Develop Reference

How to stitch the two images more accurately?

I'm doing a "Circle View"(Bird View) system for a long truck. Due to the fact that the car is long on the sides of one camera is not enough. I decided to try to put two cameras and sew them, but there is a drawback. the code that I use stitches the image is not quite even and the joint is visible. How can I change the code to make the joint was less visible and sewn better? A chessboard with a size of 4x6. It stands in the middle of two video cameras. Maybe there's a way to stitch on a checkerboard?
Here's my stitching result:
Here are two images to be stitched together:
1 image:
2 image:
The code I have now:
import cv2 as cv
import numpy as np
def FindHomography(Matches, BaseImage_kp, SecImage_kp):
# If less than 4 matches found, exit the code.
if len(Matches) < 4:
print("\nNot enough matches found between the images.\n")
exit(0)
# Storing coordinates of points corresponding to the matches found in both the images
BaseImage_pts = []
SecImage_pts = []
for Match in Matches:
BaseImage_pts.append(BaseImage_kp[Match[0].queryIdx].pt)
SecImage_pts.append(SecImage_kp[Match[0].trainIdx].pt)
# Changing the datatype to "float32" for finding homography
BaseImage_pts = np.float32(BaseImage_pts)
SecImage_pts = np.float32(SecImage_pts)
# Finding the homography matrix(transformation matrix).
(HomographyMatrix, Status) = cv.findHomography(SecImage_pts, BaseImage_pts, cv.RANSAC, 4.0)
return HomographyMatrix, Status
def GetNewFrameSizeAndMatrix(HomographyMatrix, Sec_ImageShape, Base_ImageShape):
# Reading the size of the image
(Height, Width) = Sec_ImageShape
# Taking the matrix of initial coordinates of the corners of the secondary image
# Stored in the following format: [[x1, x2, x3, x4], [y1, y2, y3, y4], [1, 1, 1, 1]]
# Where (xi, yi) is the coordinate of the i th corner of the image.
InitialMatrix = np.array([[0, Width - 1, Width - 1, 0],
[0, 0, Height - 1, Height - 1],
[1, 1, 1, 1]])
# Finding the final coordinates of the corners of the image after transformation.
# NOTE: Here, the coordinates of the corners of the frame may go out of the
# frame(negative values). We will correct this afterwards by updating the
# homography matrix accordingly.
FinalMatrix = np.dot(HomographyMatrix, InitialMatrix)
[x, y, c] = FinalMatrix
x = np.divide(x, c)
y = np.divide(y, c)
# Finding the dimentions of the stitched image frame and the "Correction" factor
min_x, max_x = int(round(min(x))), int(round(max(x)))
min_y, max_y = int(round(min(y))), int(round(max(y)))
New_Width = max_x
New_Height = max_y
Correction = [0, 0]
if min_x < 0:
New_Width -= min_x
Correction[0] = abs(min_x)
if min_y < 0:
New_Height -= min_y
Correction[1] = abs(min_y)
# Again correcting New_Width and New_Height
# Helpful when secondary image is overlaped on the left hand side of the Base image.
if New_Width < Base_ImageShape[1] + Correction[0]:
New_Width = Base_ImageShape[1] + Correction[0]
if New_Height < Base_ImageShape[0] + Correction[1]:
New_Height = Base_ImageShape[0] + Correction[1]
# Finding the coordinates of the corners of the image if they all were within the frame.
x = np.add(x, Correction[0])
y = np.add(y, Correction[1])
OldInitialPoints = np.float32([[0, 0],
[Width - 1, 0],
[Width - 1, Height - 1],
[0, Height - 1]])
NewFinalPonts = np.float32(np.array([x, y]).transpose())
# Updating the homography matrix. Done so that now the secondary image completely
# lies inside the frame
HomographyMatrix = cv.getPerspectiveTransform(OldInitialPoints, NewFinalPonts)
return [New_Height, New_Width], Correction, HomographyMatrix
ratio_thresh = 0.9
image1 = cv.imread(filename='/home/msi-user/PycharmProjects/170Camera/1_camera.jpg')
image2 = cv.imread(filename='/home/msi-user/PycharmProjects/170Camera/2_camera.jpg')
# -----------------------------------------KAZE--------------------------------#
AKAZE = cv.KAZE_create() # KAZE, AKAZE, ORB, BRISK, xfeatures2d.SURF
keypoints1, descriptors1 = AKAZE.detectAndCompute(image1, None)
keypoints2, descriptors2 = AKAZE.detectAndCompute(image2, None)
FLANN_INDEX_KDTREE = 1
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50)
descriptors1 = np.float32(descriptors1)
descriptors2 = np.float32(descriptors2)
FLANN = cv.FlannBasedMatcher(indexParams=index_params,
searchParams=search_params)
matches = FLANN.knnMatch(queryDescriptors=descriptors1,
trainDescriptors=descriptors2,
k=2)
good_matches = []
t = []
for m, n in matches:
if m.distance < ratio_thresh * n.distance:
good_matches.append([m])
t.append(m)
output = cv.drawMatches(img1=image1,
keypoints1=keypoints1,
img2=image2,
keypoints2=keypoints2,
matches1to2=t,
outImg=None,
flags=cv.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS)
cv.namedWindow("drawMatches.jpg", cv.WINDOW_NORMAL)
cv.imshow("drawMatches.jpg", output)
# ----------------------------------FindHomography-------------------------------------------#
HomographyMatrix, Status = FindHomography(good_matches, keypoints1, keypoints2)
BaseImage = image1
SecImage = image2
NewFrameSize, Correction, HomographyMatrix = GetNewFrameSizeAndMatrix(HomographyMatrix, SecImage.shape[:2],
BaseImage.shape[:2])
StitchedImage = cv.warpPerspective(SecImage, HomographyMatrix, (NewFrameSize[1], NewFrameSize[0]))
StitchedImage[Correction[1]:Correction[1] + BaseImage.shape[0],
Correction[0]:Correction[0] + BaseImage.shape[1]] = BaseImage
cv.namedWindow("stisched2.jpg", cv.WINDOW_NORMAL)
cv.imshow("stisched2.jpg", StitchedImage)
cv.imwrite("result.jpg", StitchedImage)
while True:
if cv.waitKey(1) == 27:
break

Finding an unfilled circle in an image of finite size using Python

Trying to find a circle in an image that has finite radius. Started off using 'HoughCircles' method from OpenCV as the parameters for it seemed very much related to my situation. But it is failing to find it. Looks like the image may need more pre-processing for it to find reliably. So, started off playing with different thresholds in opencv to no success. Here is an example of an image (note that the overall intensity of the image will vary, but the radius of the circle always remain the same ~45pixels)
Here is what I have tried so far
image = cv2.imread('image1.bmp', 0)
img_in = 255-image
mean_val = int(np.mean(img_in))
ret, img_thresh = cv2.threshold(img_in, thresh=mean_val-30, maxval=255, type=cv2.THRESH_TOZERO)
# detect circle
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.0, 100, minRadius=40, maxRadius=50)
If you look at the image, the circle is obvious, its a thin light gray circle in the center of the blob.
Any suggestions?
Edited to show expected result
The expected result should be like this, as you can see, the circle is very obvious for naked eye on the original image and is always of the same radius but not at the same location on the image. But there will be only one circle of this kind on any given image.
As of 8/20/2020, here is the code I am using to get the center and radii
from numpy import zeros as np_zeros,\
full as np_full
from cv2 import calcHist as cv2_calcHist,\
HoughCircles as cv2_HoughCircles,\
HOUGH_GRADIENT as cv2_HOUGH_GRADIENT
def getCenter(img_in, saturated, minradius, maxradius):
img_local = img_in[100:380,100:540,0]
res = np_full(3, -1)
# do some contrast enhancement
img_local = stretchHistogram(img_local, saturated)
circles = cv2_HoughCircles(img_local, cv2_HOUGH_GRADIENT, 1, 40, param1=70, param2=20,
minRadius=minradius,
maxRadius=maxradius)
if circles is not None: # found some circles
circles = sorted(circles[0], key=lambda x: x[2])
res[0] = circles[0][0]+100
res[1] = circles[0][1]+100
res[2] = circles[0][2]
return res #x,y,radii
def stretchHistogram(img_in, saturated=0.35, histMin=0.0, binSize=1.0):
img_local = img_in.copy()
img_out = img_in.copy()
min, max = getMinAndMax(img_local, saturated)
if max > min:
min = histMin+min * binSize
max = histMin+max * binSize
w, h = img_local.shape[::-1]
#create a new lut
lut = np_zeros(256)
max2 = 255
for i in range(0, 256):
if i <= min:
lut[i] = 0
elif i >= max:
lut[i] = max2
else:
lut[i] = (round)(((float)(i - min) / (max - min)) * max2)
#update image with new lut values
for i in range(0, h):
for j in range(0, w):
img_out[i, j] = lut[img_local[i, j]]
return img_out
def getMinAndMax(img_in, saturated):
img_local = img_in.copy()
hist = cv2_calcHist([img_local], [0], None, [256], [0, 256])
w, h = img_local.shape[::-1]
pixelCount = w * h
saturated = 0.5
threshold = (int)(pixelCount * saturated / 200.0)
found = False
count = 0
i = 0
while not found and i < 255:
count += hist[i]
found = count > threshold
i = i + 1
hmin = i
i = 255
count = 0
while not found and i > 0:
count += hist[i]
found = count > threshold
i = i - 1
hmax = i
return hmin, hmax
and calling the above function as
getCenter(img, 5.0, 55, 62)
But it is still very unreliable. Not sure why it is so hard to get to an algorithm that works reliably for something that is very obvious to a naked eye. Not sure why there is so much variation in the result from frame to frame even though there is no change between them.
Any suggestions are greatly appreciated. Here are some more samples to play with

simple, draw your circles: cv2.HoughCircles returns a list of circles..
take care of maxRadius = 100
for i in circles[0,:]:
# draw the outer circle
cv2.circle(image,(i[0],i[1]),i[2],(255,255,0),2)
# draw the center of the circle
cv2.circle(image,(i[0],i[1]),2,(255,0,255),3)
a full working code (you have to change your tresholds):
import cv2
import numpy as np
image = cv2.imread('0005.bmp', 0)
height, width = image.shape
print(image.shape)
img_in = 255-image
mean_val = int(np.mean(img_in))
blur = cv2.blur(img_in , (3,3))
ret, img_thresh = cv2.threshold(blur, thresh=100, maxval=255, type=cv2.THRESH_TOZERO)
# detect circle
circles = cv2.HoughCircles(img_thresh, cv2.HOUGH_GRADIENT,1,40,param1=70,param2=20,minRadius=60,maxRadius=0)
print(circles)
for i in circles[0,:]:
# check if center is in middle of picture
if(i[0] > width/2-30 and i[0] < width/2+30 \
and i[1] > height/2-30 and i[1] < height/2+30 ):
# draw the outer circle
cv2.circle(image,(i[0],i[1]),i[2],(255,255,0),2)
# draw the center of the circle
cv2.circle(image,(i[0],i[1]),2,(255,0,255),3)
cv2.imshow("image", image )
while True:
keyboard = cv2.waitKey(2320)
if keyboard == 27:
break
cv2.destroyAllWindows()
result:

Pixels intensity values between two lines

I have created an alghoritm that detects the edges of an extruded colagen casing and draws a centerline between these edges on an image. Casing with a centerline.
Here is my code:
import numpy as np
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
img = cv2.imread("C:/Users/5.jpg", cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (1500, 1200))
#ROI
fromCenter = False
r = cv2.selectROI(img, fromCenter)
imCrop = img[int(r[1]):int(r[1]+r[3]), int(r[0]):int(r[0]+r[2])]
#Operations on an image
_,thresh = cv2.threshold(imCrop,100,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
kernel = np.ones((5,5),np.uint8)
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
blur = cv2.GaussianBlur(opening,(7,7),0)
edges = cv2.Canny(blur, 0,20)
#Edges localization, packing coords into a list
indices = np.where(edges != [0])
coordinates = list(zip(indices[1], indices[0]))
num = len(coordinates)
#Separating into top and bot edge
bot_cor = coordinates[:int(num/2)]
top_cor = coordinates[-int(num/2):]
#Converting to arrays, sorting
a, b = np.array(top_cor), np.array(bot_cor)
a, b = a[a[:,0].argsort()], b[b[:,0].argsort()]
#Edges approximation by a 5th degree polynomial
min_a_x, max_a_x = np.min(a[:,0]), np.max(a[:,0])
new_a_x = np.linspace(min_a_x, max_a_x, imCrop.shape[1])
a_coefs = np.polyfit(a[:,0],a[:,1], 5)
new_a_y = np.polyval(a_coefs, new_a_x)
min_b_x, max_b_x = np.min(b[:,0]), np.max(b[:,0])
new_b_x = np.linspace(min_b_x, max_b_x, imCrop.shape[1])
b_coefs = np.polyfit(b[:,0],b[:,1], 5)
new_b_y = np.polyval(b_coefs, new_b_x)
#Defining a centerline
midx = [np.average([new_a_x[i], new_b_x[i]], axis = 0) for i in range(imCrop.shape[1])]
midy = [np.average([new_a_y[i], new_b_y[i]], axis = 0) for i in range(imCrop.shape[1])]
plt.figure(figsize=(16,8))
plt.title('Cross section')
plt.xlabel('Length of the casing', fontsize=18)
plt.ylabel('Width of the casing', fontsize=18)
plt.plot(new_a_x, new_a_y,c='black')
plt.plot(new_b_x, new_b_y,c='black')
plt.plot(midx, midy, '-', c='blue')
plt.show()
#Converting coords type to a list (plotting purposes)
coords = list(zip(midx, midy))
points = list(np.int_(coords))
mask = np.zeros((imCrop.shape[:2]), np.uint8)
mask = edges
#Plotting
for point in points:
cv2.circle(mask, tuple(point), 1, (255,255,255), -1)
for point in points:
cv2.circle(imCrop, tuple(point), 1, (255,255,255), -1)
cv2.imshow('imCrop', imCrop)
cv2.imshow('mask', mask)
cv2.waitKey(0)
cv2.destroyAllWindows()
Now I would like to sum up the intensities of each pixel in a region between top edge and a centerline (same thing for a region between centerline and a bottom edge).
Is there any way to limit the ROI to the region between the detected edges and split it into two regions based on the calculated centerline?
Or is there any way to access the pixels which are contained between the edge and a centerline based on theirs coordinates?
(It's my very first post here, sorry in advance for all the mistakes)

I wrote a somewhat naïve code to get masks for the upper and lower part. My code considers that the source image will be always like yours: with horizontal stripes.
After applying Canny I get this:
Then I run some loops through image array to fill unwanted areas of your image. This is done separately for upper and lower part, creating masks. The results are:
Then you can use this masks to sum only the elements you're interested in, using cv.sumElems.
import cv2 as cv
#open as grayscale image
src = cv.imread("colagen.png",cv.IMREAD_GRAYSCALE)
# apply canny and find contours
threshold = 100
canny_output = cv.Canny(src, threshold, threshold * 2)
# find mask for upper part
mask1 = canny_output.copy()
x, y = canny_output.shape
area = 0
for j in range(y):
area = 0
for i in range(x):
if area == 0:
if mask1[i][j] > 0:
area = 1
continue
else:
mask1[i][j] = 255
elif area == 1:
if mask1[i][j] > 0:
area = 2
else:
continue
else:
mask1[i][j] = 255
mask1 = cv.bitwise_not(mask1)
# find mask for lower part
mask2 = canny_output.copy()
x, y = canny_output.shape
area = 0
for j in range(y):
area = 0
for i in range(x):
if area == 0:
if mask2[-i][j] > 0:
area = 1
continue
else:
mask2[-i][j] = 255
elif area == 1:
if mask2[-i][j] > 0:
area = 2
else:
continue
else:
mask2[-i][j] = 255
mask2 = cv.bitwise_not(mask2)
# apply masks and calculate sum of elements in upper and lower part
sums = [0,0]
(sums[0],_,_,_) = cv.sumElems(cv.bitwise_and(src,mask1))
(sums[1],_,_,_) = cv.sumElems(cv.bitwise_and(src,mask2))
cv.imshow('src',src)
cv.imshow('canny',canny_output)
cv.imshow('mask1',mask1)
cv.imshow('mask2',mask2)
cv.imshow('masked1',cv.bitwise_and(src,mask1))
cv.imshow('masked2',cv.bitwise_and(src,mask2))
cv.waitKey()
Alternatives...
Probably there exist some function that fill the areas of the Canny result. I tried cv.fillPoly and cv.floodFill, but didn't manage to make them work easily... But maybe someone else can help you with that...
Edit
Found another way to get the masks with a cleaner code. Using numpy np.add.accumulate then np.clip, and then a modulo operation:
# first divide canny_output by 255 to get 0's and 1's, then perform
# an accumulate addition for each column. Thus you'll get +1 for every
# line, "painting" areas with 1, 2, 3...
a = np.add.accumulate(canny_output/255,0)
# clip values: anything greater than 2 becomes 2
a = np.clip(a, 0, 2)
# performe a modulo, to get areas alternating with 0 or 1; then multiply by 255
a = a%2 * 255
# convert to uint8
mask1 = cv.convertScaleAbs(a)
# to get mask2 (the lower mask) flip the array then do the same as above
a = np.add.accumulate(np.flip(canny_output,0)/255,0)
a = np.clip(a, 0, 2)
a = a%2 * 255
mask2 = cv.convertScaleAbs(np.flip(a,0))
This returns almost the same result. The border of the mask is a little bit different...

Extracting data from tables without any grid lines and border from scanned image of document

Extracting table data from digital PDFs have been simple using camelot and tabula. However, the solution doesn't work with scanned images of the document pages specifically when the table doesn't have borders and inner grids. I have been trying to generate vertical and horizontal lines using OpenCV. However, since the scanned images will have slight rotation angles, it is difficult to proceed with the approach.
How can we utilize OpenCV to generate grids (horizontal and vertical lines) and borders for the scanned document page which contains table data (along with paragraphs of text)? If this is feasible, how to nullify the rotation angle of the scanned image?

I wrote some code to estimate the horizontal lines from the printed letters in the page. The same could be done for vertical ones I guess. The code below follows some general assumptions, here
some basic steps in pseudo code style:
prepare picture for contour detection
do contour detection
we assume most contours are letters
calc mean width of all contours
calc mean area of contours
filter all contours with two conditions:
a) contour (letter) heigths < meanHigh * 2
b) contour area > 4/5 meanArea
calc center point of all remaining contours
assume we have line regions (bins)
list all center point which are inside the region
do linear regression of region points
save slope and intercept
calc mean slope and intercept
here the full code:
import cv2
import numpy as np
from scipy import stats
def resizeImageByPercentage(img,scalePercent = 60):
width = int(img.shape[1] * scalePercent / 100)
height = int(img.shape[0] * scalePercent / 100)
dim = (width, height)
# resize image
return cv2.resize(img, dim, interpolation = cv2.INTER_AREA)
def calcAverageContourWithAndHeigh(contourList):
hs = list()
ws = list()
for cnt in contourList:
(x, y, w, h) = cv2.boundingRect(cnt)
ws.append(w)
hs.append(h)
return np.mean(ws),np.mean(hs)
def calcAverageContourArea(contourList):
areaList = list()
for cnt in contourList:
a = cv2.minAreaRect(cnt)
areaList.append(a[2])
return np.mean(areaList)
def calcCentroid(contour):
houghMoments = cv2.moments(contour)
# calculate x,y coordinate of centroid
if houghMoments["m00"] != 0: #case no contour could be calculated
cX = int(houghMoments["m10"] / houghMoments["m00"])
cY = int(houghMoments["m01"] / houghMoments["m00"])
else:
# set values as what you need in the situation
cX, cY = -1, -1
return cX,cY
def getCentroidWhenSizeInRange(contourList,letterSizeWidth,letterSizeHigh,deltaOffset,minLetterArea=10.0):
centroidList=list()
for cnt in contourList:
(x, y, w, h) = cv2.boundingRect(cnt)
area = cv2.minAreaRect(cnt)
#calc diff
diffW = abs(w-letterSizeWidth)
diffH = abs(h-letterSizeHigh)
#thresold A: almost smaller than mean letter size +- offset
#when almost letterSize
if diffW < deltaOffset and diffH < deltaOffset:
#threshold B > min area
if area[2] > minLetterArea:
cX,cY = calcCentroid(cnt)
if cX!=-1 and cY!=-1:
centroidList.append((cX,cY))
return centroidList
DEBUGMODE = True
#read image, do git clone https://github.com/WZBSocialScienceCenter/pdftabextract.git for the example
img = cv2.imread('pdftabextract/examples/catalogue_30s/data/ALA1934_RR-excerpt.pdf-2_1.png')
#get some basic infos
imgHeigh, imgWidth, imgChannelAmount = img.shape
if DEBUGMODE:
cv2.imwrite("img00original.jpg",resizeImageByPercentage(img,30))
cv2.imshow("original",img)
# prepare img
imgGrey = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# apply Gaussian filter
imgGaussianBlur = cv2.GaussianBlur(imgGrey,(5,5),0)
#make binary img, black or white
_, imgBinThres = cv2.threshold(imgGaussianBlur, 130, 255, cv2.THRESH_BINARY)
## detect contours
contours, _ = cv2.findContours(imgBinThres, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#we get some letter parameter
averageLetterWidth, averageLetterHigh = calcAverageContourWithAndHeigh(contours)
threshold1AllowedLetterSizeOffset = averageLetterHigh * 2 # double size
averageContourAreaSizeOfMinRect = calcAverageContourArea(contours)
threshHold2MinArea = 4 * averageContourAreaSizeOfMinRect / 5 # 4/5 * mean
print("mean letter Width: ", averageLetterWidth)
print("mean letter High: ", averageLetterHigh)
print("threshold 1 tolerance: ", threshold1AllowedLetterSizeOffset)
print("mean letter area ", averageContourAreaSizeOfMinRect)
print("thresold 2 min letter area ", threshHold2MinArea)
#we get all centroid of letter sizes contours, the other we ignore
centroidList = getCentroidWhenSizeInRange(contours,averageLetterWidth,averageLetterHigh,threshold1AllowedLetterSizeOffset,threshHold2MinArea)
if DEBUGMODE:
#debug print all centers:
imgFilteredCenter = img.copy()
for cX,cY in centroidList:
#draw in red color as BGR
cv2.circle(imgFilteredCenter, (cX, cY), 5, (0, 0, 255), -1)
cv2.imwrite("img01letterCenters.jpg",resizeImageByPercentage(imgFilteredCenter,30))
cv2.imshow("letterCenters",imgFilteredCenter)
#we estimate a bin widths
amountPixelFreeSpace = averageLetterHigh #TODO get better estimate out of histogram
estimatedBinWidth = round( averageLetterHigh + amountPixelFreeSpace) #TODO round better ?
binCollection = dict() #range(0,imgHeigh,estimatedBinWidth)
#we do seperate the center points into bins by y coordinate
for i in range(0,imgHeigh,estimatedBinWidth):
listCenterPointsInBin = list()
yMin = i
yMax = i + estimatedBinWidth
for cX,cY in centroidList:
if yMin < cY < yMax:#if fits in bin
listCenterPointsInBin.append((cX,cY))
binCollection[i] = listCenterPointsInBin
#we assume all point are in one line ?
#model = slope (x) + intercept
#model = m (x) + n
mList = list() #slope abs in img
nList = list() #intercept abs in img
nListRelative = list() #intercept relative to bin start
minAmountRegressionElements = 12 #is also alias for letter amount we expect
#we do regression for every point in the bin
for startYOfBin, values in binCollection.items():
#we reform values
xValues = [] #TODO use more short transform
yValues = []
for x,y in values:
xValues.append(x)
yValues.append(y)
#we assume a min limit of point in bin
if len(xValues) >= minAmountRegressionElements :
slope, intercept, r, p, std_err = stats.linregress(xValues, yValues)
mList.append(slope)
nList.append(intercept)
#we calc the relative intercept
nRelativeToBinStart = intercept - startYOfBin
nListRelative.append(nRelativeToBinStart)
if DEBUGMODE:
#we debug print all lines in one picute
imgLines = img.copy()
colorOfLine = (0, 255, 0) #green
for i in range(0,len(mList)):
slope = mList[i]
intercept = nList[i]
startPoint = (0, int( intercept)) #better round ?
endPointY = int( (slope * imgWidth + intercept) )
if endPointY < 0:
endPointY = 0
endPoint = (imgHeigh,endPointY)
cv2.line(imgLines, startPoint, endPoint, colorOfLine, 2)
cv2.imwrite("img02lines.jpg",resizeImageByPercentage(imgLines,30))
cv2.imshow("linesOfLetters ",imgLines)
#we assume in mean we got it right
meanIntercept = np.mean(nListRelative)
meanSlope = np.mean(mList)
print("meanIntercept :", meanIntercept)
print("meanSlope ", meanSlope)
#TODO calc angle with math.atan(slope) ...
if DEBUGMODE:
cv2.waitKey(0)
original:
center point of letters:
lines:

I had the same problem some time ago and this tutorial is the solution to that. It explains using pdftabextract which is a Python library by Markus Konrad and leverages OpenCV’s Hough transform to detect the lines and works even if the scanned document is a bit tilted. The tutorial walks your through parsing a 1920s German newspaper

Unable to find enough matches between two images to stitch them both

I'm trying to stitch two images together, but I'm failing to do so because the program doesn't detect enough matches between the two images
Here's the code:
import numpy as np
import imutils
import cv2
class Stitcher:
def __init__(self):
self.isv3 = imutils.is_cv3()
def stitch(self, images, ratio=0.75, reprojThresh=5.0,
showMatches=False):
(imageB, imageA) = images
(kpsA, featuresA) = self.detectAndDescribe(imageA)
(kpsB, featuresB) = self.detectAndDescribe(imageB)
M = self.matchKeypoints(kpsA, kpsB,
featuresA, featuresB, ratio, reprojThresh)
if M is None:
return None
(matches, H, status) = M
result = cv2.warpPerspective(imageA, H,
(imageA.shape[1] + imageB.shape[1], imageA.shape[0]))
result[0:imageB.shape[0], 0:imageB.shape[1]] = imageB
if showMatches:
vis = self.drawMatches(imageA, imageB, kpsA, kpsB, matches,
status)
return (result, vis)
return result
def detectAndDescribe(self, image):
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
if self.isv3:
descriptor = cv2.xfeatures2d.SIFT_create()
(kps, features) = descriptor.detectAndCompute(image, None)
else:
detector = cv2.FeatureDetector_create("SIFT")
kps = detector.detect(gray)
# extract features from the image
extractor = cv2.DescriptorExtractor_create("SIFT")
(kps, features) = extractor.compute(gray, kps)
# convert the keypoints from KeyPoint objects to NumPy
# arrays
kps = np.float32([kp.pt for kp in kps])
# return a tuple of keypoints and features
return (kps, features)
def matchKeypoints(self, kpsA, kpsB, featuresA, featuresB,
ratio, reprojThresh):
# compute the raw matches and initialize the list of actual
# matches
matcher = cv2.DescriptorMatcher_create("BruteForce")
rawMatches = matcher.knnMatch(featuresA, featuresB, 2)
matches = []
# loop over the raw matches
for m in rawMatches:
# ensure the distance is within a certain ratio of each
# other (i.e. Lowe's ratio test)
if len(m) == 2 and m[0].distance < m[1].distance * ratio:
matches.append((m[0].trainIdx, m[0].queryIdx))
# computing a homography requires at least 4 matches
if len(matches) > 4:
# construct the two sets of points
ptsA = np.float32([kpsA[i] for (_, i) in matches])
ptsB = np.float32([kpsB[i] for (i, _) in matches])
# compute the homography between the two sets of points
(H, status) = cv2.findHomography(ptsA, ptsB, cv2.RANSAC,
reprojThresh)
# return the matches along with the homograpy matrix
# and status of each matched point
return (matches, H, status)
# otherwise, no homograpy could be computed
return None
def drawMatches(self, imageA, imageB, kpsA, kpsB, matches, status):
# initialize the output visualization image
(hA, wA) = imageA.shape[:2]
(hB, wB) = imageB.shape[:2]
vis = np.zeros((max(hA, hB), wA + wB, 3), dtype="uint8")
vis[0:hA, 0:wA] = imageA
vis[0:hB, wA:] = imageB
# loop over the matches
for ((trainIdx, queryIdx), s) in zip(matches, status):
# only process the match if the keypoint was successfully
# matched
if s == 1:
# draw the match
ptA = (int(kpsA[queryIdx][0]), int(kpsA[queryIdx][1]))
ptB = (int(kpsB[trainIdx][0]) + wA, int(kpsB[trainIdx][1]))
cv2.line(vis, ptA, ptB, (0, 255, 0), 1)
# return the visualization
return vis
And here are the original images:
Image A:
Image B:
matched points:
The result of stitching:
The result is nowhere as desired, and if I'm correct it's due to there not being enough matching points between the two images.