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

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)

Related

How to fill a contour plot mask and retain data inside the contour and blackout the rest

I have an image like so,
By using the following code,
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg", 1)
#color boundaries [B, G, R]
lower = [0, 3, 30]
upper = [30, 117, 253]
# create NumPy arrays from the boundaries
lower = np.array(lower, dtype="uint8")
upper = np.array(upper, dtype="uint8")
# find the colors within the specified boundaries and apply
# the mask
mask = cv2.inRange(image, lower, upper)
output = cv2.bitwise_and(image, image, mask=mask)
ret,thresh = cv2.threshold(mask, 50, 255, 0)
if (int(cv2.__version__[0]) > 3):
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
else:
im2, contours, hierarchy = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
if len(contours) != 0:
# find the biggest countour (c) by the area
c = max(contours, key = cv2.contourArea)
x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imshow('ROI',ROI)
cv2.imwrite('ROI.png',ROI)
cv2.waitKey(0)
I get the following cropped image,
I would like to retain all data within the orange hand-drawn boundary including the boundary itself and blackout the rest.
In the image above the data outside the orange boundary is still there. I do not want that. How do i fill the mask which is like this now so that i can retain data inside the orange boundary,
I would still like to retain other properties like the rectangular bounding box. I don't want anything else to change. How do I go about this?
Thanks.
As you desire (in your comments to my previous answer) to have the outer region to be black rather than transparent, you can do that as follows in Python/OpenCV with a couple of lines changed to multiply the mask by the input rather than put the mask into the alpha channel.
Input:
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg")
#color boundaries [B, G, R]
lower = (0, 70, 210)
upper = (50, 130, 255)
# threshold on orange color
thresh = cv2.inRange(image, lower, upper)
# get largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x,y,w,h = cv2.boundingRect(big_contour)
# draw filled contour on black background
mask = np.zeros_like(image)
cv2.drawContours(mask, [big_contour], 0, (255,255,255), -1)
# apply mask to input image
new_image = cv2.bitwise_and(image, mask)
# crop
ROI = new_image[y:y+h, x:x+w]
# save result
cv2.imwrite('frame50_thresh.jpg',thresh)
cv2.imwrite('frame50_mask.jpg',mask)
cv2.imwrite('frame50_new_image2.jpg',new_image)
cv2.imwrite('frame50_roi2.jpg',ROI)
# show images
cv2.imshow('thresh',thresh)
cv2.imshow('mask',mask)
cv2.imshow('new_image',new_image)
cv2.imshow('ROI',ROI)
cv2.waitKey(0)
new_image after applying the mask:
cropped roi image:
Here is one way to do that in Python/OpenCV.
Read the input
Threshold on the orange color
Find the (largest) contour and get its bounding box
Draw a white filled contour on a black background as a mask
Create a copy of the input with an alpha channel
Copy the mask into the alpha channel
Crop the ROI
Save the results
Input:
import numpy as np
import cv2
# load the image
image = cv2.imread("frame50.jpg")
#color boundaries [B, G, R]
lower = (0, 70, 210)
upper = (50, 130, 255)
# threshold on orange color
thresh = cv2.inRange(image, lower, upper)
# get largest contour
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
big_contour = max(contours, key=cv2.contourArea)
x,y,w,h = cv2.boundingRect(big_contour)
# draw filled contour on black background
mask = np.zeros_like(image)
cv2.drawContours(mask, [big_contour], 0, (255,255,255), -1)
# put mask into alpha channel of input
new_image = cv2.cvtColor(image, cv2.COLOR_BGR2BGRA)
new_image[:,:,3] = mask[:,:,0]
# crop
ROI = new_image[y:y+h, x:x+w]
# save result
cv2.imwrite('frame50_thresh.jpg',thresh)
cv2.imwrite('frame50_mask.jpg',mask)
cv2.imwrite('frame50_new_image.jpg',new_image)
cv2.imwrite('frame50_roi.png',ROI)
# show images
cv2.imshow('thresh',thresh)
cv2.imshow('mask',mask)
cv2.imshow('new_image',new_image)
cv2.imshow('ROI',ROI)
cv2.waitKey(0)
Threshold image:
Mask Image:
New image with mask in alpha channel:
Cropped ROI

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:

Separate objects countours with OpenCV

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:

Removing background color from image opencv python

I have many images of specimen which have uncontrollable background color. Some of them have black background. Some of them have white background. Some of them have green background, etc.
I would like to remove these background color of a given image where the object in the image is just only one specimen. I try this code but it does not work as i expect.
def get_holes(image, thresh):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
im_bw = cv2.threshold(gray, thresh, 255, cv2.THRESH_BINARY)[1]
im_bw_inv = cv2.bitwise_not(im_bw)
_, contour, _ = cv2.findContours(im_bw_inv, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contour:
cv2.drawContours(im_bw_inv, [cnt], 0, 255, -1)
nt = cv2.bitwise_not(im_bw)
im_bw_inv = cv2.bitwise_or(im_bw_inv, nt)
return im_bw_inv
def remove_background(image, thresh, scale_factor=.25, kernel_range=range(1, 15), border=None):
border = border or kernel_range[-1]
holes = get_holes(image, thresh)
small = cv2.resize(holes, None, fx=scale_factor, fy=scale_factor)
bordered = cv2.copyMakeBorder(small, border, border, border, border, cv2.BORDER_CONSTANT)
for i in kernel_range:
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2*i+1, 2*i+1))
bordered = cv2.morphologyEx(bordered, cv2.MORPH_CLOSE, kernel)
unbordered = bordered[border: -border, border: -border]
mask = cv2.resize(unbordered, (image.shape[1], image.shape[0]))
fg = cv2.bitwise_and(image, image, mask=mask)
return fg
file = your_file_location
img = cv2.imread(file)
nb_img = dm.remove_background(img, 255)
These are some example images
May i have your suggestions?
Here's a simple approach with the assumption that there is only one specimen per image.
Kmeans color quantization. We load the image then perform Kmeans color quantization to segment the image into a specified cluster of colors. For instance with clusters=4, the image will be labeled into four colors.
Obtain binary image. Convert to grayscale, Gaussian blur, adaptive threshold.
Draw largest enclosing circle onto mask. Find contours, sort for largest contour using contour area filtering then draw the largest enclosing circle onto a mask using cv2.minEnclosingCircle.
Bitwise-and. Since we have isolated the desired sections to extract, we simply bitwise-and the mask and input image
Input image -> Kmeans -> Binary image
Detected largest enclosing circle -> Mask -> Result
Here's the output for the second image
Input image -> Kmeans -> Binary image
Detected largest enclosing circle -> Mask -> Result
Code
import cv2
import numpy as np
# Kmeans color segmentation
def kmeans_color_quantization(image, clusters=8, rounds=1):
h, w = image.shape[:2]
samples = np.zeros([h*w,3], dtype=np.float32)
count = 0
for x in range(h):
for y in range(w):
samples[count] = image[x][y]
count += 1
compactness, labels, centers = cv2.kmeans(samples,
clusters,
None,
(cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10000, 0.0001),
rounds,
cv2.KMEANS_RANDOM_CENTERS)
centers = np.uint8(centers)
res = centers[labels.flatten()]
return res.reshape((image.shape))
# Load image and perform kmeans
image = cv2.imread('2.jpg')
original = image.copy()
kmeans = kmeans_color_quantization(image, clusters=4)
# Convert to grayscale, Gaussian blur, adaptive threshold
gray = cv2.cvtColor(kmeans, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,21,2)
# Draw largest enclosing circle onto a mask
mask = np.zeros(original.shape[:2], dtype=np.uint8)
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
for c in cnts:
((x, y), r) = cv2.minEnclosingCircle(c)
cv2.circle(image, (int(x), int(y)), int(r), (36, 255, 12), 2)
cv2.circle(mask, (int(x), int(y)), int(r), 255, -1)
break
# Bitwise-and for result
result = cv2.bitwise_and(original, original, mask=mask)
result[mask==0] = (255,255,255)
cv2.imshow('thresh', thresh)
cv2.imshow('result', result)
cv2.imshow('mask', mask)
cv2.imshow('kmeans', kmeans)
cv2.imshow('image', image)
cv2.waitKey()

How to extract only characters from image?

I have this type of image from that I only want to extract the characters.
After binarization, I am getting this image
img = cv2.imread('the_image.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 11, 9)
Then find contours on this image.
(im2, cnts, _) = cv2.findContours(thresh.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
for contour in cnts[:2000]:
x, y, w, h = cv2.boundingRect(contour)
aspect_ratio = h/w
area = cv2.contourArea(contour)
cv2.drawContours(img, [contour], -1, (0, 255, 0), 2)
I am getting
I need a way to filter the contours so that it selects only the characters. So I can find the bounding boxes and extract roi.
I can find contours and filter them based on the size of areas, but the resolution of the source images are not consistent. These images are taken from mobile cameras.
Also as the borders of the boxes are disconnected. I can't accurately detect the boxes.
Edit:
If I deselect boxes which has an aspect ratio less than 0.4. Then it works up to some extent. But I don't know if it will work or not for different resolution of images.
for contour in cnts[:2000]:
x, y, w, h = cv2.boundingRect(contour)
aspect_ratio = h/w
area = cv2.contourArea(contour)
if aspect_ratio < 0.4:
continue
print(aspect_ratio)
cv2.drawContours(img, [contour], -1, (0, 255, 0), 2)
Not so difficult...
import cv2
img = cv2.imread('img.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv2.imshow('gray', gray)
ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU)
cv2.imshow('thresh', thresh)
im2, ctrs, hier = cv2.findContours(thresh.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
sorted_ctrs = sorted(ctrs, key=lambda ctr: cv2.boundingRect(ctr)[0])
for i, ctr in enumerate(sorted_ctrs):
x, y, w, h = cv2.boundingRect(ctr)
roi = img[y:y + h, x:x + w]
area = w*h
if 250 < area < 900:
rect = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow('rect', rect)
cv2.waitKey(0)
Result
You can tweak the code like you want (here it can save ROI using original image; for eventually OCR recognition you have to save them in binary format - better methods than sorting by area are available)
Source: Extract ROI from image with Python and OpenCV and some of my knowledge.
Just kidding, take a look at my questions/answers.

Categories

Resources