Develop Reference

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:

How to count lines in an image with python, openCV

I want to count paper, so I am thinking about using line detection. I have tried some methods like Canny, HoughLines, and FLD. But I only get the processed photo. I have no idea how to count it. There are some small line segments that are the lines we want. I have used len(lines) or len(contours). However, the result is far from what I expected. The result is a hundred or thousand. So, does anyone have any suggestions?
The original photo:
Processd by Canny:
Processed by LSD:
Processed by HoughLinesP:
#Canny
samplename = "sam04.jpg"
img = cv2.imread('D:\\Users\\Administrator\\PycharmProjects\\EdgeDetect\\venv\\sample\\{}'.format(samplename),0)
edges = cv2.Canny(img,100,200)
cv2.imwrite('.\\detected\\{}'.format("p03_"+samplename),edges)
plt.subplot(121),plt.imshow(img,cmap = 'gray')
plt.title('Original Image'), plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(edges,cmap = 'gray')
plt.title('Edge Image'), plt.xticks([]), plt.yticks([])
plt.show()
#LSD
samplename = "sam09.jpg"
img0 = cv2.imread('D:\\Users\\Administrator\\PycharmProjects\\EdgeDetect\\venv\\sample\\{}'.format(samplename))
img = cv2.cvtColor(img0,cv2.COLOR_BGR2GRAY)
fld = cv2.ximgproc.createFastLineDetector()
dlines = fld.detect(img)
# drawn_img = fld.drawSegments(img0,dlines, )
for dline in dlines:
x0 = int(round(dline[0][0]))
y0 = int(round(dline[0][1]))
x1 = int(round(dline[0][2]))
y1 = int(round(dline[0][3]))
cv2.line(img0, (x0, y0), (x1,y1), (0,255,0), 1, cv2.LINE_AA)
cv2.imwrite('.\\detected\\{}'.format("p12_"+samplename), img0)
cv2.imshow("LSD", img0)
cv2.waitKey(0)
cv2.destroyAllWindows()
#HoughLine
import cv2
import numpy as np
samplename = "sam09.jpg"
#First, get the gray image and process GaussianBlur.
img = cv2.imread('D:\\Users\\Administrator\\PycharmProjects\\EdgeDetect\\venv\\sample\\{}'.format(samplename))
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
kernel_size = 5
blur_gray = cv2.GaussianBlur(gray,(kernel_size, kernel_size),0)
#Second, process edge detection use Canny.
low_threshold = 50
high_threshold = 150
edges = cv2.Canny(blur_gray, low_threshold, high_threshold)
cv2.imshow('photo2',edges)
cv2.waitKey(0)
#Then, use HoughLinesP to get the lines. You can adjust the parameters for better performance.
rho = 1 # distance resolution in pixels of the Hough grid
theta = np.pi / 180 # angular resolution in radians of the Hough grid
threshold = 15 # minimum number of votes (intersections in Hough grid cell)
min_line_length = 50 # minimum number of pixels making up a line
max_line_gap = 20 # maximum gap in pixels between connectable line segments
line_image = np.copy(img) * 0 # creating a blank to draw lines on
# Run Hough on edge detected image
# Output "lines" is an array containing endpoints of detected line segments
lines = cv2.HoughLinesP(edges, rho, theta, threshold, np.array([]),
min_line_length, max_line_gap)
print(lines)
print(len(lines))
for line in lines:
for x1,y1,x2,y2 in line:
cv2.line(line_image,(x1,y1),(x2,y2 ),(255,0,0),5)
#Finally, draw the lines on your srcImage.
# Draw the lines on the image
lines_edges = cv2.addWeighted(img, 0.8, line_image, 1, 0)
cv2.imshow('photo',lines_edges)
cv2.waitKey(0)
cv2.destroyAllWindows()
cv2.imwrite('.\\detected\\{}'.format("p14_"+samplename),lines_edges)

I think you could count the number of lines (papers) based on how many straight lines do you have. My idea is that
You should calculate the distances for all points that you get from HoughLinesP by using np.linalg.norm(point1 - point2) for more details.
Then you could adjust the proper distance that used to identify the lines to ignore the noise (small) lines. I recommend using min_line_length in HoughLinesP.
Count the number of distances (lines) that are bigger than the proper distance.
This is the code that I used for your image:
# After you apply Hough on edge detected image
lines = cv.HoughLinesP(img, rho, theta, threshold, np.array([]),
min_line_length, max_line_gap)
# calculate the distances between points (x1,y1), (x2,y2) :
distance = []
for line in lines:
distance.append(np.linalg.norm(line[:,:2] - line[:,2:]))
print('max distance:',max(distance),'\nmin distance:',min(distance))
# Adjusting the best distance
bestDistance=1110
numberOfLines=[]
count=0
for x in distance:
if x>bestDistance:
numberOfLines.append(x)
count=count+1
print('Number of lines:',count)
Output:
max distance: 1352.8166912039487
min distance: 50.0
Number of lines: 17

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

Writing robust (size invariant) circle detection (Watershed)

Edit: Quick Summary so far: I use the watershed algorithm but I have probably a problem with threshold. It didn't detect the brighter circles.
New: Fast radial symmetry transform approach which didn't quite work eiter (Edit 6).
I want to detect circles with different sizes. The use case is to detect coins on an image and to extract them solely. -> Get the single coins as single image files.
For this I used the Hough Circle Transform of open-cv:
(https://docs.opencv.org/2.4/doc/tutorials/imgproc/imgtrans/hough_circle/hough_circle.html)
import sys
import cv2 as cv
import numpy as np
def main(argv):
## [load]
default_file = "data/newcommon_1euro.jpg"
filename = argv[0] if len(argv) > 0 else default_file
# Loads an image
src = cv.imread(filename, cv.IMREAD_COLOR)
# Check if image is loaded fine
if src is None:
print ('Error opening image!')
print ('Usage: hough_circle.py [image_name -- default ' + default_file + '] \n')
return -1
## [load]
## [convert_to_gray]
# Convert it to gray
gray = cv.cvtColor(src, cv.COLOR_BGR2GRAY)
## [convert_to_gray]
## [reduce_noise]
# Reduce the noise to avoid false circle detection
gray = cv.medianBlur(gray, 5)
## [reduce_noise]
## [houghcircles]
rows = gray.shape[0]
circles = cv.HoughCircles(gray, cv.HOUGH_GRADIENT, 1, rows / 8,
param1=100, param2=30,
minRadius=0, maxRadius=120)
## [houghcircles]
## [draw]
if circles is not None:
circles = np.uint16(np.around(circles))
for i in circles[0, :]:
center = (i[0], i[1])
# circle center
cv.circle(src, center, 1, (0, 100, 100), 3)
# circle outline
radius = i[2]
cv.circle(src, center, radius, (255, 0, 255), 3)
## [draw]
## [display]
cv.imshow("detected circles", src)
cv.waitKey(0)
## [display]
return 0
if __name__ == "__main__":
main(sys.argv[1:])
I tried all parameters (rows, param1, param2, minRadius, and maxRadius) to optimize the results. This worked very well for one specific image but other images with different sized coins didn't work.
Examples:
Parameters
circles = cv.HoughCircles(gray, cv.HOUGH_GRADIENT, 1, rows / 16,
param1=100, param2=30,
minRadius=0, maxRadius=120)
With the same parameters:
Changed to rows/8
I also tried two other approaches of this thread: writing robust (color and size invariant) circle detection with opencv (based on Hough transform or other features)
The approach of fireant leads to this result:
The approach of fraxel didn't work either.
For the first approach: This happens with all different sizes and also the min and max radius.
How could I change the code, so that the coin size is not important or that it finds the parameters itself?
Thank you in advance for any help!
Edit:
I tried the watershed algorithm of Open-cv, as suggested by Alexander Reynolds: https://docs.opencv.org/3.4/d3/db4/tutorial_py_watershed.html
import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
img = cv.imread('data/P1190263.jpg')
gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
ret, thresh = cv.threshold(gray,0,255,cv.THRESH_BINARY_INV+cv.THRESH_OTSU)
# noise removal
kernel = np.ones((3,3),np.uint8)
opening = cv.morphologyEx(thresh,cv.MORPH_OPEN,kernel, iterations = 2)
# sure background area
sure_bg = cv.dilate(opening,kernel,iterations=3)
# Finding sure foreground area
dist_transform = cv.distanceTransform(opening,cv.DIST_L2,5)
ret, sure_fg = cv.threshold(dist_transform,0.7*dist_transform.max(),255,0)
# Finding unknown region
sure_fg = np.uint8(sure_fg)
unknown = cv.subtract(sure_bg,sure_fg)
# Marker labelling
ret, markers = cv.connectedComponents(sure_fg)
# Add one to all labels so that sure background is not 0, but 1
markers = markers+1
# Now, mark the region of unknown with zero
markers[unknown==255] = 0
markers = cv.watershed(img,markers)
img[markers == -1] = [255,0,0]
#Display:
cv.imshow("detected circles", img)
cv.waitKey(0)
It works very well on the test image of the open-cv website:
But it performs very bad on my own images:
I can't really think of a good reason why it's not working on my images?
Edit 2:
As suggested I looked at the intermediate images. The thresh looks not good in my opinion. Next, there is no difference between opening and dist_transform. The corresponding sure_fg shows the detected images.
thresh:
opening:
dist_transform:
sure_bg:
sure_fg:
Edit 3:
I tried all distanceTypes and maskSizes I could find, but the results were quite the same (https://www.tutorialspoint.com/opencv/opencv_distance_transformation.htm)
Edit 4:
Furthermore, I tried to change the (first) threshold function. I used different threshold values instead of the OTSU Function. The best one was with 160, but it was far from good:
In the tutorial it looks like this:
It seems like the coins are somehow too bright to be detected by this algorithm, but I don't know how to improve it?
Edit 5:
Changing the overall contrast and brightness of the image (with cv.convertScaleAbs) didn't improve the results. Increasing the contrast however should increase the "difference" between foreground and background, at least on the normal image. But it even got worse. The corresponding threshold image didn't improved (didn't get more white pixel).
Edit 6: I tried another approach, the fast radial symmetry transform (from here https://github.com/ceilab/frst_python)
import cv2
import numpy as np
def gradx(img):
img = img.astype('int')
rows, cols = img.shape
# Use hstack to add back in the columns that were dropped as zeros
return np.hstack((np.zeros((rows, 1)), (img[:, 2:] - img[:, :-2]) / 2.0, np.zeros((rows, 1))))
def grady(img):
img = img.astype('int')
rows, cols = img.shape
# Use vstack to add back the rows that were dropped as zeros
return np.vstack((np.zeros((1, cols)), (img[2:, :] - img[:-2, :]) / 2.0, np.zeros((1, cols))))
# Performs fast radial symmetry transform
# img: input image, grayscale
# radii: integer value for radius size in pixels (n in the original paper); also used to size gaussian kernel
# alpha: Strictness of symmetry transform (higher=more strict; 2 is good place to start)
# beta: gradient threshold parameter, float in [0,1]
# stdFactor: Standard deviation factor for gaussian kernel
# mode: BRIGHT, DARK, or BOTH
def frst(img, radii, alpha, beta, stdFactor, mode='BOTH'):
mode = mode.upper()
assert mode in ['BRIGHT', 'DARK', 'BOTH']
dark = (mode == 'DARK' or mode == 'BOTH')
bright = (mode == 'BRIGHT' or mode == 'BOTH')
workingDims = tuple((e + 2 * radii) for e in img.shape)
# Set up output and M and O working matrices
output = np.zeros(img.shape, np.uint8)
O_n = np.zeros(workingDims, np.int16)
M_n = np.zeros(workingDims, np.int16)
# Calculate gradients
gx = gradx(img)
gy = grady(img)
# Find gradient vector magnitude
gnorms = np.sqrt(np.add(np.multiply(gx, gx), np.multiply(gy, gy)))
# Use beta to set threshold - speeds up transform significantly
gthresh = np.amax(gnorms) * beta
# Find x/y distance to affected pixels
gpx = np.multiply(np.divide(gx, gnorms, out=np.zeros(gx.shape), where=gnorms != 0),
radii).round().astype(int);
gpy = np.multiply(np.divide(gy, gnorms, out=np.zeros(gy.shape), where=gnorms != 0),
radii).round().astype(int);
# Iterate over all pixels (w/ gradient above threshold)
for coords, gnorm in np.ndenumerate(gnorms):
if gnorm > gthresh:
i, j = coords
# Positively affected pixel
if bright:
ppve = (i + gpx[i, j], j + gpy[i, j])
O_n[ppve] += 1
M_n[ppve] += gnorm
# Negatively affected pixel
if dark:
pnve = (i - gpx[i, j], j - gpy[i, j])
O_n[pnve] -= 1
M_n[pnve] -= gnorm
# Abs and normalize O matrix
O_n = np.abs(O_n)
O_n = O_n / float(np.amax(O_n))
# Normalize M matrix
M_max = float(np.amax(np.abs(M_n)))
M_n = M_n / M_max
# Elementwise multiplication
F_n = np.multiply(np.power(O_n, alpha), M_n)
# Gaussian blur
kSize = int(np.ceil(radii / 2))
kSize = kSize + 1 if kSize % 2 == 0 else kSize
S = cv2.GaussianBlur(F_n, (kSize, kSize), int(radii * stdFactor))
return S
img = cv2.imread('data/P1190263.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
result = frst(gray, 60, 2, 0, 1, mode='BOTH')
cv2.imshow("detected circles", result)
cv2.waitKey(0)
I only get this nearly black output (it has some very dark grey shadows). I don't know what to change and would be thankful for help!

Detect the green lines in this image and calculate their lengths

Sample Images
The image can be more noisy at times where more objects intervene from the background. Right now I am using various techniques using the RGB colour space to detect the lines but it fails when there is change in the colour due to intervening obstacles from the background. I am using opencv and python.
I have read that HSV is better for colour detection and used but haven't been successful yet.
I am not able to find a generic solution to this problem. Any hints or clues in this direction would be of great help.

STILL IN PROGRESS
First of all, an RGB image consists of 3 grayscale images. Since you need the green color you will deal only with one channel. The green one. To do so, you can split the image, you can use b,g,r = cv2.split('Your Image'). You will get an output like that if you are showing the green channel:
After that you should threshold the image using your desired way. I prefer Otsu's thresholding in this case. The output after thresholding is:
It's obvious that the thresholded image is extremley noisy. So performing erosion will reduce the noise a little bit. The noise reduced image will be similar to the following:
I tried using closing instead of dilation, but closing preserves some unwanted noise. So I separately performed erosion followed by dilation. After dilation the output is:
Note that: You can do your own way in morphological operation. You can use opening instead of what I did. The results are subjective from
one person to another.
Now you can try one these two methods:
1. Blob Detection.
2. HoughLine Transform.
TODO
Try out these two methods and choose the best.

You should use the fact that you know you are trying to detect a line by using the line hough transform.
http://docs.opencv.org/2.4/doc/tutorials/imgproc/imgtrans/hough_lines/hough_lines.html
When the obstacle also look like a line use the fact that you know approximately what is the orientation of the green lines.
If you don't know the orientation of the line use hte fact that there are several green lines with the same orientation and only one line that is the obstacle
Here is a code for what i meant:
import cv2
import numpy as np
# Params
minLineCount = 300 # min number of point alogn line with the a specif orientation
minArea = 100
# Read img
img = cv2.imread('i.png')
greenChannel = img[:,:,1]
# Do noise reduction
iFilter = cv2.bilateralFilter(greenChannel,5,5,5)
# Threshold data
#ret,iThresh = cv2.threshold(iFilter,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
iThresh = (greenChannel > 4).astype(np.uint8)*255
# Remove small areas
se1 = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
iThreshRemove = cv2.morphologyEx(iThresh, cv2.MORPH_OPEN, se1)
# Find edges
iEdge = cv2.Canny(iThreshRemove,50,100)
# Hough line transform
lines = cv2.HoughLines(iEdge, 1, 3.14/180,75)
# Find the theta with the most lines
thetaCounter = dict()
for line in lines:
theta = line[0, 1]
if theta in thetaCounter:
thetaCounter[theta] += 1
else:
thetaCounter[theta] = 1
maxThetaCount = 0
maxTheta = 0
for theta in thetaCounter:
if thetaCounter[theta] > maxThetaCount:
maxThetaCount = thetaCounter[theta]
maxTheta = theta
# Find the rhos that corresponds to max theta
rhoValues = []
for line in lines:
rho = line[0, 0]
theta = line[0, 1]
if theta == maxTheta:
rhoValues.append(rho)
# Go over all the lines with the specific orientation and count the number of pixels on that line
# if the number is bigger than minLineCount draw the pixels in finaImage
lineImage = np.zeros_like(iThresh, np.uint8)
for rho in range(min(rhoValues), max(rhoValues), 1):
a = np.cos(maxTheta)
b = np.sin(maxTheta)
x0 = round(a*rho)
y0 = round(b*rho)
lineCount = 0
pixelList = []
for jump in range(-1000, 1000, 1):
x1 = int(x0 + jump * (-b))
y1 = int(y0 + jump * (a))
if x1 < 0 or y1 < 0 or x1 >= lineImage.shape[1] or y1 >= lineImage.shape[0]:
continue
if iThreshRemove[y1, x1] == int(255):
pixelList.append((y1, x1))
lineCount += 1
if lineCount > minLineCount:
for y,x in pixelList:
lineImage[y, x] = int(255)
# Remove small areas
## Opencv 2.4
im2, contours, hierarchy = cv2.findContours(lineImage,cv2.RETR_CCOMP,cv2.CHAIN_APPROX_NONE )
finalImage = np.zeros_like(lineImage)
finalShapes = []
for contour in contours:
if contour.size > minArea:
finalShapes.append(contour)
cv2.fillPoly(finalImage, finalShapes, 255)
## Opencv 3.0
# output = cv2.connectedComponentsWithStats(lineImage, 8, cv2.CV_32S)
#
# finalImage = np.zeros_like(output[1])
# finalImage = output[1]
# stat = output[2]
# for label in range(output[0]):
# if label == 0:
# continue
# cc = stat[label,:]
# if cc[cv2.CC_STAT_AREA] < minArea:
# finalImage[finalImage == label] = 0
# else:
# finalImage[finalImage == label] = 255
# Show image
#cv2.imwrite('finalImage2.jpg',finalImage)
cv2.imshow('a', finalImage.astype(np.uint8))
cv2.waitKey(0)
and the result for the images: