I am trying to extract handwritten characters from field boxes
My desired output would be the character segments with the boxes removed. So far, I've tried defining contours and filtering by area but that hasn't yielded any good results.
# Reading image and binarization
im = cv2.imread('test.png')
char_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
char_bw = cv2.adaptiveThreshold(char_gray, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 75, 10)
# Applying erosion and dilation
kernel = np.ones((5,5), np.uint8)
img_erosion = cv2.erode(char_bw, kernel, iterations=1)
img_dilation = cv2.dilate(img_erosion, kernel, iterations=1)
# Find Canny edges
edged = cv2.Canny(img_dilation, 100, 200)
# Finding Contours
edged_copy = edged.copy()
im2, cnts, hierarchy = cv2.findContours(edged_copy, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print("Number of Contours found = " + str(len(cnts)))
# Draw all contours
cv2.drawContours(im, cnts, -1, (0, 255, 0), 3)
# Filter using area and save
for no, c in enumerate(cnts):
area = cv2.contourArea(c)
if area > 100:
contour = c
(x, y, w, h) = cv2.boundingRect(contour)
img = im[y:y+h, x:x+w]
cv2.imwrite(f'./cnts/cnt-{no}.png', img_dilation)
Here's a simple approach:
Obtain binary image. We load the image, enlarge using imutils.resize(), convert to grayscale, and perform Otsu's thresholding to obtain a binary image
Remove horizontal lines. We create a horizontal kernel then perform morphological opening and remove the horizontal lines using cv2.drawContours
Remove vertical lines. We create a vertical kernel then perform morphological opening and remove the vertical lines using cv2.drawContours
Here's a visualization of each step:
Binary image
Detected lines/boxes to remove highlighted in green
Result
Code
import cv2
import numpy as np
import imutils
# Load image, enlarge, convert to grayscale, Otsu's threshold
image = cv2.imread('1.png')
image = imutils.resize(image, width=500)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Remove horizontal
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (25,1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(image, [c], -1, (255,255,255), 5)
# Remove vertical
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,25))
detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(image, [c], -1, (255,255,255), 5)
cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()
Related
I am new in computer vision, and I want to create a program which helps me to detect box in the image and save as an image.
and etc...
I tried some code but did not get my desired result.
here is my code and its output.
import cv2
# Load iamge, grayscale, adaptive threshold
image = cv2.imread('image.jpeg')
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,51,9)
# Fill rectangular contours
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:
cv2.drawContours(thresh, [c], -1, (255,255,255), -1)
# Morph open
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=4)
# Draw rectangles
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 3)
cv2.imshow('thresh', thresh)
cv2.imshow('opening', opening)
cv2.imshow('image', image)
cv2.waitKey()
output:
All you need to do is simply first remove the outermost white area, that is, make it black so that we can detect the boxes without any issues using the cv2.RETR_EXTERNAL flag as they are not touching. Then we'll just extract the boxes one by one.
To remove the outmost area, I have used the point polygon test of the contours. If the point (1, 1) lies inside or on a contour, it is not drawn and every other contour will be drawn on a new image. From this new image, I have read the box contours and extracted them.
import cv2
import numpy as np
img = cv2.imread("2lscp.png", cv2.IMREAD_GRAYSCALE)
ret, img = cv2.threshold(img, 50, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
Contours = cv2.findContours(img, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)[-2]
newImg = np.zeros(img.shape, dtype=np.uint8)
for Contour in Contours:
if cv2.pointPolygonTest(Contour, (1, 1), False) == -1:
cv2.drawContours(newImg, [Contour], -1, 255, 1)
Contours = cv2.findContours(newImg, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2]
for Contour in Contours:
[x, y, w, h] = cv2.boundingRect(Contour)
cv2.imshow("box extracted", img[y:y+h, x:x+w])
cv2.waitKey(0)
cv2.destroyAllWindows()
This case seems particularly simple because the image is quasi-binary. Detect the contours of the white regions and select those that have an area like 10 to 15% of the whole image. These are the desired boxes. Then fit a rectangle or rotated rectangle.
No need for additional processing.
Here is solution
try this:
import cv2
import numpy as np
#Read input image
img = cv2.imread('hw_data.png')
#convert from BGR to HSV color space
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#apply threshold
thresh = cv2.threshold(gray, 30, 255, cv2.THRESH_BINARY)[1]
# find contours and get one with area about 180*35
# draw all contours in green and accepted ones in red
contours = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
#area_thresh = 0
min_area = 0.95*180*44
max_area = 1.05*180*44
print(min_area)
print(max_area)
result = img.copy()
i = 1
for c in contours:
# print(c)
area = cv2.contourArea(c)
cv2.drawContours(result, [c], -1, (0, 255, 0), 1)
x,y,w,h = cv2.boundingRect(c)
# crop region of img using bounding box
region = result[y:y+h, x:x+w]
# save region to new image
print(region.shape,' i ',i)
# cv2.imwrite("black_region_{0}.png".format(i), region)
i = i + 1
if region.shape[0]>70 and region.shape[1]<100:
cv2.imwrite("black_region_{0}.png".format(i), region)
# break
# if area > min_area and area < max_area:
# cv2.drawContours(result, [c], -1, (0, 0, 255), 1)
# break
# save result
# cv2.imwrite("box_found.png", result)
# show images
# cv2.imshow("GRAY", gray)
# cv2.imshow("THRESH", thresh)
# cv2.imshow("RESULT", result)
# cv2.waitKey(0)
I have the image, i have removed the noise (dots in the background) and, I want to draw a bounding box around the block of text In image how can I do it using python OpenCV
Input image:
Noise Removed Image:
Here is the code used to remove noise in background Where i can change to save images with bounding boxes around the text
import cv2
import matplotlib.pyplot as plt
import glob
import os
def remove_dots(image_path,outdir):
image = cv2.imread(image_path)
mask = np.zeros(image.shape, dtype=np.uint8)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,51,9)
# Create horizontal kernel then dilate to connect text contours
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dilate = cv2.dilate(thresh, kernel, iterations=2)
# Find contours and filter out noise using contour approximation and area filtering
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.04 * peri, True)
x,y,w,h = cv2.boundingRect(c)
area = w * h
ar = w / float(h)
if area > 1200 and area < 50000 and ar <8:
cv2.drawContours(mask, [c], -1, (255,255,255), -1)
# Bitwise-and input image and mask to get result
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
result = cv2.bitwise_and(image, image, mask=mask)
result[mask==0] = (255,255,255) # Color background white
cv2.imwrite(os.path.join(outdir,os.path.basename(image_path)),result)
for jpgfile in glob.glob(r'C:\custom\TableDetectionWork\text_detection_dataset/*'):
print(jpgfile)
remove_dots(jpgfile,r'C:\custom\TableDetectionWork\textdetect/')
You can do that by using a horizontal morphology filter to merge the letters in a mask image. Then find the contours. Then get the bounding boxes.
Input:
import cv2
import numpy as np
img = cv2.imread("john.jpg")
# convert to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# threshold
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
# invert
thresh = 255 - thresh
# apply horizontal morphology close
kernel = np.ones((5 ,191), np.uint8)
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# draw contours
result = img.copy()
for cntr in contours:
# get bounding boxes
pad = 10
x,y,w,h = cv2.boundingRect(cntr)
cv2.rectangle(result, (x-pad, y-pad), (x+w+pad, y+h+pad), (0, 0, 255), 4)
# save result
cv2.imwrite("john_bbox.png",result)
# display result
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Morphology Closed Image:
Bounding Boxes Image:
Here is the core of your code modified to do what you want in Python/OpenCV. It is just adding my code to the end of your code.
Input:
import cv2
import numpy as np
image = cv2.imread("john.jpg")
mask = np.zeros(image.shape, dtype=np.uint8)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,51,9)
# Create horizontal kernel then dilate to connect text contours
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
dilate = cv2.dilate(thresh, kernel, iterations=2)
# Find contours and filter out noise using contour approximation and area filtering
cnts = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.04 * peri, True)
x,y,w,h = cv2.boundingRect(c)
area = w * h
ar = w / float(h)
if area > 1200 and area < 50000 and ar <8:
cv2.drawContours(mask, [c], -1, (255,255,255), -1)
# Bitwise-and input image and mask to get result
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
result = cv2.bitwise_and(image, image, mask=mask)
result[mask==0] = (255,255,255) # Color background white
# NEW CODE HERE TO END _____________________________________________________________
gray2 = cv2.cvtColor(result, cv2.COLOR_BGR2GRAY)
thresh2 = cv2.threshold(gray2, 128, 255, cv2.THRESH_BINARY)[1]
thresh2 = 255 - thresh2
kernel = np.ones((5 ,191), np.uint8)
close = cv2.morphologyEx(thresh2, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
# draw contours
result2 = result.copy()
for cntr in contours:
# get bounding boxes
pad = 10
x,y,w,h = cv2.boundingRect(cntr)
cv2.rectangle(result2, (x-pad, y-pad), (x+w+pad, y+h+pad), (0, 0, 255), 4)
cv2.imwrite("john_bboxes.jpg", result2)
cv2.imshow("mask",mask)
cv2.imshow("thresh",thresh)
cv2.imshow("dilate",dilate)
cv2.imshow("result",result)
cv2.imshow("gray2",gray2)
cv2.imshow("thresh2",thresh2)
cv2.imshow("close",close)
cv2.imshow("result2",result2)
cv2.waitKey(0)
cv2.destroyAllWindows()
Bounding Boxes on Your Result:
The image has 4 streams, how do we crop each stream, Disclaimer: The number of streams could be 4, 8, 16, 32
I have tried to develop an algorithm with the below steps.
Get horizontal and vertical lines
Draw on the line.
Find rectangle tiles using the find contours method from OpenCV
Crop each stream and save it into a different file.
But this approach does not hold true for a random number of streams.
Let me know your inputs on this.
import cv2
# Load image, convert to grayscale, Otsu's threshold
image = cv2.imread(r'C:\oldLaptopData\PF_2021\iotG_work\test_black\MSBlack.jpg')
#image = cv2.imread(r"C:\oldLaptopData\PF_2021\iotG_data\video_samples\split_frames\out1.jpg")
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Detect horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (200, 1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
print(len(cnts))
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 10)
# Detect vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, 200))
detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(result, [c], -1, (36,255,12), 10)
cv2.imwrite('result.jpg', result)
I am trying to extract handwritten numbers and alphabet from an image, for that i followed this stackoverflow link
but it is still not extracting the numbers and alphabet properly and picking up the border line as well.
You can find the result below:
Code:
import cv2
import imutils
# Load image, grayscale, Otsu's threshold
image = cv2.imread('xxx/ocr/pic_crop_2.png')
image = imutils.resize(image, width=375)
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)
_,thresh = cv2.threshold(gray, 120, 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]
for c in cnts:
x,y,w,h = cv2.boundingRect(c)
cv2.rectangle(img, (x, y), (x + w, y + h), (36,255,12), 2)
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey()
I tried to use dialate but no luck.
Please find the sample image below:
you Can Check the Contour Area For Fix That.
import cv2
# Load image, grayscale, Otsu's threshold
image = cv2.imread('pic_crop_2.png')
#image = cv2.resize(image, width=375)
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)
_,thresh = cv2.threshold(gray, 120, 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=200
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)
cv2.imshow('thresh', thresh)
cv2.imshow('img', img)
cv2.waitKey()
3x3 closing and binarization give good results, it seems (thought the black area is problematic and should be erased or cropped explicitly).
I have this code, that draws contours in my image, but I need only the external contours:
import cv2
import numpy as np
camino= "C:/Users/Usuario/Documents/Deteccion de Objetos/123.jpg"
img = cv2.imread("C:/Users/Usuario/Documents/Deteccion de Objetos/123.jpg")
grises= cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
bordes= cv2.Canny(grises, 100, 250)
ctns = cv2.findContours(bordes, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
ctns = ctns[0] if len(ctns)==2 else ctns[1]
for c in ctns:
cv2.drawContours(img,[c], -1,(0,0,255),2)
print ('Numero de contornos es ', len(ctns))
texto= 'Contornos encontrados ' + str(len(ctns))
cv2.putText(img, texto, (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.7,
(255, 0, 0), 1)
cv2.imshow('Bordes', bordes)
cv2.imshow('Imagen', img)
cv2.waitKey(0)
cv2.destroyAllWindows().
This is my original image:
This is the obtained image with the contours:
In this case I just only need to detect 10 contours 1 for each entity, but it detects 450 contours.
Here's an approach using thresholding + morphological operations + contour filtering
First we convert to grayscale then Otsu's threshold for a binary image (left) then remove dotted lines using contour area filtering (right)
From here we perform morph close to remove the text then invert the image (left). We find contours and fill all contours smaller than a threshold to black (right)
Next we invert again and perform morph open with a large rectangle kernel to remove the small edges and spikes
Finally we find contours to get our result
import cv2
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# Remove dotted lines
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)
if area < 5000:
cv2.drawContours(thresh, [c], -1, (0,0,0), -1)
# Fill contours
close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
close = 255 - cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, close_kernel, iterations=6)
cnts = cv2.findContours(close, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
area = cv2.contourArea(c)
if area < 15000:
cv2.drawContours(close, [c], -1, (0,0,0), -1)
# Smooth contours
close = 255 - close
open_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (20,20))
opening = cv2.morphologyEx(close, cv2.MORPH_OPEN, open_kernel, iterations=3)
# Find contours and draw result
cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
cv2.drawContours(image, [c], -1, (36,255,12), 3)
cv2.imshow('thresh', thresh)
cv2.imshow('opening', opening)
cv2.imshow('image', image)
cv2.waitKey()
You can try flood fill combined with some morph operators.