Moroccan License Plate Recognition (LPR) using OpenCV and Tesseract - opencv

Question

I'm working on a project about recognizing moroccan license plates which look like this image :
Moroccan License Plate
Please how can I use OpenCV to cut the license plate out and Tesseract to read the numbers and arabic letter in the middle.
I have looked into this research paper : https://www.researchgate.net/publication/323808469_Moroccan_License_Plate_recognition_using_a_hybrid_method_and_license_plate_features
I have installed OpenCV and Tesseract for python in Windows 10. When I run the tesseract on the text only part of the license plate using "fra" language I get 7714315l Bv. How can I separate the data?
Edit:
The arabic letters we use in Morocco are :
أ ب ت ج ح د هـ
The expected result is : 77143 د 6
The vertical lines are irrelevant, I have to use them to separate the image and read data separately.
Thanks in advance!

Answer 1

You can use HoughTransform since the two vertical lines are irrelevant, to crop the image:
import numpy as np
import cv2
image = cv2.imread("lines.jpg")
grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
dst = cv2.Canny(grayImage, 0, 150)
cv2.imwrite("canny.jpg", dst)
lines = cv2.HoughLinesP(dst, 1, np.pi / 180, 50, None, 60, 20)
lines_x = []
# Get height and width to constrain detected lines
height, width, channels = image.shape
for i in range(0, len(lines)):
l = lines[i][0]
# Check if the lines are vertical or not
angle = np.arctan2(l[3] - l[1], l[2] - l[0]) * 180.0 / np.pi
if (l[2] > width / 4) and (l[0] > width / 4) and (70 < angle < 100):
lines_x.append(l[2])
# To draw the detected lines
#cv2.line(image, (l[0], l[1]), (l[2], l[3]), (0, 0, 255), 3, cv2.LINE_AA)
#cv2.imwrite("lines_found.jpg", image)
# Sorting to get the line with the maximum x-coordinate for proper cropping
lines_x.sort(reverse=True)
crop_image = "cropped_lines"
for i in range(0, len(lines_x)):
if i == 0:
# Cropping to the end
img = image[0:height, lines_x[i]:width]
else:
# Cropping from the start
img = image[0:height, 0:lines_x[i]]
cv2.imwrite(crop_image + str(i) + ".jpg", img)
I am sure you know now how to get the middle part ;)
Hope it helps!
EDIT:
Using some morphological operations, you can also extract the characters individually:
import numpy as np
import cv2
image = cv2.imread("lines.jpg")
grayImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
dst = cv2.Canny(grayImage, 50, 100)
dst = cv2.morphologyEx(dst, cv2.MORPH_RECT, np.zeros((5,5), np.uint8),
iterations=1)
cv2.imwrite("canny.jpg", dst)
im2, contours, heirarchy = cv2.findContours(dst, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_NONE)
for i in range(0, len(contours)):
if cv2.contourArea(contours[i]) > 200:
x,y,w,h = cv2.boundingRect(contours[i])
# The w constrain to remove the vertical lines
if w > 10:
cv2.rectangle(image, (x, y), (x+w, y+h), (0, 0, 255), 1)
cv2.imwrite("contour.jpg", image)
Result:

Answer 2

This what I achieved by now...
The detection on second image was made by using the code found here: License plate detection with OpenCV and Python
Full code (which work from the third image an on) is this:
import cv2
import numpy as np
import tesserocr as tr
from PIL import Image
image = cv2.imread("cropped.png")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow('gray', image)
thresh = cv2.adaptiveThreshold(gray, 250, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 255, 1)
cv2.imshow('thresh', thresh)
kernel = np.ones((1, 1), np.uint8)
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
im2, ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
clean_plate = 255 * np.ones_like(img_dilation)
for i, ctr in enumerate(sorted_ctrs):
x, y, w, h = cv2.boundingRect(ctr)
roi = img_dilation[y:y + h, x:x + w]
# these are very specific values made for this image only - it's not a factotum code
if h > 70 and w > 100:
rect = cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
clean_plate[y:y + h, x:x + w] = roi
cv2.imshow('ROI', rect)
cv2.imwrite('roi.png', roi)
img = cv2.imread("roi.png")
blur = cv2.medianBlur(img, 1)
cv2.imshow('4 - blur', blur)
pil_img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
api = tr.PyTessBaseAPI()
try:
api.SetImage(pil_img)
boxes = api.GetComponentImages(tr.RIL.TEXTLINE, True)
text = api.GetUTF8Text()
finally:
api.End()
# clean the string a bit
text = str(text).strip()
plate = ""
# 77143-1916 ---> NNNNN|symbol|N
for char in text:
firstSection = text[:5]
# the arabic symbol is easy because it's nearly impossible for the OCR to misunderstood the last 2 digit
# so we have that the symbol is always the third char from the end (right to left)
symbol = text[-3]
lastChar = text[-1]
plate = firstSection + "[" + symbol + "]" + lastChar
print(plate)
cv2.waitKey(0)
For arabic symbols you should install additional languages from TesseractOCR (and possibly use the version 4 of it).
Output: 77143[9]6
The number between brackets is the arabic symbol (undetected).
Hope I helped you.