Develop Reference

How to get rid of skeleton line except contour?

I want to get rid of the skeletonized lines except the contours using python.
And, want to extract only the largest contour.
(Actually, I tried to make skeletonized line from the segmented mask. And, I got the main stem with contour like above picture. Among the contours, I want to extract only the contour with largest area.)
I don't know how to do it.
Please help me if you have any idea.
Thanks in advance.
import os
import numpy as np
import cv2
from plantcv.plantcv import find_objects
from plantcv.plantcv import image_subtract
from plantcv.plantcv.morphology import segment_sort
from plantcv.plantcv.morphology import segment_skeleton
from plantcv.plantcv.morphology import _iterative_prune
from plantcv.plantcv import print_image
from plantcv.plantcv import plot_image
from plantcv.plantcv import params
from cv2.ximgproc import thinning
def find_large_contour(img, mask):
params.device += 1
mask1 = np.copy(mask)
ori_img = np.copy(img)
# If the reference image is grayscale convert it to color
if len(np.shape(ori_img)) == 2:
ori_img = cv2.cvtColor(ori_img, cv2.COLOR_GRAY2BGR)
objects, hierarchy = cv2.findContours(mask1, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)[-2:]
for i, cnt in enumerate(objects):
cv2.drawContours(ori_img, objects, i, (255, 102, 255), -1, lineType=8, hierarchy=hierarchy)
if params.debug == 'print':
print_image(ori_img, os.path.join(params.debug_outdir, str(params.device) + '_id_objects.png'))
elif params.debug == 'plot':
plot_image(ori_img)
return objects, hierarchy, ori_img
def prune(skel_img, size=2, mask=None):
# Store debug
debug = params.debug
params.debug = None
pruned_img = skel_img.copy()
# Check to see if the skeleton has multiple objects
skel_objects, _ = find_objects(skel_img, skel_img)
_, objects = segment_skeleton(skel_img)
kept_segments = []
removed_segments = []
if size > 0:
# If size>0 then check for segments that are smaller than size pixels long
# Sort through segments since we don't want to remove primary segments
secondary_objects, primary_objects = segment_sort(skel_img, objects)
# Keep segments longer than specified size
for i in range(0, len(secondary_objects)):
if len(secondary_objects[i]) > size:
kept_segments.append(secondary_objects[i])
else:
removed_segments.append(secondary_objects[i])
# Draw the contours that got removed
removed_barbs = np.zeros(skel_img.shape[:2], np.uint8)
cv2.drawContours(removed_barbs, removed_segments, -1, 255, 1,
lineType=8)
# Subtract all short segments from the skeleton image
pruned_img = image_subtract(pruned_img, removed_barbs)
pruned_contour_img = image_subtract(pruned_img, removed_barbs)
pruned_img = _iterative_prune(pruned_img, 1)
# Reset debug mode
params.debug = debug
# Make debugging image
if mask is None:
pruned_plot = np.zeros(skel_img.shape[:2], np.uint8)
else:
pruned_plot = mask.copy()
pruned_plot = cv2.cvtColor(pruned_plot, cv2.COLOR_GRAY2RGB)
pruned_obj, pruned_hierarchy, large_contour = find_large_contour(pruned_img, pruned_img)
cv2.drawContours(pruned_plot, removed_segments, -1, (0, 0, 255), params.line_thickness, lineType=8)
cv2.drawContours(pruned_plot, pruned_obj, -1, (150, 150, 150), params.line_thickness, lineType=8)
# Auto-increment device
params.device += 1
if params.debug == 'print':
print_image(pruned_img, os.path.join(params.debug_outdir, str(params.device) + '_pruned.png'))
print_image(pruned_plot, os.path.join(params.debug_outdir, str(params.device) + '_pruned_debug.png'))
elif params.debug == 'plot':
plot_image(pruned_img, cmap='gray')
plot_image(pruned_plot)
# Segment the pruned skeleton
segmented_img, segment_objects = segment_skeleton(pruned_img, mask)
return pruned_img, segmented_img, segment_objects, large_contour
vseg = cv2.imread("vseg.png", cv2.IMREAD_GRAYSCALE)
gray = thinning(vseg, thinningType=cv2.ximgproc.THINNING_GUOHALL)
pruned, seg_img, edge_objects, large_contour = prune(skel_img=gray, size=3, mask=vseg)
img_cont_gray = cv2.cvtColor(large_contour, cv2.COLOR_BGR2GRAY)
ret_cont, thresh_cont = cv2.threshold(img_cont_gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
cv2.imwrite("first_cont111.png", thresh_cont)
## then I want to extract the only contour with largest area

Use morphology as the first step
ret,thresh = cv2.threshold(img, 127, 255, cv2.THRESH_BINARY)
rect=cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, rect)
Then find the conneсted component of maximal area
max_component=np.full(opening.shape, 0, np.uint8)
nb_components,labels,stats,centroids= cv2.connectedComponentsWithStats(opening,8)
max_component[labels == np.argmax(stats[1:, -1])+1]=255

using skimage (if you don't have it: conda install scikit-image)
import scipy.ndimage as ndi
from skimage.morphology import binary_erosion, binary_dilation
from skimage.measure import regionprops
from skimage import io
#
img = io.imread("first_cont111.png") > 0 # open image and ensure 0,1 data
# get rid of 1-pixel lines
img = binary_erosion(img)
img = binary_dilation(img)
# find individual objects and give them unique labels
label_img, _ = ndi.label(img)
props = regionprops(label_img)
# find the label that corresponds to the object with maximum area:
objects = sorted([(p.label, p.area) for p in props], key=lambda x: x[1], reverse=True)
obj = objects[0][0]
# make an image of the same size as the input image:
output_img = np.zeros_like(img)
# and use fancy indexing to copy the largest object
output_img[label_img==obj] = 1
# now make the contour by subtracting the eroded shape
output_img = output_img - binary_erosion(output_image)

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...

How to blur the image according to segmentation map

Forgive me if I am unable to explain well because I am not native speaker.
I am working on blurring the part of image according to the white part of segmentation map. For example here is my segmentation image ( bmp image ).
.
Now what I want is to blur the part of original image where the pixels are white in the segmentation map. I just wrote the following code to so.
mask = mask >= 0.5
mask = np.reshape(mask, (512, 512))
mh, mw = 512, 512
mask_n = np.ones((mh, mw, 3))
mask_n[:,:,0] *= mask
mask_n[:,:,1] *= mask
mask_n[:,:,2] *= mask
# discard padded area
ih, iw, _ = image_n.shape
delta_h = mh - ih
delta_w = mw - iw
top = delta_h // 2
bottom = mh - (delta_h - top)
left = delta_w // 2
right = mw - (delta_w - left)
mask_n = mask_n[top:bottom, left:right, :]
# addWeighted
image_n = image_n *1 + cv2.blur(mask_n * 0.8, (800, 800))
Please help me, Thanks.

You can do it in the following steps:
Load original image and mask image.
Blur the whole original image and save it in a different variable.
Use np.where() method to select the pixels from the mask where you want blurred values and then replace it.
See the sample code below:
import cv2
import numpy as np
img = cv2.imread("./image.png")
blurred_img = cv2.GaussianBlur(img, (21, 21), 0)
mask = cv2.imread("./mask.png")
output = np.where(mask==np.array([255, 255, 255]), blurred_img, img)
cv2.imwrite("./output.png", output)

Here's an alternative to the solution proposed by #Chris Henri. It relies on scipy.ndimage.filters.gaussian_filter and NumPy's boolean indexing:
from skimage import io
import numpy as np
from scipy.ndimage.filters import gaussian_filter
import matplotlib.pyplot as plt
mask = io.imread('https://i.stack.imgur.com/qJiKf.png')
img = np.random.random(size=mask.shape[:2])
idx = mask.min(axis=-1) == 255
blurred = gaussian_filter(img, sigma=3)
blurred[~idx] = 0
fig, axs = plt.subplots(1, 3, figsize=(12, 4))
for ax, im in zip(axs, [img, mask, blurred]):
ax.imshow(im, cmap='gray')
ax.set_axis_off()
plt.show(fig)

Here is yet another alternative to do so, useful though when you have a 2D segmentation array indicating the segmented object class of pixel (mutually exclusive) for every index (i,j), and a 3D image on which you want to apply the blur.
def gaussian_blur(image: np.ndarray,
segmentation: np.ndarray,
classes_of_interest: list,
gaussian_variance: float = 10) -> np.ndarray:
'''
Function that applies a gaussian filter to the image,
specifically to the pixels contained in the possible segmented classes.
Returns an image (np.ndarray) where the gaussian blur intensity is
regulated by the parameter gaussian_variance.
'''
#Apply masking to select only the indices where the specific class is present
mask = np.isin(segmentation, classes_of_interest)
#Creating a 3D mask for all the channels and place it at channel axis
mask_3d = np.stack([mask,mask,mask], axis=2)
#Mask the image according to the 3D mask
img_masked = np.where(mask_3d, img, 0).astype(np.int8)
#Define gaussian blur noisy function
def noisy(image):
row,col,ch= image.shape
mean = 0
var = gaussian_variance
sigma = np.sqrt(var)
gauss = np.random.normal(mean,sigma,(row,col,ch))
gauss = gauss.reshape(row,col,ch)
#Sums up gaussian noise to img
noisy = image + gauss
return noisy.astype(np.uint8)
#Blurs the masked segmentation
img_masked_noisy = noisy(img_masked)
#Puts the blurred part back in the original image as substitution
img[mask_3d] = img_masked_noisy[mask_3d]
return img
And here is a toy example:
import numpy as np
possible_classes = [1,2,3]
#Setting up a toy example with a small image,
#shape (N, N, 3)
img = np.floor(np.random.random(size=(8,8,3)) * 256).astype(np.uint8)
#Setting up a fake segmentation with 3 mutually exclusive possible classes,
#shape (N, N)
segmentation = np.random.choice(possible_classes, size=(8,8))
new_img_blurred = gaussian_blur(img,
segmentation= segmentation,
classes_of_interest= possible_classes[:2])

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!