Develop Reference

opencv get bounding box of two squares from image

I want to get the bounding boxes from an image.
I want the coordinates of the two white boxes.
This is an example image:
I tried out
_a, _b, stats, _c = cv2.connectedComponentsWithStats(image, connectivity=8)
and then the boxes are in the stats object.
But I got for the image more then 2 boxes. This is strange.
Maybe somebody has an other solution?

import cv2
# Read image
img = cv2.imread("/Users/sb/Desktop/7n8uq.png", cv2.IMREAD_COLOR)
# Convert to grayscale
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Threshold (Produces a binary image)
_, thresh = cv2.threshold(
img_gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
cv2.imwrite("thresh.png", thresh)
# Find contours
contours, hierarchy = cv2.findContours(
thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print("Total number of contours: {}".format(len(contours)))
all_contours_drawn = cv2.drawContours(
img.copy(), contours, -1, (0, 255, 0), 2) # draw all contours
cv2.imwrite("all_contours.png", all_contours_drawn)
box_center_x = []
box_center_y = []
for cnt in contours:
x, y, w, h = cv2.boundingRect(cnt)
box_center_x.append(x+w/2)
box_center_y.append(y+h/2)
print("x-coordinate of boxes: {}".format(box_center_x))
print("y-coordinate of boxes: {}".format(box_center_y))
# Draw box centers
all_box_centers_drawn = img.copy()
for i in range(len(box_center_x)):
cv2.circle(
all_box_centers_drawn,
(int(box_center_x[i]), int(box_center_y[i])),
2, (0 , 0, 255), 2)
cv2.imwrite("box-centers.png", all_box_centers_drawn)

Try using find contours
contours, hierarchy = cv2.findContours(image, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for i, contour in enumerate(contours[1::]):
bbox = cv2.boundingRect(contour)
find contours example

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:

How to detect and extract signature from an image with OpenCV?

I am importing the attached image. After importing the image, I want to remove horizontal lines, detect the signature and then extract it, create rectangle around signature, crop the rectangle and save it. I am struggling to identify entire region of a signature as one contour or a group of contours.
I have already tried findcontour and then various ways to detect signature region. Please refer the code below.
Python Script:
imagePath
#read image
image = cv2.imread(imagePath,cv2.COLOR_BGR2RGB)
#Convert to greyscale
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY) # grayscale
#Apply threshold
ret,thresh1 = cv2.threshold(gray, 0, 255,cv2.THRESH_OTSU|cv2.THRESH_BINARY_INV)
plt.imshow(thresh1,cmap = 'gray')
#preprocessing
rect_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15,15))
dilation = cv2.dilate(thresh1, rect_kernel, iterations = 1)
plt.imshow(dilation,cmap = 'gray')
#Detect contours
contours, hierarchy = cv2.findContours(dilation, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
contours[0]
height, width, _ = image.shape
min_x, min_y = width, height
max_x = max_y = 0
for contour, hier in zip(contours, hierarchy):
(x,y,w,h) = cv2.boundingRect(contour)
min_x, max_x = min(x, min_x), max(x+w, max_x)
min_y, max_y = min(y, min_y), max(y+h, max_y)
if w > 80 and h > 80:
cv2.rectangle(frame, (x,y), (x+w,y+h), (255, 0, 0), 2)
if max_x - min_x > 0 and max_y - min_y > 0:
fin=cv2.rectangle(image, (min_x, min_y), (max_x, max_y), (255, 0, 0), 2)
plt.imshow(fin)
final=cv2.drawContours(image, contours,-1,(0,0,255),6)
plt.imshow(final,cmap = 'gray')
Final objective is to create rectangle around entire signature
Trying to generalize on the other image:

Instead of removing the horizontal lines, it may be easier to perform HSV color thresholding. The idea is to isolate the signature onto a mask and then extract it. We convert the image to HSV format then use a lower/upper color threshold to generate a mask
lower = np.array([90, 38, 0])
upper = np.array([145, 255, 255])
mask = cv2.inRange(image, lower, upper)
Mask
To detect the signature, we can get the combined bounding box for all of the contours with np.concatenate() then use cv2.boundingRect() to obtain the coordinates
Now that we have the bounding box coordinates, we can use Numpy slicing to crop and extract the ROI
import numpy as np
import cv2
# Load image and HSV color threshold
image = cv2.imread('1.jpg')
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([90, 38, 0])
upper = np.array([145, 255, 255])
mask = cv2.inRange(hsv, lower, upper)
result = cv2.bitwise_and(image, image, mask=mask)
result[mask==0] = (255, 255, 255)
# Find contours on extracted mask, combine boxes, and extract ROI
cnts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = np.concatenate(cnts)
x,y,w,h = cv2.boundingRect(cnts)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
ROI = result[y:y+h, x:x+w]
cv2.imshow('result', result)
cv2.imshow('mask', mask)
cv2.imshow('image', image)
cv2.imshow('ROI', ROI)
cv2.waitKey()
Note: The lower/upper color ranges were obtained from choosing the correct upper and lower HSV boundaries for color detection with cv::inRange (OpenCV)

Find contours of a square table (matrix shape) in an image using Python OpenCV

I am new and I wonder how can I find the contours of the image like the below with Python OpenCV (cv2 library):
I am going to fill in each square a number and then convert it into numpy array, so I think I need to figure out how to get the contours of each square in the matrix first (maybe the coordinates of the square in the picture)
I try to use some code snippet:
img = cv2.imread(img_path, 1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
binary = cv2.bitwise_not(gray)
contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for contour in contours:
(x, y, w, h) = cv2.boundingRect(contour)
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
But it doesn't work

Try this:
img = cv2.imread(img_path, 1)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gauss = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 3, 0)
ret,thresh = cv2.threshold(gauss,0,255,cv2.THRESH_BINARY|cv2.THRESH_OTSU)
rev=255-thresh
_ ,contours, hierarchy = cv2.findContours(thresh, cv2.RETR_LIST ,cv2.CHAIN_APPROX_SIMPLE)
print(contours)
min_rect_len = 15
max_rect_len = 20
for contour in contours:
(x, y, w, h) = cv2.boundingRect(contour)
if h>min_rect_len and w>min_rect_len:
cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 1)
cv2.imwrite(img_path[:-4] + "_with_contours.jpg", img)
It produces the following image for the given image :

Python file write all the bounding box coordinates using OpenCV

My task:
My task is to extract bounding box coordinates of following image:
I have following code. I am trying to get these coordinates using roi, but I am not sure how to get them.
import cv2
import numpy as np
large = cv2.imread('1.jpg')
small = cv2.cvtColor(large, cv2.COLOR_BGR2GRAY)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
grad = cv2.morphologyEx(small, cv2.MORPH_GRADIENT, kernel)
_, bw = cv2.threshold(grad, 0.0, 255.0, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9, 1))
connected = cv2.morphologyEx(bw, cv2.MORPH_CLOSE, kernel)
contours, hierarchy = cv2.findContours(connected.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
mask = np.zeros(bw.shape, dtype=np.uint8)
for idx in range(len(contours)):
x, y, w, h = cv2.boundingRect(contours[idx])
mask[y:y+h, x:x+w] = 0
cv2.drawContours(mask, contours, idx, (255, 255, 255), -1)
r = float(cv2.countNonZero(mask[y:y+h, x:x+w])) / (w * h)
if r > 0.45 and w > 8 and h > 8:
cv2.rectangle(large, (x, y), (x+w-1, y+h-1), (0, 255, 0), 1)
roi=large[y:y+h, x:x+w]
print(roi)
Result should be something like this:
1675,1335,2338,1338,2337,1455,1674,1452. :Box1
3067,519,3604,521,3603,651,3066,648 :Box2
1017,721,1729,726,1728,857,1016,852 :Box3
I have referred:
Extract all bounding boxes using OpenCV Python . On this link they are extracting images inside bounding boxes when they already have annotated image with rectangular GUI as a input. I want to extract the detected regions into a text file. How do I do it?

x, y, w, h = cv2.boundingRect(contours[idx]) is the coordinates you want, then write it to a txt file:
...
with open("coords.txt","w+") as file:
for idx in range(len(contours)):
x, y, w, h = cv2.boundingRect(contours[idx])
mask[y:y+h, x:x+w] = 0
file.write("Box {0}: ({1},{2}), ({3},{4}), ({5},{6}), ({7},{8})".format(idx,x,y,x+w,y,x+w,y+h,x,y+h))
cv2.drawContours(mask, contours, idx, (255, 255, 255), -1)
r = float(cv2.countNonZero(mask[y:y+h, x:x+w])) / (w * h)
...
The result will contain 4 points for each box, like this.
Box 0: (360,259), (364,259), (364,261), (360,261)
Box 1: (380,258), (385,258), (385,262), (380,262)
Box 2: (365,258), (370,258), (370,262), (365,262)
Box 3: (386,256), (393,256), (393,260), (386,260)
Box 4: (358,256), (361,256), (361,258), (358,258)

import cv2
import numpy as np
# Load an image in grayscale
img = cv2.imread('image.jpg', cv2.IMREAD_GRAYSCALE)
# Perform OTSU thresholding
thresh, img_bin = cv2.threshold(img, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
# Find contours
contours, _ = cv2.findContours(img_bin, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Iterate through all contours
for cnt in contours:
# Get bounding box coordinates
x, y, w, h = cv2.boundingRect(cnt)
# Draw bounding box on the original image
cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
# Show the original image with bounding boxes
cv2.imshow("Bounding Boxes", img)
cv2.waitKey(0)
cv2.destroyAllWindows()