Separate objects countours with OpenCV - python

I have been working with OpenCV in order to detect an squared obstacle. So far this is the image I get after applying filters and canny.
The obstacle I am trying to identify is the horizontal one, the three vertical rectangles are guide lines on the floor.My goal is to keep only the horizontal rectangle, separating it from the others, but after applying find Contours I only get I single object that includes all the shapes.This is the code I have been using in order to fin only the biggest rectangle by their area:
# find the biggest countour (c) by the area
if contours != 0:
if not contours:
print("Empty")
else:
bigone = max(contours, key=cv2.contourArea) if max else None
area = cv2.contourArea(bigone)
if area > 10000:
x, y, w, h = cv2.boundingRect(bigone)
cv2.rectangle(img, (x, y), (x+w, y+h), (0, 0, 255), 2)
cv2.putText(img, "Obstacle", (x+w/2, y-20),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
pts = np.array(
[[[x, y], [x+w, y], [x+w, y+h], [x, y+h]]], dtype=np.int32)
cv2.fillPoly(mask, pts, (255, 255, 255))
#values = img[np.where((mask == (255, 255, 255)).all(axis=2))]
res = cv2.bitwise_and(img, mask) # View only the obstacle
obs_area = w*h
print(obs_area)
if obs_area <= 168000:
command_publisher.publish("GO")
cv2.putText(
img, "GO", (380, 400), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 255), 1)
else:
command_publisher.publish("STOP")
cv2.putText(img, "STOP", (380, 400),
cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 255), 1)
# show the output image
cv2.imshow("Image", img)
cv2.waitKey(1)
And this is the result I am getting:
Is there a way of separating my obstacle from the lines on the floor with some kind of filter or algorithm?
Here is an example image to work with:

Here is one way to do that using Python/OpenCV.
- Read the input
- Convert to HSV and extract only the saturation channel (black/white/gray have zero saturation)
- Threshold
- Apply morphology open and close to remove the extranous white regions
- Get the contour and approximate to simple polygon
- Draw the polygon on the input
- Save the results
Input:
import cv2
import numpy as np
# read image
img = cv2.imread('board.png')
# convert to HSV and extract saturation channel
sat = cv2.cvtColor(img, cv2.COLOR_RGB2HSV)[:,:,1]
# threshold
thresh = cv2.threshold(sat, 90, 255, 0)[1]
# apply morphology close to fill interior regions in mask
kernel = np.ones((7,7), np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = np.ones((13,13), np.uint8)
morph = cv2.morphologyEx(morph, cv2.MORPH_CLOSE, kernel)
# get contours (presumably only 1) and fit to simple polygon (quadrilateral)
cntrs = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cntrs = cntrs[0] if len(cntrs) == 2 else cntrs[1]
c = cntrs[0]
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.05 * peri, True)
# draw polygon on input
result = img.copy()
cv2.polylines(result, [np.int32(approx)], True, (0,0,255), 1, cv2.LINE_AA)
# write result to disk
cv2.imwrite("board_saturation.png", sat)
cv2.imwrite("board_thresh.png", thresh)
cv2.imwrite("board_morph.png", morph)
cv2.imwrite("board_contour.png", result)
# display it
cv2.imshow("IMAGE", img)
cv2.imshow("SAT", sat)
cv2.imshow("THRESH", thresh)
cv2.imshow("MORPH", morph)
cv2.imshow("RESULT", result)
cv2.waitKey(0)
Saturation channel image:
Thresholded image:
Morphology cleaned image:
Contour on input:

In your image the problem seems white rectangles. My approach is checking each line and if line consist many pixels which are close to white(255,255,255) then make the line black.
Here is my code:
import cv2
import numpy as np
import random as rng
img=cv2.imread("/ur/image/directory/obstacle.png")
height, width, channels = img.shape
cv2.imshow('Source',img)
# Check each line and eliminate white rectangles(if line consist white pixels more than limit)
for x in range(0,height):
white_counter = 0
for y in range(0,width):
if img[x,y,0] >= 180 and img[x,y,1] >= 180 and img[x,y,2] >= 180:
white_counter = white_counter + 1
if white_counter>10:
for y in range(0,width):
img[x,y,0] = 0
img[x,y,1] = 0
img[x,y,2] = 0
cv2.imshow('Elimination White Rectangles', img)
# Find contours and draw rectangle for each
src_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
threshold = 300
canny_output = cv2.Canny(src_gray, threshold, threshold * 2)
contours, _ = cv2.findContours(canny_output, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours_poly = [None]*len(contours)
boundRect = [None]*len(contours)
for i, c in enumerate(contours):
contours_poly[i] = cv2.approxPolyDP(c, 3, True)
boundRect[i] = cv2.boundingRect(contours_poly[i])
rng.seed(12345)
drawing = np.zeros((canny_output.shape[0], canny_output.shape[1], 3), dtype=np.uint8)
for i in range(len(contours)):
color = (rng.randint(0,256), rng.randint(0,256), rng.randint(0,256))
cv2.rectangle(drawing, (int(boundRect[i][0]), int(boundRect[i][1])), \
(int(boundRect[i][0]+boundRect[i][2]), int(boundRect[i][1]+boundRect[i][3])), color, 2)
cv2.imshow('Output', drawing)
cv2.waitKey(0)
cv2.destroyAllWindows()
Eliminate White Rectangles:
Result:

Related

OpenCV python code to calculate distance of object relative to a point

Consider the image below:
I want to write an OpenCV program to calculate the distance (blue line) in pixels between the midpoint of the table (red dot) and the midpoint of the brown box (blue dot).
I figured using I would use cv2.findContours to find the boundaries of the table, the boundaries of the box, get the midpoint of the table, the midpoint of the box and then probably use dist.euclidean to calculate the distance between the box's midpoint and table's midpoint. However, I am stuck at this point:
My code (shown below) is drawing contours for the wires and the glare and I have no interest in them:
cv2.namedWindow("Object detector", cv2.WINDOW_NORMAL)
image = cv2.imread(PATH_TO_IMAGE)
cv2.resizeWindow('Object detector', 800, 600)
im_bw = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,2))
morphology_img = cv2.morphologyEx(im_bw, cv2.MORPH_OPEN, kernel,iterations=1)
edged = cv2.Canny(morphology_img, 50, 100)
edged = cv2.dilate(edged, None, iterations=1)
cnts= cv2.findContours(edged.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
(cnts, _) = contours.sort_contours(cnts)
cv2.drawContours(image, cnts, -1, (0,255,0), 3)
orig = image.copy()
cv2.imshow('Object detector', image)
cv2.waitKey(0)
cv2.destroyAllWindows()
I even added the following piece of code to filter out contours of a certain size:
for (i, c) in enumerate(cnts):
# if the contour is not sufficiently large, ignore it
if cv2.contourArea(c) < 50000:
continue
else:
box = cv2.minAreaRect(c)
box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
box = np.array(box, dtype="int")
cv2.drawContours(image, [box.astype("int")], -1, (0, 255, 0), 1)
(tl, tr, br, bl) = box
(tltrX, tltrY) = midpoint(tl, tr)
(blbrX, blbrY) = midpoint(bl, br)
(tlblX, tlblY) = midpoint(tl, bl)
(trbrX, trbrY) = midpoint(tr, br)
# compute the Euclidean distance between the midpoints
dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY))
dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY))
cv2.putText(image, "{:.1f}".format(dA),
(int(tltrX - 15), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
cv2.putText(image, "{:.1f}".format(dB),
(int(trbrX + 10), int(trbrY)), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (255, 255, 255), 2)
But even that didn't help.
How can I accomplish this task of calculating relative distance of the box from the center of the table?

How can I extract this watermelon from the image?

I'm trying to get the watermelon from the image. I have tried doing hsv segmentation and grabcut but it doesn't give me the output I wanted. How can I get the watermelon only? Any method will do except for Neural Networks since I'm new to image processing.
# hsv segmentation
lb = (20, 50, 0)
ub = (100, 255, 255)
mask_hsv = cv.inRange(hsv, lb, ub)
image_copy = image.copy()
morph = cv.erode(mask_hsv, (3, 3), iterations=4)
output = cv.bitwise_and(image_copy, image_copy, mask=morph)
After I use hsv I find the largest contour in the image.
draw = image.copy()
contours, h = cv.findContours(morph, cv.RETR_LIST, cv.CHAIN_APPROX_NONE)
if contours != 0:
for contour in contours:
area = cv.contourArea(contour)
if max_area < area:
max_area = area
cnt = contour
# else:
# pass
else:
print('No contours found!')
Then I find the boundingRect of the biggest contour and feed it to grabcut function
x, y, h, w = cv.boundingRect(cnt)
rect = (x, y, h, w)
output_rect = image.copy()
mask = np.ones(image.shape[:2], dtype=np.uint8) * cv.GC_PR_BGD
bgdModel = np.zeros((1, 65), dtype=np.float64)
fgdModel = np.zeros((1, 65), dtype=np.float64)
# performs grabCut
cv.grabCut(output_rect, mask, rect, bgdModel, fgdModel, 100, cv.GC_INIT_WITH_RECT)
mask = np.where((mask == 2)|(mask == 0), 0, 1).astype('uint8')
mask *= 255
# applying the genrated mask to the image
output_image = cv.bitwise_and(output_rect, output_rect, mask=mask)
# change black pixels to white
black_pixels = np.where(
(output_image[:, :, 0] == 0) & (output_image[:, :, 1] == 0) & (output_image[:, :, 2] == 0)
)
output_image[black_pixels] = [255, 255, 255]
Original Image
Biggest contour found
Output after grabcut
I got the correct outputs via drawing your detected contours on blank image, then applying erosion and finally finding HoughCircles. Feel Free to change hyper-parameters to obtain better results.
Code:
import cv2
import numpy as np
image = cv2.imread("watermelon.png")
image_hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
image_copy = image.copy()
lower_boundary = (20,50, 0)
upper_boundary = (100,255,255)
mask_hsv = cv2.inRange(image_hsv, lower_boundary, upper_boundary)
blank_im = np.zeros((image.shape[0], image.shape[1], 1), dtype=np.uint8)
morph = cv2.erode(mask_hsv, (3,3), iterations=4)
output = cv2.bitwise_and(image, image, mask=morph)
# Finding Contours
contours, _ = cv2.findContours(morph, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
if len(contours) != 0:
# Rather than using long for loop, this is how you can find the max value with given function
contour = max(contours, key=cv2.contourArea)
else:
print("No contours found!")
# Draw Contours on Blank Image (np.zeros() with same shape as original image)
cv2.drawContours(blank_im, contour, -1, (255,255,255), 10)
# Eroding the Blank Image with Drawn Contours
blank_im = cv2.erode(blank_im, (3,3), iterations=4)
# Find The Possible Circles, (Feel Free to Change Hyperparameters)
circles = cv2.HoughCircles(blank_im, cv2.HOUGH_GRADIENT, 1, 20, param1=50, param2=30, minRadius=0, maxRadius=0)
circles = np.uint16(np.around(circles))
# Draw each circle in green and centers in red
for i in circles[0,:]:
cv2.circle(image, (i[0],i[1]), i[2], (0,255,0), 2)
cv2.circle(image, (i[0], i[1]), 2, (0,0,255), 3)
# Display Images
cv2.imshow('Original Image', image_copy)
cv2.imshow('Drawed Contours On Blank Image', blank_im)
cv2.imshow('Detected Circle', image)
Output:

How to crop inner (incomplete) rectangle from contours in OpenCV

I have cropped the original photo to the surrounding area but it is dependent on the mouse position as well and will be different every time. Therefore I do not want a static crop of dimensions as it will vary.
The contours do not want to detect the rectangle I want because it is an incomplete rectangle since there is a cursor in the way.
Currently, my code is able to detect the contours but will only grab the outer rectangle and make a small crop.
I would like to make it detect the inner rectangle, do I have to somehow complete the rectangle first?
Source image
Contours detected
What I would LIKE to crop
What it is currently cropping
import cv2
import imutils # https://pypi.org/project/imutils/
import numpy as np
...
def crop_hover_list(cursor_coord_x, cursor_coord_y):
img_test = cv2.imread("source.jpg")
grayimage = cv2.cvtColor(img_test, cv2.COLOR_BGR2GRAY)
ret, mask = cv2.threshold(grayimage, 235, 255, cv2.THRESH_BINARY)
contours, hierarchy = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
cv2.drawContours(img_test, contours, -1, (0,255,0), 3)
cv2.imshow("test", img_test)
cv2.waitKey(0)
for contour in contours:
if cv2.contourArea(contour) < 250:
continue
print(list(contour))
ext_left = tuple(contour[contour[:, :, 0].argmin()][0])
ext_right = tuple(contour[contour[:, :, 0].argmax()][0])
ext_top = tuple(contour[contour[:, :, 1].argmin()][0])
ext_bot = tuple(contour[contour[:, :, 1].argmax()][0])
(x,y,w,h) = cv2.boundingRect(contour)
cv2.rectangle(img_test, (x, y), (x + w, y + h), (0, 0, 255), 3)
cv2.imshow("test", img_test)
cv2.waitKey(0)
I have your test image in images/ folder. Change it as you need to test the script.
img_test = cv2.imread("images/MCeLz.png")
Please pay attention here:
ret ,contours, hierarchy = cv2.findContours ...
I need 'ret' to work in my opencv version 3.2. May be you not.
My solution is use 2 parameters:
minimum area as you did , and color in a range. Then check that cursor is inside the contour.
import cv2
import imutils # https://pypi.org/project/imutils/
import numpy as np
def crop_hover_list(cursor_coord_x, cursor_coord_y):
img_test = cv2.imread("images/MCeLz.png")
cimg = img_test.copy()
mask = cv2.inRange(img_test, (200,200,200), (235, 235,235))
cv2.imshow("test", img_test)
cv2.imshow('mask',mask)
ret ,contours, hierarchy = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
for contour in contours:
if cv2.contourArea(contour) < 2000:
continue
(x,y,w,h) = cv2.boundingRect(contour)
is_cursor_inside = x <= cursor_coord_x <= (x+w) and y <= cursor_coord_y <= (y+h)
if is_cursor_inside:
cv2.rectangle(cimg, (x, y), (x + w, y + h), (0, 0, 255), 4)
cv2.drawContours(cimg, [contour], 0, (0,255,0), 3)
crop = img_test[y:y+h,x:x+w]
cv2.imshow("crop", crop)
cv2.imshow("cimg", cimg)
cv2.imshow("test", img_test)
cv2.waitKey(0)
crop_hover_list(300, 50)

How I can detect recognize text in а shape

Need your help. Now I'm writing python script to recognize text in a shape. This shape can be captured from RTSP (IP Camera) at any angle.
For the example see attached file. My code is here, but coords to crop rotated shape is sets manually
import cv2
import numpy as np
def main():
fn = cv2.VideoCapture("rtsp://admin:Admin123-#172.16.10.254")
flag, img = fn.read()
cnt = np.array([
[[64, 49]],
[[122, 11]],
[[391, 326]],
[[308, 373]]
])
print("shape of cnt: {}".format(cnt.shape))
rect = cv2.minAreaRect(cnt)
print("rect: {}".format(rect))
box = cv2.boxPoints(rect)
box = np.int0(box)
print("bounding box: {}".format(box))
cv2.drawContours(img, [box], 0, (0, 255, 0), 2)
img_crop, img_rot = crop_rect(img, rect)
print("size of original img: {}".format(img.shape))
print("size of rotated img: {}".format(img_rot.shape))
print("size of cropped img: {}".format(img_crop.shape))
new_size = (int(img_rot.shape[1]/2), int(img_rot.shape[0]/2))
img_rot_resized = cv2.resize(img_rot, new_size)
new_size = (int(img.shape[1]/2)), int(img.shape[0]/2)
img_resized = cv2.resize(img, new_size)
cv2.imshow("original contour", img_resized)
cv2.imshow("rotated image", img_rot_resized)
cv2.imshow("cropped_box", img_crop)
# cv2.imwrite("crop_img1.jpg", img_crop)
cv2.waitKey(0)
def crop_rect(img, rect):
# get the parameter of the small rectangle
center = rect[0]
size = rect[1]
angle = rect[2]
center, size = tuple(map(int, center)), tuple(map(int, size))
# get row and col num in img
height, width = img.shape[0], img.shape[1]
print("width: {}, height: {}".format(width, height))
M = cv2.getRotationMatrix2D(center, angle, 1)
img_rot = cv2.warpAffine(img, M, (width, height))
img_crop = cv2.getRectSubPix(img_rot, size, center)
return img_crop, img_rot
if __name__ == "__main__":
main()
example pic
You may start with the example in the following post.
The code sample detects the license plate, and it also detects your "shape" with text.
After detecting the "shape" with the text, you may use the following stages:
Apply threshold the cropped area.
Find contours, and find the contour with maximum area.
Build a mask, and mask area outside the contour (like in the license plate example).
Use minAreaRect (as fmw42 commented), and get the angle of the rectangle.
Rotate the cropped area (by angle+90 degrees).
Apply OCR using pytesseract.image_to_string.
Here is the complete code:
import cv2
import numpy as np
import imutils
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # I am using Windows
# Read the input image
img = cv2.imread('Admin123.jpg')
# Reused code:
# https://stackoverflow.com/questions/60977964/pytesseract-not-recognizing-text-as-expected/60979089#60979089
################################################################################
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #convert to grey scale
gray = cv2.bilateralFilter(gray, 11, 17, 17)
edged = cv2.Canny(gray, 30, 200) #Perform Edge detection
cnts = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None
# loop over our contours
for c in cnts:
# 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 "shape"
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]
################################################################################
# Apply threshold the cropped area
_, thresh = cv2.threshold(cropped, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
# Find contours
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cnts = imutils.grab_contours(cnts)
# Get contour with maximum area
c = max(cnts, key=cv2.contourArea)
# Build a mask (same as the code above)
mask = np.zeros(cropped.shape, np.uint8)
new_cropped = cv2.drawContours(mask, [c], 0, 255, -1)
new_cropped = cv2.bitwise_and(cropped, cropped, mask=mask)
# Draw green rectangle for testing
test = cv2.cvtColor(new_cropped, cv2.COLOR_GRAY2BGR)
cv2.drawContours(test, [c], -1, (0, 255, 0), thickness=2)
# Use minAreaRect as fmw42 commented
rect = cv2.minAreaRect(c)
angle = rect[2] # Get angle of the rectangle
# Rotate the cropped rectangle.
rotated_cropped = imutils.rotate(new_cropped, angle + 90)
# Read the text in the "shape"
text = pytesseract.image_to_string(rotated_cropped, config='--psm 3')
print("Extracted text is:\n\n", text)
# Show images for testing:
cv2.imshow('cropped', cropped)
cv2.imshow('thresh', thresh)
cv2.imshow('test', test)
cv2.imshow('rotated_cropped', rotated_cropped)
cv2.waitKey(0)
cv2.destroyAllWindows()
OCR output result:
AB12345
DEPARTMENT OF
INFORMATION
COMMUNICATION
TECHNOLOGY
cropped:
thresh:
test:
rotated_cropped:

opencv, python, how to read grouped text in boxes

I would like to get from the image in the groups that are on the image
I have managed to remove first contour (as described below), but issue is that when I try to read the text, I have some missing text, I expect that this is because of other contours that have stayed on the image, but while I try to remove them, I loose the grouping or part of text...
for i in range(len(contours)):
if 800 < cv2.contourArea(contours[i]) < 2000:
x, y, width, height = cv2.boundingRect(contours[i])
roi = img[y:y + height, x:x + width]
roi_h = roi.shape[0]
roi_w = roi.shape[1]
resize_roi = cv2.resize(roi,(int(roi_w*6),int(roi_h*6)), interpolation=cv2.INTER_LINEAR)
afterd = cv2.cvtColor(resize_roi, cv2.COLOR_BGR2GRAY)
retim, threshm = cv2.threshold(afterd, 210, 225, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
contoursm, hierarchym = cv2.findContours(threshm, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
mask = np.ones(resize_roi.shape[:2], dtype="uint8") * 255
for m in range(len(contoursm)):
if 10000 < cv2.contourArea(contoursm[m]) < 33000:
cv2.drawContours(mask, contoursm, m, 0, 7)
afterd = cv2.bitwise_not(afterd)
afterd = cv2.bitwise_and(afterd, afterd, mask=mask)
afterd = cv2.bitwise_not(afterd)
print(pytesseract.image_to_string(afterd, lang='eng', config='--psm 3'))
Instead of dealing with all the boxes, I suggest deleting them by finding connected components, and filling the large clusters with background color.
You may use the following stages:
Convert image to Grayscale, apply threshold, and invert polarity.
Delete all clusters having more than 100 pixels (assume letters are smaller).
Dilate thresh for uniting text areas to single "blocks".
Find contours on the dilated thresh image.
Find bounding rectangles, and apply OCR to the rectangle.
Here is the complete code sample:
import numpy as np
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' # I am using Windows
img = cv2.imread('img.png') # Read input image
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Convert to Grayscale.
ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) # Convert to binary and invert polarity
nlabel,labels,stats,centroids = cv2.connectedComponentsWithStats(thresh, connectivity=8)
thresh_size = 100
# Delete all lines by filling large clusters with zeros.
for i in range(1, nlabel):
if stats[i, cv2.CC_STAT_AREA] > thresh_size:
thresh[labels == i] = 0
# Dilate thresh for uniting text areas to single blocks.
dilated_thresh = cv2.dilate(thresh, np.ones((5,5)))
# Find contours on dilated thresh
contours, hierarchy = cv2.findContours(dilated_thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# Iterate contours, find bounding rectangles
for c in contours:
# Get bounding rectangle
x, y, w, h = cv2.boundingRect(c)
# Draw green rectangle for testing
cv2.rectangle(img, (x, y), (x+w, y+h), (0, 255, 0), thickness = 1)
# Get the slice with the text (slice with margins).
afterd = thresh[y-3:y+h+3, x-3:x+w+3]
# Show afterd as image for testing
# cv2.imshow('afterd', afterd)
# cv2.waitKey(100)
# The OCR works only when image is enlarged and black text?
resized_afterd = cv2.resize(afterd, (afterd.shape[1]*5, afterd.shape[0]*5), interpolation=cv2.INTER_LANCZOS4)
print(pytesseract.image_to_string(255 - resized_afterd, lang='eng', config='--psm 3'))
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result strings after OCR:
DF6DF645
RFFTW
2345
2277
AABBA
DF1267
ABCET5456
Input image with green boxes around the text:
Update:
Grouping contours:
For contours contours you may use the hierarchy result of cv2.findContours with cv2.RETR_TREE.
See Contours Hierarchy documentation.
You may use the parent-child relationship for grouping contours.
Here is an incomplete sample code for using the hierarchy:
img = cv2.imread('img.png') # Read input image
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Convert to Grayscale.
ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU) # Convert to binary and invert polarity
nlabel,labels,stats,centroids = cv2.connectedComponentsWithStats(thresh, connectivity=8)
thresh_boxes = np.zeros_like(thresh)
thresh_size = 100
# Delete all lines by filling large clusters with zeros.
# Make new image that contains only boxes - without text
for i in range(1, nlabel):
if stats[i, cv2.CC_STAT_AREA] > thresh_size:
thresh[labels == i] = 0
thresh_boxes[labels == i] = 255
# Find contours on thresh_boxes, use cv2.RETR_TREE to build tree with hierarchy
contours, hierarchy = cv2.findContours(thresh_boxes, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
# Iterate contours, and hierarchy
for c, i in zip(contours, range(len(contours))):
h = hierarchy[0, i, :]
h_child = h[2]
# if contours has no child (last level)
if h_child == -1:
h_parent = h[3]
x, y, w, h = cv2.boundingRect(c)
cv2.putText(img, str(h_parent), (x+w//2-4, y+h//2+8), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=(0, 0, 255), thickness=2)
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
Result:

Categories

Resources