I need a hand to be able to fix my project with opencv, which consists in detecting plates and using tesseract to extrapolate the content, but I don't understand why only the text written on a white background detects me and not when I use a real plate. I tried to arrange the image in order to make it more legible and maybe frame only the white part of the European license plates in order to simplify the extrapolation of the text, but nothing I can not isolate only the white. I using a raspberry pi 4, i don't know if it can be useful
Could anyone help me? Many thanks in advance.
print("Aspetta 5 secondi per catturare l'immagine, oppure premi <space> per scattare...")
cam = cv2.VideoCapture(0)
num_frames = 0
while True:
ret, image = cam.read()
if not ret:
print("La webcam non funziona...")
sys.exit(1)
cv2.imshow('image', image)
# Catturo l'immagine se premo <space>
if (cv2.waitKey(1) & 0xFF) == ord(' '):
break
# Aspetto 5 secondi prima di catturare l'immagine
num_frames += 1
if num_frames / 10 == 5:
break
cam.release()
cv2.destroyAllWindows()
cv2.imwrite("/home/pi/Desktop/Riconoscimento Targa/imagee.jpg", image)
filename = 'imagee.jpg'
img = np.array(Image.open(filename))
img = cv2.resize(img, (600,400) )
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = cv2.bilateralFilter(gray, 13, 15, 15)
edged = cv2.Canny(gray, 30, 200) #Perform Edge detection
contours=cv2.findContours(edged.copy(),cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
contours = sorted(contours,key=cv2.contourArea, reverse = True)[:10]
screenCnt = None
for c in contours:
# approximate the contour
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.018 * peri, True)
# if our approximated contour has four points, then
# we can assume that we have found our screen
if len(approx) == 4:
screenCnt = approx
break
# Masking the part other than the number plate
mask = np.zeros(gray.shape,np.uint8)
new_image = cv2.drawContours(mask,[screenCnt],0,255,-1,)
new_image = cv2.bitwise_and(img,img,mask=mask)
# Now crop
(x, y) = np.where(mask == 255)
(topx, topy) = (np.min(x), np.min(y))
(bottomx, bottomy) = (np.max(x), np.max(y))
Cropped = gray[topx:bottomx+1, topy:bottomy+1]
cv2.imwrite("/home/pi/Desktop/Riconoscimento Targa/Da eliminare.jpg", Cropped)
text = pytesseract.image_to_string(Cropped, config='--psm 11 -l ita')
return text
Related
I am using tesseract 5.3.0 With the code below I am able to identify the licence plate and mask it out, however when I resize the licence plate part does not increase. How do I grab just the licence portion and increase it? Any tips on reading the licence plate would also be appreciated.
import cv2
import numpy as np
import imutils
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'/usr/local/bin/tesseract'
# Load the image and convert it to grayscale
image = cv2.imread('/Users/PythonProg/IMG_4592.JPG')
if image is None:
print("Error: Could not load the image")
exit()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Apply Gaussian Blur to reduce noise and smooth the image
gray = cv2.bilateralFilter(gray, 13, 15, 15)
edged = cv2.Canny(gray, 30, 200)
contours = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
contours = sorted(contours, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None
# Loop over the contours and find the one with the largest area
licence_plate = None
for c in contours:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.018 * peri, True)
if len(approx) == 4:
screenCnt = approx
break
if screenCnt is None:
detected = 0
print ("No contour detected")
else:
detected = 1
if detected == 1:
cv2.drawContours(image, [screenCnt], -1, (0, 0, 255), 3)
cv2.imwrite('/Users/PythonProg/output.jpg', image)
mask = np.zeros(gray.shape,np.uint8)
licence_plate = cv2.drawContours(mask,[screenCnt],0,255,-1,)
licence_plate = cv2.bitwise_and(image,image,mask=mask)
cv2.imwrite('/Users/anthonywilson/PythonProg/mask.jpg', licence_plate)
# Resize the masked image to a specific size
resized = cv2.resize(licence_plate, (400, 200), interpolation = cv2.INTER_AREA)
# Save the resized image
cv2.imwrite('/Users/PythonProg/resized.jpg', resized)
Im trying to save only the rectangular ROI region from a video file into images. But the entire image is getting saved with the RED rectangular ROI box on it. What am I doing wrong here ?
I tried saving rect_img but thats giving error "!_img.empty() in function 'imwrite'" ,
and not saving any images at all.
The upper_left and bottom_right coordinates are for a 1920 X 1080p video, you wil have to adjust is as per your video resolution.
import cv2
from matplotlib import pyplot as plt
import imutils
import numpy as np
import pytesseract
cam_capture = cv2.VideoCapture('1080_EDIT.webm')
upper_left = (1400, 700)
bottom_right = (700, 1000)
ctr=1 #filename counter
while True:
_, image_frame = cam_capture.read()
ctr+=1
#Rectangle marker
r = cv2.rectangle(image_frame, upper_left, bottom_right, (100, 50, 200), 5)
rect_img = image_frame[upper_left[1] : bottom_right[1], upper_left[0] : bottom_right[0]]
cv2.imwrite("rect"+str(ctr)+".jpg",r)
#print (rect_img)
#img=cv2.imread(rect_img)
gray = cv2.cvtColor(r, cv2.COLOR_BGR2GRAY)
gray = cv2.bilateralFilter(gray, 13, 15, 15)
edged = cv2.Canny(gray, 30, 200)
contours = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
contours = sorted(contours, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None
for c in contours:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.018 * peri, True)
if len(approx) == 4:
screenCnt = approx
break
if screenCnt is None:
detected = 0
print ("No contour detected")
else:
detected = 1
if detected == 1:
cv2.drawContours(r, [screenCnt], -1, (0, 0, 255), 3)
cv2.imshow("image", image_frame)
if cv2.waitKey(1) % 256 == 27 :
break
cam_capture.release()
cv2.destroyAllWindows()
Solved it by
roi=r[700:1000,700:1400]
cv2.imwrite("rect"+str(ctr)+".jpg",roi)
I have an image that converted from PDF to PNG. The converted image contains several keywords that I wanted to extracted using OCR Tesseract.
Right now, I need to determine the ROI manually to crop the selected ROI. Since I have more than 5 ROI's to be applied, what would be the most efficient way to apply the ROI instead of doing it by try and error to find the exact location?
Below is the code:
def cropped(self, event):
#1st ROI
y = 20
x = 405
h = 230
w = 425
#2nd ROI
y1 = 30
x1 = 305
h1 = 330
w1 = 525
#open the converted image
image = cv2.imread("Output.png")
#perform image cropping
crop_image = image[x:w, y:h]
crop_image1 = image[x1:w1, y1:h1]
#save the cropped image
cv2.imwrite("Cropped.png", crop_image)
cv2.imwrite("Cropped1.png", crop_image1)
#open the cropped image and pass to the OCR engine
im = cv2.imread("Cropped.png")
im1 = cv2.imread("Cropped1.png")
## Do the text extraction here
you can use mouse event to select multiple ROI and crop based on the location
#!/usr/bin/env python3
import argparse
import cv2
import numpy as np
from PIL import Image
import os
drawing = False # true if mouse is pressed
ix,iy = -1,-1
refPt = []
img = ""
clone = ""
ROIRegion = []
# mouse callback function
def draw_rectangle(event,x,y,flags,param):
global ix,iy,drawing,img,clone,refPt, ROIRegion
if event == cv2.EVENT_LBUTTONDOWN:
drawing = True
ix,iy = x,y
refPt = [(x, y)]
ROIRegion.append(refPt)
#clone = img.copy()
elif event == cv2.EVENT_MOUSEMOVE:
if drawing == True:
img = clone.copy()
cv2.rectangle(img,(ix,iy),(x,y),(0,255,0),3)
a=x
b=y
if a != x | b != y:
cv2.rectangle(img,(ix,iy),(x,y),(0,0,0),-1)
elif event == cv2.EVENT_LBUTTONUP:
drawing = False
refPt.append((x,y))
img = clone.copy()
cv2.rectangle(img, (ix,iy),(x,y), (0, 255, 0), 2)
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True, help="Path to the image")
args = vars(ap.parse_args())
# load the image, clone it, and setup the mouse callback function
img = cv2.imread(args["image"])
img = np.array(img)
clone = img.copy()
cv2.namedWindow('image')
cv2.setMouseCallback('image',draw_rectangle)
while(1):
cv2.imshow('image',img)
k = cv2.waitKey(1) & 0xFF
if k == ord("r"):
del ROIRegion[-1]
del refPt[-1]
img = clone.copy()
elif k == 27:
break
#Do your cropping here
for region in range(len(ROIRegion)):
cv2.rectangle(img, ROIRegion[region][0],ROIRegion[region][1], (0, 255, 0), 2)
roi = clone[ROIRegion[region][0][1]:ROIRegion[region][1][1], ROIRegion[region][0][0]:ROIRegion[region][1][0]]
roi = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
Here is one way in Python/OpenCV.
Read the input
Threshold on box outline color
Apply morphology to ensure closed
Get the external contours
Loop over each contour, get its bounding box, crop the region in the input and write the output
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('text_boxes.jpg')
# threshold on box outline color
lowerBound = (80,120,100)
upperBound = (160,200,180)
thresh = cv2.inRange(img, lowerBound, upperBound)
# apply morphology to ensure regions are filled and remove extraneous noise
kernel = np.ones((3,3), np.uint8)
thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# get contours
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# get bounding boxes
i = 1
for cntr in contours:
# get bounding boxes
x,y,w,h = cv2.boundingRect(cntr)
crop = img[y:y+h, x:x+w]
cv2.imwrite("text_boxes_crop_{0}.png".format(i), crop)
i = i + 1
# save threshold
cv2.imwrite("text_boxes_thresh.png",thresh)
# show thresh and result
cv2.imshow("thresh", thresh)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold image:
Cropped Images:
I have a code that gets a video from a folder and does some calculations using contours and background subtraction. After that I am going to save that edited video into the folder. The code is shown below:
import numpy as np
import cv2
import time
# Capture video from file
cap = cv2.VideoCapture('test_video.mp4')
time.sleep(1)
fgbg = cv2.createBackgroundSubtractorMOG2()
j = 0
fourcc = cv2.VideoWriter_fourcc(*'MPEG')
out = cv2.VideoWriter('output.avi',fourcc, 20.0, (640,480))
while (cap.isOpened()):
ret, frame = cap.read()
if ret == True:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
fgmask = fgbg.apply(gray)
_, contours, _ = cv2.findContours(fgmask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
if contours:
areas = []
for contour in contours:
ar = cv2.contourArea(contour)
areas.append(ar)
max_area = max(areas or [0])
max_area_index = areas.index(max_area)
cnt = contours[max_area_index]
M = cv2.moments(cnt)
x, y, w, h = cv2.boundingRect(cnt)
cv2.drawContours(fgmask, [cnt], 0, (255,255,255), 3, maxLevel = 0)
if h < w:
j += 1
if j>10:
cv2.rectangle(frame,(x,y),(x+w,y+h),(0,0,255),2)
if h > w:
j = 0
cv2.rectangle(frame,(x,y),(x+w,y+h),(0,255,0),2)
cv2.imshow('video',frame)
out.write(frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
This opens up a window and plays a video, then output.avi is created, but it doesn't contain any content.
cmd produces nothing. I just can't able to save a file in a proper way.
Please recommend a solution to this issue
The error is telling you that frame does not have 3 or 4 channels.
Can you check that your camera is initialized properly
if not cap.isOpened():
print("Camera not initialized")
return
It is returning you a valid frame
if not ret:
print("Problem reading frame")
return
else:
# Convert your frame to gray and find contours etc.
I've been trying to store cropped images from as single frame to a list but i keep getting errors. Here's a snippet of my code
import cv2
import numpy as np
cap = cv2.VideoCapture('/home/wael-karkoub/Desktop/Research/Videos/test.mp4')
ret = True
cropped_images = []
while ret == True:
ret, frame = cap.read()
height, width, channels = frame.shape
gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),0)
_ ,thresh = cv2.threshold(blur[0:height//2],10,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
im2, contours, hierarchy = cv2.findContours(thresh,1,2)
for cnt in contours:
x,y,w,h = cv2.boundingRect(cnt)
cv2.rectangle(frame,(x,y),(x+w,y+h),(0,255,0),2)
image = frame[y:y+h, x:x+w]
cv2.imshow('test',image)
time.sleep(2)
# cv2.imshow('Contours',frame)
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
cap.release()
cv2.destroyAllWindows()
Is this the correct way of doing it?
Output = enter image description here
If you want to store your cropped images to a list, you need some assignment going on. Just add cropped_images.append(image) somewhere in your code, most likely after image = frame[y:y+h, x:x+w]