We Keep Coding

Combining 2 tresholded images to get this effect

I have the following 2 images:
How could I combine the images to get any of these 2 images?
My code:
import cv2
import numpy as np
image = cv2.imread('skadi.png')
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
cv2.imshow('greyscale',gray)
_, binary = cv2.threshold(gray, 100, 255, cv2.THRESH_BINARY)
cv2.imshow('treshold',binary)
binary= 255 - binary
cv2.imshow('inverted',binary)
kernel = np.ones((25, 25), np.uint8)
closing = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel)
cv2.imshow('closing',closing)
#closing = 255-closing
closing2 = cv2.bitwise_not(closing)
cv2.imshow('invetedclosing',closing2)
result = cv2.bitwise_or(closing, closing2)
cv2.imshow('convned',result)
edges = cv2.Canny(result, 100, 200)
cv2.waitKey(0)
cv2.destroyAllWindows()
I tried combining them wit cv2.bitwise_or and cv2.bitwise_xor, but ended with a white screen.
Any help appreciated!

Here's a handy script that basically extracts the biggest white blob in a binary image. Since the biggest white blob in your image is blob is the foreground (and the shape you are looking for), this should give you the expected result.
It basically gets all the external contours and keeps the contour with the biggest area. It then draws it on a new image.
This is the code, I'm using this image, since you did not provide the original.
# Imports:
import cv2
import numpy as np
# image path
path = "D://opencvImages//"
# Reading an image in default mode:
inputImage = cv2.imread(path + "testBlob.png")
# Grayscale conversion:
grayscaleImage = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Threshold via Otsu:
# Note the image inversion:
_, binaryImage = cv2.threshold(grayscaleImage, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
# Store a copy of the input image:
biggestBlob = binaryImage.copy()
# Set initial values for the
# largest contour:
largestArea = 0
largestContourIndex = 0
# Find the contours on the binary image:
contours, hierarchy = cv2.findContours(binaryImage, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
# Get the largest contour in the contours list:
for i, cc in enumerate(contours):
# Find the area of the contour:
area = cv2.contourArea(cc)
# Store the index of the largest contour:
if area > largestArea:
largestArea = area
largestContourIndex = i
# Once we get the biggest blob, paint it black:
tempMat = binaryImage.copy()
cv2.drawContours(tempMat, contours, largestContourIndex, (0, 0, 0), -1, 8, hierarchy)
# Erase smaller blobs:
biggestBlob = biggestBlob - tempMat
# Show the result:
cv2.imshow("biggestBlob", biggestBlob)
cv2.waitKey(0)
This is the result:

OpenCV - findContours on generated image doesn't work

I have an image of a graph. I perform some preprocessing functions on the image in order to extract the graph line (which works). I then, however, try to find the contour of the graph line that is found and saved as a separate image. When I do this, however, I do not get the desired results.
Graph line extracted
Contour found of the above image
import cv2
import numpy as np
import matplotlib.pyplot as plt
img = cv2.imread("/Users/2020shatgiskessell/Desktop/graph_extracting/Test_Graphs/Graph2.jpg")
h,w = img.shape[:2]
mask = np.zeros((h,w), np.uint8)
mask2 = mask = np.zeros((h,w), np.uint8)
def find_contours(image):
# Transform to gray colorspace and threshold the image
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
# erod then dialate image (for denoising)
kernel = np.ones((2,2),np.uint8)
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
#Find contours in order of hiarchy
#CHAIN_APPROX_NONE gives all the points on the contour
_, contours, hierarchy = cv2.findContours(opening,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE)
return contours
#---------------------------------------------------------------
#CLEAN UP IMAGE AND JUST EXTRACT LINE
#get the biggest contour
cnt = max(find_contours(img), key=cv2.contourArea)
cv2.drawContours(mask, [cnt], 0, 255, -1)
# Perform a bitwise operation
res = cv2.bitwise_and(img, img, mask=mask)
# Threshold the image again
gray = cv2.cvtColor(res,cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
# Find all non white pixels of image
non_zero = cv2.findNonZero(thresh)
# Transform all other pixels in non_white to white
for i in range(0, len(non_zero)):
first_x = non_zero[i][0][0]
first_y = non_zero[i][0][1]
first = res[first_y, first_x]
res[first_y, first_x] = 255
# Display the image
cv2.imwrite("extractedline.png", res)
#-------------------------------------------------------
#GET CONTOUR OF EXTRACTED LINE - NOT WORKING
i = 0
#Display contours
for contour in find_contours(res):
#approximate the contour shape
cv2.drawContours(mask2, [contour], 0, 255, -1)
res2 = cv2.bitwise_and(res,res,mask=mask2)
i = i+1
print (i)
cv2.imshow('after', mask2)

Is there a function similar to OpenCV findContours that detects curves and replaces points with a spline?

I am trying to take the below image, trace the white shape, and export the resulting path to pdf. The problem I have is that findContours seeming only finds points along the edge of the shape. Is there a solution out there, similar to findContours, that detects curves in a shape and replaces its points with a spline wherever there is a curve? If I use scipy.interpolate it ignores straight lines and turns the entire contour into one big curved shape, which is no good either. I need something that does both things.
import numpy as np
import cv2
from scipy.interpolate import splprep, splev
from pyx import *
import matplotlib.pyplot as plt
#read in image file
original = cv2.imread('test.jpg')
#blur the image to smooth edges
im = cv2.medianBlur(original,5)
#threshold the image
imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(imgray,170,255,cv2.THRESH_BINARY)
#findContours
im2, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_\
APPROX_SIMPLE)
#drawContours
cv2.drawContours(original, [approx], -1, (0,255,0), 3)
cv2.imshow("Imageee", original)
cv2.waitKey(0)

Except using cv2.findContours with flag cv2.CHAIN_APPROX_SIMPLE to approx the contours, we can do it manually.
use cv2.findContours with flag cv2.CHAIN_APPROX_NONE to find contours.
use cv2.arcLength to calculate the contour length.
use cv2.approxPoolyDP to approx the contour manually with epsilon = eps * arclen.
Here is one of the results when eps=0.005:
More results:
#!/usr/bin/python3
# 2018.01.04 13:01:24 CST
# 2018.01.04 14:42:58 CST
import cv2
import numpy as np
import os
img = cv2.imread("test.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,threshed = cv2.threshold(gray,170,255,cv2.THRESH_BINARY)
# find contours without approx
cnts = cv2.findContours(threshed,cv2.RETR_LIST,cv2.CHAIN_APPROX_NONE)[-2]
# get the max-area contour
cnt = sorted(cnts, key=cv2.contourArea)[-1]
# calc arclentgh
arclen = cv2.arcLength(cnt, True)
# do approx
eps = 0.0005
epsilon = arclen * eps
approx = cv2.approxPolyDP(cnt, epsilon, True)
# draw the result
canvas = img.copy()
for pt in approx:
cv2.circle(canvas, (pt[0][0], pt[0][1]), 7, (0,255,0), -1)
cv2.drawContours(canvas, [approx], -1, (0,0,255), 2, cv2.LINE_AA)
# save
cv2.imwrite("result.png", canvas)

I think your problem actually consists of two issues.
The first issue is to extract the contour, which you can achieve using teh findContour function:
import numpy as np
print cv2.__version__
rMaskgray = cv2.imread('test.jpg', 0)
(thresh, binRed) = cv2.threshold(rMaskgray, 200, 255, cv2.THRESH_BINARY)
_, Rcontours, hier_r = cv2.findContours(binRed,cv2.RETR_CCOMP,cv2.CHAIN_APPROX_SIMPLE)
r_areas = [cv2.contourArea(c) for c in Rcontours]
max_rarea = np.argmax(r_areas)
CntExternalMask = np.ones(binRed.shape[:2], dtype="uint8") * 255
contour= Rcontours[max_rarea]
cv2.drawContours(CntExternalMask,[contour],-1,0,1)
print "These are the contour points:"
print c
print
print "shape: ", c.shape
for p in contour:
print p[0][0]
cv2.circle(CntExternalMask, (p[0][0], p[0][1]), 5, (0,255,0), -1)
cv2.imwrite("contour.jpg", CntExternalMask)
cv2.imshow("Contour image", CntExternalMask)
cv2.waitKey(0)
If you execute the program, the contour points are printed as a list of point coordinates.
The contour approximation method you choose influences the interpolation which is actually used (and the number of points found), as described here. I have added small dots at the points found with the approximation method cv2.CHAIN_APPROX_SIMPLE. You see that the straight lines are already approximated.
I may not fully have understood your second step, though. You want to omit some of those points, replacing point lists partially by splines. There might be different way to do this, depending on your final intention. Do you just want to replace the straight lines? If you replace curved parts, what is the margin of error you are allowing?

# import the necessary packages
import numpy as np
import argparse
import glob
import cv2
#For saving pdf
def save_pdf(imagename):
import img2pdf
# opening from filename
with open("output.pdf","wb") as f:
f.write(img2pdf.convert(imagename))
#for fouind biggest contours
def bigercnt(contours):
max_area=0
cnt=[]
for ii in contours:
area=cv2.contourArea(ii)
if area>max_area:
cnt = ii
return cnt
#STARTING
print ("Reading img.jpg file")
# load the image, convert it to grayscale, and blur it slightly
image = cv2.imread('img.jpg')
image = cv2.resize(image, (0,0), fx=0.5, fy=0.5)
print ("Converting it gray scale")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
print ("Bluring")
blurred = cv2.GaussianBlur(gray, (3, 3), 0)
print ("Looking for edges" )
# apply Canny edge detection using a wide threshold, tight
# threshold, and automatically determined threshold
tight = cv2.Canny(blurred, 255, 250)
print ("Looking for contours")
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (10, 10))
close = cv2.morphologyEx(tight, cv2.MORPH_CLOSE, kernel)
_,contours, hierarchy = cv2.findContours( close.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
print("Looking for big contour")
cnt = bigercnt(contours)
print ("Cropping found contour")
x,y,w,h = cv2.boundingRect(cnt)
croped_image = image[y:y+h,x:x+w]
img2 = np.zeros((h,w,4),np.uint8)
print ("Taking only pixels in countour and creating png")
for i in range(h):
for j in range(w):
#print (x+j, y+i)
#print cv2.pointPolygonTest(cnt, (x+j, y+i), False)
if cv2.pointPolygonTest(cnt, (x+j, y+i), False)==1:
#print True
img2[i,j] = [croped_image[i, j][0],croped_image[i, j][1],croped_image[i, j][2],255]
else:
img2[i,j] = [255,255,255,0]
print ("Showing output image")
# Show the output image
#cv2.imshow('croped', croped_image)
cv2.imshow('output', img2)
params = list()
params.append(cv2.IMWRITE_PNG_COMPRESSION)
params.append(8)
print ("Saving output image")
cv2.imwrite("output.png",img2,params)
print ("Finish:converted")
cv2.waitKey(0)
cv2.destroyAllWindows()

OpenCV MSER detect text areas - Python

I have an invoice image, and I want to detect the text on it. So I plan to use 2 steps: first is to identify the text areas, and then using OCR to recognize the text.
I am using OpenCV 3.0 in python for that. I am able to identify the text(including some non text areas) but I further want to identify text boxes from the image(also excluding the non-text areas).
My input image is:
And the output is:
I am using the below code for this:
img = cv2.imread('/home/mis/Text_Recognition/bill.jpg')
mser = cv2.MSER_create()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #Converting to GrayScale
gray_img = img.copy()
regions = mser.detectRegions(gray, None)
hulls = [cv2.convexHull(p.reshape(-1, 1, 2)) for p in regions]
cv2.polylines(gray_img, hulls, 1, (0, 0, 255), 2)
cv2.imwrite('/home/mis/Text_Recognition/amit.jpg', gray_img) #Saving
Now, I want to identify the text boxes, and remove/unidentify any non-text areas on the invoice. I am new to OpenCV and am a beginner in Python. I am able to find some examples in MATAB example and C++ example, but If I convert them to python, it will take a lot of time for me.
Is there any example with python using OpenCV, or can anyone help me with this?

Below is the code
# Import packages
import cv2
import numpy as np
#Create MSER object
mser = cv2.MSER_create()
#Your image path i-e receipt path
img = cv2.imread('/home/rafiullah/PycharmProjects/python-ocr-master/receipts/73.jpg')
#Convert to gray scale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
vis = img.copy()
#detect regions in gray scale image
regions, _ = mser.detectRegions(gray)
hulls = [cv2.convexHull(p.reshape(-1, 1, 2)) for p in regions]
cv2.polylines(vis, hulls, 1, (0, 255, 0))
cv2.imshow('img', vis)
cv2.waitKey(0)
mask = np.zeros((img.shape[0], img.shape[1], 1), dtype=np.uint8)
for contour in hulls:
cv2.drawContours(mask, [contour], -1, (255, 255, 255), -1)
#this is used to find only text regions, remaining are ignored
text_only = cv2.bitwise_and(img, img, mask=mask)
cv2.imshow("text only", text_only)
cv2.waitKey(0)

This is an old post, yet I'd like to contribute that if you are trying to extract all the texts out of an image, here is the code to get that text in an array.
import cv2
import numpy as np
import re
import pytesseract
from pytesseract import image_to_string
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
from PIL import Image
image_obj = Image.open("screenshot.png")
rgb = cv2.imread('screenshot.png')
small = cv2.cvtColor(rgb, cv2.COLOR_BGR2GRAY)
#threshold the image
_, bw = cv2.threshold(small, 0.0, 255.0, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# get horizontal mask of large size since text are horizontal components
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (20, 1))
connected = cv2.morphologyEx(bw, cv2.MORPH_CLOSE, kernel)
# find all the contours
contours, hierarchy,=cv2.findContours(connected.copy(),cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
#Segment the text lines
counter=0
array_of_texts=[]
for idx in range(len(contours)):
x, y, w, h = cv2.boundingRect(contours[idx])
cropped_image = image_obj.crop((x-10, y, x+w+10, y+h ))
str_store = re.sub(r'([^\s\w]|_)+', '', image_to_string(cropped_image))
array_of_texts.append(str_store)
counter+=1
print(array_of_texts)

How to create a shapefile after watershed segmentation using python

After using watershed segmentation in opencv-python, I would like to create vector objects (objects in the blue circle) and save it into shapefile but I don't know how to do this in python. Please help me how to solve this.
import cv2
import numpy as np
import scipy.misc
import scipy.ndimage as snd
# image is read and is converted to a numpy array
img = cv2.imread('D:/exam_watershed/Example_2_medicine/Medicine_create_poly/medicine.jpg')
# image is convereted to grayscale
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# binary thresholding is done using the threshold
# from Otsu's method
ret1,thresh1 = cv2.threshold(gray,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# foreground pixels are determined by
# performing erosion
fore_ground = cv2.erode(thresh1,None,iterations = 3)
bgt = cv2.dilate(thresh1,None,iterations = 3)
ret,back_ground = cv2.threshold(bgt,1,100,1)
# marker is determined by adding foreground and background pixels
marker = cv2.add(fore_ground,back_ground)
# converting marker to 32 int
marker32 = np.int32(marker)
cv2.watershed(img,marker32)
m = cv2.convertScaleAbs(marker32) #the output is converted to unit8 image
ret3,thresh3 = cv2.threshold(gray,0,255,\
cv2.THRESH_BINARY+cv2.THRESH_OTSU)
_, contours1, _= cv2.findContours(thresh3,cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
polys = []
for cont in contours1:
approx_curve = cv2.approxPolyDP(cont, 3, False)
polys.append(approx_curve)
cv2.drawContours(img, polys, -1, (0, 255, 0), thickness=1, lineType=8)