to redirect →