I have the above number plate image with me. My goal is to segment each character individually and pass into my neural network. I have tried to find countours and use bounding rectangles to segment these characters using the following code:
img = cv2.imread('download.jpeg')
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray_img = cv2.GaussianBlur(gray_img, (5,5), 0)
ret, im_th = cv2.threshold(gray_img, 90, 255, cv2.THRESH_BINARY_INV)
im_th = cv2.adaptiveThreshold(gray_img, 255,
cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY,75, 10)
im_th = cv2.bitwise_not(im_th)
ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, ctrs, -1, (0,255,0), 3)
rects = [cv2.boundingRect(ctr) for ctr in ctrs]
print len(rects)
for rect in rects:
cv2.rectangle(img,(rect[0], rect[1]), (rect[0] + rect[2], rect[1] + rect[3]), (0,255,0),3)
length = int(rect[3] * 1.6)
pt1 = int(rect[1] + rect[3] // 2 - length // 2)
pt2 = int(rect[0] + rect[2] // 2 - length // 2)
roi = img[pt1:pt1+length, pt2:pt2+length]
The above code creates regions that include bounding rectangles other than the characters. Although I could manually filter out these regions, it would vary from image to image. How would I go about this if I need to only extract the regions with characters?
#read image
img = cv2.imread('input_image.png')
#grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
cv2.waitKey(0)
#binarize
ret,thresh = cv2.threshold(gray,127,255,cv2.THRESH_BINARY_INV)
cv2.waitKey(0)
#find contours
im2,ctrs, hier = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
#sort contours
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
for i, ctr in enumerate(sorted_ctrs):
# Get bounding box
x, y, w, h = cv2.boundingRect(ctr)
# Getting ROI
roi = img[y:y+h, x:x+w]
# show ROI
#cv2.imwrite('roi_imgs.png', roi)
cv2.imshow('charachter'+str(i), roi)
cv2.rectangle(img,(x,y),( x + w, y + h ),(90,0,255),2)
cv2.waitKey(0)
cv2.imshow('marked areas',img)
cv2.waitKey(0)
Related
I have a problem with the contour, i.e. the mask I get after that. I am bothered by all the peaks, I marked them with a red circle, which remain after the graph. Is there any easy way to get rid of them?
h, w = img.shape[:2]
mask = np.zeros((h, w), np.uint8)
# Transform to gray colorspace and threshold the image
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
# Search for contours and select the biggest one and draw it on mask
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cntsSorted = sorted(contours, key=lambda x: cv2.contourArea(x), reverse=True)
for n in range(0,2):
cnt = cntsSorted[n]
cv2.drawContours(mask, [cnt], 0, 255, -1)
# Perform a bitwise operation
color = cv2.bitwise_and(img, img, mask=mask)
x, y, w, h = cv2.boundingRect(cnt)
crop = color[y:(y + h)-3, x+3:x + w]
I want to detect a rectangle shape in the digital meter, to detect the shape contour approximation, but not able to find the exact contour of rectangle .I don't know where is the mistake .please have a look and suggest
digitalMeter.jpg
required-Output-digitalMeter-contour
import imutils
import cv2
image = cv2.imread('C:\\digitalMeter.jpg')
image = imutils.resize(image, height=500)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(blurred, 50, 200, 255)
cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
displayCnt = None
for c in (cnts):
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.02 * peri, True)
if len(approx) == 4:
print(displayCnt)[enter image description here][2]
displayCnt = approx
break
cv2.drawContours(image, [displayCnt], -1, (0, 230, 255), 6)
cv2.imshow('cnts', image)
cv2.waitKey(0)
Here is one way to do that in Python/OpenCV.
Read the input
Convert to gray
Threshold
Apply morphology to clean up the threshold image
Invert so that the meter is white on a black background
Find the contours and extract the largest (actually only) contour
Draw the contour on the input image
Save the results
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('digital_meter.jpg')
hh, ww = img.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# threshold
thresh = cv2.threshold(gray,30,255,cv2.THRESH_BINARY)[1]
# apply close and open morphology
kernel = np.ones((3,3), np.uint8)
mask = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
kernel = np.ones((11,11), np.uint8)
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
# invert
mask = 255 - mask
# get largest contour
contours = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
# draw green contour on input
contour_img = img.copy()
cv2.drawContours(contour_img,[big_contour],0,(0,255,0),2)
# save cropped image
cv2.imwrite('digital_meter_thresh.png',thresh)
cv2.imwrite('digital_meter_mask.png',mask)
cv2.imwrite('digital_meter_contour.png',contour_img)
# show the images
cv2.imshow("THRESH", thresh)
cv2.imshow("MASK", mask)
cv2.imshow("CONTOUR", contour_img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold Image:
Morphology cleaned and inverted image:
Resulting contour on input:
In this image I am trying to detect horizontal lines. The code works well when image is not skewed. However, it is not working on such skewed images. I have tried this method to detect the right angle by histogram but many times is actually making it more skewed - python-opencv-skew-correction-for-ocr
Below is code to detect horizontal lines:
gray=cv2.cvtColor(img_final_bin,cv2.COLOR_BGR2GRAY)
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (100,1))
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
detected_lines = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts, hierarchy = cv2.findContours(detected_lines, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
boundingBoxes = [list(cv2.boundingRect(c)) for c in cnts]
Below is the code for skew correction, which is giving wrong results to me:
def correct_skew(image, delta=0.001, limit=3):
def determine_score(arr, angle):
data = inter.rotate(arr, angle, reshape=False, order=0)
histogram = np.sum(data, axis=1)
score = np.sum((histogram[1:] - histogram[:-1]) ** 2)
return histogram, score
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
print("thresh", thresh.shape)
thresh1 = thresh[0:500, 0:500]
print("thresh1", thresh1.shape)
scores = []
angles = np.arange(-limit, limit + delta, delta)
for i, angle in enumerate(angles):
histogram, score = determine_score(thresh1, angle)
scores.append(score)
# if i%100 == 0:
# print(score, angle, len(angles), i)
best_angle = angles[scores.index(max(scores))]
(h, w) = image.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, best_angle, 1.0)
rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, \
borderMode=cv2.BORDER_REPLICATE)
return best_angle, rotated
Python Wand, which is based upon ImageMagick has a deskew function.
Input:
from wand.image import Image
from wand.display import display
with Image(filename='table.png') as img:
img.deskew(0.4*img.quantum_range)
img.save(filename='table_deskew.png')
display(img)
Result:
Is there a simple way that I can do digit segmentation from files like in the screenshot below?
I want to use OpenCV to do it as it's the library I'm using to do the rest of processing but other suggestions are welcomed.
Paper form:
Text box:
Simple OpenCV Contours method will not work here because digits are present in some sort of box template hence you need to detect boxes first check out this blog
Take this piece of code and adapt for your problem. It's not difficult with your situation:
import cv2
import numpy as np
# import image
image = cv2.imread('C:\\Users\\PC\\Desktop\\roi.png')
# grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow('gray', gray)
# binary
ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV)
cv2.imshow('threshold', thresh)
# dilation
kernel = np.ones((10, 1), np.uint8)
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
cv2.imshow('dilated', img_dilation)
# find contours
# cv2.findCountours() function changed from OpenCV3 to OpenCV4: now it have only two parameters instead of 3
cv2MajorVersion = cv2.__version__.split(".")[0]
# check for contours on thresh
if int(cv2MajorVersion) >= 4:
ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
else:
im2, ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# sort contours
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
for i, ctr in enumerate(sorted_ctrs):
# Get bounding box
x, y, w, h = cv2.boundingRect(ctr)
# Getting ROI
roi = image[y:y + h, x:x + w]
# show ROI
# cv2.imshow('segment no:'+str(i),roi)
cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
if w > 15 and h > 15:
cv2.imwrite('C:\\Users\\PC\\Desktop\\output\\{}.png'.format(i), roi)
cv2.imshow('marked areas', image)
cv2.waitKey(0)
Source: https://lucians.dev/extract-roi-from-image-with-python-and-opencv
I want to extract some rectangles at the top from a UML sequence diagram in jpg format by using OpenCV.
The algorithm I use finds way too many rectangles that are super small and not needed.
I think the mess up is somewhere in the beginning of the code where I apply canny edge detection but I am not sure.
I want to capture only the big rectangles from the top and center.
Thanks for any help.
import cv2
import numpy as np
import imutils
image = cv2.imread("./diagrams/sd2.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 90, 150, 3)
cnts = cv2.findContours(edges, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if imutils.is_cv2() else cnts[1]
cv2.drawContours(image, cnts, -1, (0, 255, 0), 1)
def detect(c):
shape = "unidentified"
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.03 * peri, True)
if len(approx) == 4:
(x, y, w, h) = cv2.boundingRect(approx)
ar = w / float(h)
shape = "square" if ar >= 0.95 and ar <= 1.05 else "rectangle"
return shape
# loop over the contours
for c in cnts:
M = cv2.moments(c)
if M["m00"] != 0:
cX = int((M["m10"] / M["m00"]))
cY = int((M["m01"] / M["m00"]))
shape = detect(c)
c = c.astype("float")
c = c.astype("int")
if(shape == "rectangle"):
cv2.drawContours(image, [c], -1, (0, 255, 0), 2)
cv2.putText(image, shape, (cX, cY), cv2.FONT_HERSHEY_SIMPLEX,
0.5, (0, 0, 0), 2)
# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)