Unable to segment handwritten characters - python

I am trying to extract handwritten numbers and alphabet from an image, for that i followed this stackoverflow link. It is working fine for most of the images where letter is written using marker but when i am using image where data is written using Pen it is failing miserably. Need some help to fix this.
Below is my code:
import cv2
import imutils
from imutils import contours
# Load image, grayscale, Otsu's threshold
image = cv2.imread('xxx/pic_crop_7.png')
image = imutils.resize(image, width=350)
img=image.copy()
# Remove border
kernel_vertical = cv2.getStructuringElement(cv2.MORPH_RECT, (1,50))
temp1 = 255 - cv2.morphologyEx(image, cv2.MORPH_CLOSE, kernel_vertical)
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,1))
temp2 = 255 - cv2.morphologyEx(image, cv2.MORPH_CLOSE, horizontal_kernel)
temp3 = cv2.add(temp1, temp2)
result = cv2.add(temp3, image)
# Convert to grayscale and Otsu's threshold
gray = cv2.cvtColor(result, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray,(5,5),0)
_,thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU | cv2.THRESH_BINARY_INV)
# thresh=cv2.dilate(thresh,None,iterations=1)
# Find contours and filter using contour area
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[0]
MIN_AREA=45
digit_contours = []
for c in cnts:
if cv2.contourArea(c)>MIN_AREA:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(img, (x, y), (x + w, y + h), (36,255,12), 2)
digit_contours.append(c)
# cv2.imwrite("C:/Samples/Dataset/ocr/segmented" + str(i) + ".png", image[y:y+h,x:x+w])
sorted_digit_contours = contours.sort_contours(digit_contours, method='left-to-right')[0]
contour_number = 0
for c in sorted_digit_contours:
x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imwrite('xxx/segment_{}.png'.format(contour_number), ROI)
contour_number += 1
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey()
It is correctly able to extract the numbers when written using marker.
Below is an example:
Original Image
Correctly extracting charachters
Image where it fails to read.
Original Image
Incorrectly Extracting

In this case, you only need to adjust your parameter.
Because there is no vertical line in your handwritten characters' background, so I decided to delete them.
# Remove border
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (50,1))
temp2 = 255 - cv2.morphologyEx(image, cv2.MORPH_CLOSE, horizontal_kernel)
result = cv2.add(temp2, image)
And it works.

The solution that CodingPeter has given is perfectly fine, except that it may not be generic apropos the two test images you have posted. So, here's my take on it that might work on both of your test images, albeit with a little lesser accuracy.
import numpy as np
import cv2
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (20, 20)
plt.rcParams["image.cmap"] = 'gray'
img_rgb = cv2.imread('path/to/your/image.jpg')
img = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)
th = cv2.adaptiveThreshold(img,255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,cv2.THRESH_BINARY_INV,11,2)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15,1))
horiz = cv2.morphologyEx(th, cv2.MORPH_OPEN, kernel, iterations=3)
ctrs, _ = cv2.findContours(horiz,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for ctr in ctrs:
x,y,w,h = cv2.boundingRect(ctr)
if w < 20:
cv2.drawContours(horiz, [ctr], 0, 0, cv2.FILLED)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,10))
vert = cv2.morphologyEx(th, cv2.MORPH_OPEN, kernel, iterations=3)
ctrs, _ = cv2.findContours(vert,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for ctr in ctrs:
x,y,w,h = cv2.boundingRect(ctr)
if h < 25:
cv2.drawContours(vert, [ctr], 0, 0, cv2.FILLED)
th = th - (horiz | vert)
ctrs, _ = cv2.findContours(th,cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
min_ctr_area = 400 # Min character bounding box area
for ctr in ctrs:
x, y, w, h = cv2.boundingRect(ctr)
# Filter contours based on size
if w * h > min_ctr_area and \
w < 100 and h < 100:
cv2.rectangle(img_rgb, (x, y), (x+w, y+h), (0, 255, 0), 1)
plt.imshow(img_rgb)
Of course some of the parameters here are hard-coded for filtering, which compare the contour height and width to ascertain whether it is a part of a line or maybe a character. With different images you may have to smartly change these values.

Related

OCR. Character segmentation stage

I am trying to implement one of the stages of the OCR system. The character segmentation stage. The code is shown below. The code is quite simple:
the image is being read
grayscale image translation
image binarization
application of dilation operation
selection of contours
It is assumed that each selected contour is a symbol.
The results of the algorithm are not satisfactory. Sometimes-the characters stand out well. Sometimes only parts of characters are highlighted, sometimes several characters are highlighted. Please help with the code, I really want it to correctly highlight the characters.
UPDATE 1. I am trying to implement a character segmentation system for different fonts. It turned out that there are no universal parameters of erosion and dilation operations for different fonts
Test image:
Result of character selection 1 (Small parts of characters):
Result of character selection 2 (Big parts of characters):
Full result (All parts of characters):
import cv2
import numpy as np
def letters_extract(image_file):
img = cv2.imread(image_file)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
img_dilate = cv2.dilate(thresh, np.ones((1, 1), np.uint8), iterations=1)
# img_erode = cv2.erode(img_dilate, np.ones((3, 3), np.uint8), iterations=1)
# Get contours
contours, hierarchy = cv2.findContours(img_dilate, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
letters = []
for idx, contour in enumerate(contours):
(x, y, w, h) = cv2.boundingRect(contour)
if hierarchy[0][idx][3] == 0:
letter_crop = gray[y:y + h, x:x + w]
letters.append(letter_crop)
cv2.imwrite(r'D:\projects\proj\test\tnr\{}.png'.format(idx), letter_crop)
return letters
letters_extract(r'D:\projects\proj\test\test_tnr.png')
Run your code (a bit modified for debugging) and it looks pretty good (I've only changed the dilation mask):
import cv2
import numpy as np
import matplotlib.pyplot as plt
def letters_extract(image_file):
img = cv2.imread(image_file)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
plt.figure(figsize=(20, 20))
plt.imshow(thresh)
plt.show()
img_dilate = cv2.erode(thresh, np.ones((2,1), np.uint8))
plt.figure(figsize=(20, 20))
plt.imshow(img_dilate)
plt.show()
contours, hierarchy = cv2.findContours(img_dilate, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
im_with_aabb = img.copy()
for idx, contour in enumerate(contours):
(x, y, w, h) = cv2.boundingRect(contour)
if hierarchy[0][idx][3] == 0:
color = (255, 0, 0)
thickness = 1
im_with_aabb = cv2.rectangle(im_with_aabb, (x,y), (x+w,y+h), color, thickness)
return im_with_aabb
im_with_aabb = letters_extract('test.png')
plt.figure(figsize=(20, 20))
plt.imshow(im_with_aabb)
plt.show()
But there are problems with several chars still. If your input images looks this good (no high variability between the same char in different places) I can suggest perhaps tamplate matching with each char as template.
If the data is with high variability maybe you should use a pretrained NN like tesseract.
If your data is always as clear as the image you have shared, you do not have to do dilation or erosion. I set threshold to 190 and inverse the gray image with cv2.THRESH_BINARY_INV parameter such that countours will be find around the letters. Finally, I change contour search algorithm to find only external contours with cv2.RETR_EXTERNAL parameter.
import cv2
import numpy as np
def letters_extract(image_file):
img = cv2.imread(image_file)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 190, 255, cv2.THRESH_BINARY_INV)
contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
letters = []
for idx, contour in enumerate(contours):
(x, y, w, h) = cv2.boundingRect(contour)
letter_crop = gray[y:y + h, x:x + w]
letters.append(letter_crop)
cv2.rectangle(img, (x,y), (x + w, y + h), (0,0,255))
cv2.namedWindow("win", cv2.WINDOW_FREERATIO)
cv2.imshow("win",img)
cv2.waitKey()
return letters
letters_extract('text.png')
Final image is as follows:

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:

Recognize single characters on a page with Tesseract

this image returns empty string;
basically I am trying to make a bot for WOW game, but I am really new to this OCR thing. I cannot make tesseract to read this image; I want an unordered list of characters and if possible coordinates of each square containing them. Is there anyway to do this?
Thank you for your time!
here is my code:
from PIL import Image
import cv2
from pytesseract import image_to_string
column = Image.open('photo.png')
gray = column.convert('L')
blackwhite = gray.point(lambda x: 255 if x < 200 else 0, '1')
blackwhite.save("code_bw.jpg")
print(image_to_string(cv2.imread("code_bw.jpg")))
You need to do some preprocessing to isolate the text characters. A simple approach is to Otsu's threshold to obtain a binary image then we can find contours and filter using aspect ratio + contour area. This will give us the bounding box coordinates of the text where we can draw this onto a mask. We bitwise-and the mask with the input image to get our cleaned image then throw it into OCR. Here's the result:
Detected text characters
Result
Result from OCR
A
A R
P
Code
import cv2
import pytesseract
import numpy as np
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
# Load image, grayscale, Otsu's threshold
image = cv2.imread('1.jpg')
original = image.copy()
mask = np.zeros(image.shape, dtype=np.uint8)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Find contours and filter using aspect ratio and area
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
area = cv2.contourArea(c)
x,y,w,h = cv2.boundingRect(c)
ar = w / float(h)
if area > 1000 and ar > .85 and ar < 1.2:
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
cv2.rectangle(mask, (x, y), (x + w, y + h), (255,255,255), -1)
ROI = original[y:y+h, x:x+w]
# Bitwise-and to isolate characters
result = cv2.bitwise_and(original, mask)
result[mask==0] = 255
# OCR
data = pytesseract.image_to_string(result, lang='eng',config='--psm 6')
print(data)
cv2.imshow('image', image)
cv2.imshow('thresh', thresh)
cv2.imshow('result', result)
cv2.waitKey()

How to separate images using watershed algorithm in Python

How to separate indiviual images among multiple images after image segmentaion using watershed algorithm in Python
The attached image is consists of 4 images , from which we need to apply image segmentation and separate individual image from those 4 images
We will flood fill it first
import cv2;
import numpy as np;
# Read image
im_in = cv2.imread("2SNAT.jpg", cv2.IMREAD_GRAYSCALE);
# Threshold.
# Set values equal to or above 220 to 0.
# Set values below 220 to 255.
th, im_th = cv2.threshold(im_in, 220, 255, cv2.THRESH_BINARY_INV);
# Copy the thresholded image.
im_floodfill = im_th.copy()
# Mask used to flood filling.
# Notice the size needs to be 2 pixels than the image.
h, w = im_th.shape[:2]
mask = np.zeros((h+2, w+2), np.uint8)
# Floodfill from point (0, 0)
cv2.floodFill(im_floodfill, mask, (0,0), 255);
# Invert floodfilled image
im_floodfill_inv = cv2.bitwise_not(im_floodfill)
# Combine the two images to get the foreground.
im_out = im_th | im_floodfill_inv
Then find contour and crop out
im, contours, hierarchy = cv2.findContours(im_out.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
final_contours = []
for contour in contours:
area = cv2.contourArea(contour)
if area > 1000:
final_contours.append(contour)
Crop out step, also drawing rectangle on original image
counter = 0
for c in final_contours:
counter = counter + 1
# for c in [final_contours[0]]:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.01 * peri, True)
x,y,w,h = cv2.boundingRect(approx)
print(x, y, w, h)
aspect_ratio = w / float(h)
if (aspect_ratio >= 0.8 and aspect_ratio <= 4):
cv2.rectangle(im_in,(x,y),(x+w,y+h),(0,255,0),2)
cv2.imwrite('splitted_{}.jpg'.format(counter), im_in[y:y+h, x:x+w])
cv2.imwrite('rectangled_split.jpg', im_in)
Instead of using watershed, here's a simple approach using thresholding + morphological operations. The idea is to obtain a binary image then perform morph close to combine each object as a single contour. We then find contours and extract/save each ROI using Numpy slicing.
Here's each individual object highlighted in green
Individual saved object
Code
import cv2
# Load image, grayscale, Otsu's threshold
image = cv2.imread('1.jpg')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Morph close
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7,7))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=3)
# Find contours and extract ROI
cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
num = 0
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
ROI = original[y:y+h, x:x+w]
cv2.imwrite('ROI_{}.png'.format(num), ROI)
num += 1
cv2.imshow('image', image)
cv2.waitKey()

Image thresholding in OpenCV

I have following image ,which is scanned image of A4 paper.What I need to do is to render individual characters from scanned image in to 28*28 or 32*32 image. I am doing it for dataset generation for Devanagari OCR. I applied simple threshing that doesn't help me.But when I applied adaptive threshing the result is not like expected.
After performing greyscaling and thresholding I get following thresholded image
My Final individual character image rendered are like
But my expected images(28*28) are was like ..
My source code is:
# grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# cv2.imshow('gray', gray)
# binary
#simple threshing
#ret, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV)
#cv2.imshow('threshold', thresh)
# adaptive threshing
thresh = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY_INV,11,6)
cv2.imshow('threshold', thresh)
# dilation
kernel = np.ones((10, 1), np.uint8)
img_dilation = cv2.dilate(thresh, kernel, iterations=1)
# 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]
roi = thresh[y:y + h, x:x + w]
# resizing
resize = cv2.resize(roi, (28, 28))
if w > 15 and h > 15:
cv2.imwrite(str(i) + str(time.time()) + '{}.png'.format(i), resize)
Please suggest me how to extract individual character in black and white 28*28 image for dataset collection.If you have any idea about dataset generation,It will be highly appriciated.
The problem is how you are finding contours.
An input parameter which requires Contour Retrieval Modes in a cv.findContours() (available options are)
cv.RETR_LIST, cv.RETR_TREE, cv.RETR_CCOMP, cv.RETR_EXTERNAL
cv.RETR_EXTERNAL only finds the outer most member in the nested contours family. More can be found here
So with your code at
if int(cv2MajorVersion) >= 4:
ctrs, hier = cv2.findContours(img_dilation.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
When drawing rectangles on contours shows
On changing contours retrieval code using cv2.RETR_LIST
if int(cv2MajorVersion) >= 4:
ctrs, hier = cv2.findContours(thresh.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
When drawing rectangles on contours shows
Later on, using your logic with the restricted size of contours
if w > 15 and h > 15: (on changing this dimension as needed) you can get you the images of characters
Edited
if (w > 20 and h > 20) and (w < 130 and h < 120):
cv2.imwrite(str(i) + str(time.time()) + '{}.png'.format(i), resize)
This works for me, gives nice pictures, black and white:
#!/usr/bin/env python
import cv2
counter = 0
img = cv2.imread( 'Downloads/dewangari.jpg' )
print img.shape #(2338, 1700, 3)
img = img[77:1942,91:1517]
img.shape # (1426, 1623, 3)
_, img = cv2.threshold( img[:,:,2], 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
x_size = img.shape[0] / 15
y_size = img.shape[1] / 8
for i in range(8) :
for j in range(15) :
cell = img[j*x_size+7:(j+1)*x_size-7,i*y_size+7:(i+1)*y_size-7]
cv2.imshow( 'frame', cell )
cell = (255 - cell) # this inverts the image
cv2.imwrite( 'image_%03d.png' % counter, cell)
counter += 1 # this saves the image
cv2.waitKey(0)
cv2.destroyAllWindows()
and so on ....

Categories

Resources