I'm running a unet model on x-ray for lung region segmentation, the model seems to work well, but my dataset is not that good looking, I'm obtaining results with some missing parts as in here:
My question is: is there any cv operator I can preform to smoothen it a little more to obtain something like this:
Thanks.
What you describe can be implemented via morphology. Morphological operations are a set of (logical) operations that affect the overall shape of the image. It can "expand" or "reduce" shape regions, among many other cool operations.
Let's use a dilation to expand your image's shape:
# Imports
import cv2
import numpy as np
# Read image
imagePath = "D://opencvImages//"
inputImage = cv2.imread(imagePath+"lungs.png")
# Convert BGR back to grayscale:
grayInput = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Threshold via Otsu + bias adjustment:
threshValue, binaryImage = cv2.threshold(grayInput, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
This first bit converts the image that you posted into a binary image, as morphological operations can be only be performed on 1-channel images (also grayscale), but since we will apply a basic dilation, a binary image will suffice. this is the result of the above snippet:
Let's apply the dilation. The operation can be applied successively, so you can specify a number of iterations. Since you want a somewhat strong effect, let's try 10 iterations. The operation needs a second operand named "Structuring Element" (SE), which selects the pixels in a defined sub-region of the shape. There are different kinds of SEs. One of the most common is a 3 x 3 rectangular SE:
# Set morph operation iterations:
opIterations = 10
# Set Structuring Element size:
structuringElementSize = (3, 3)
# Set Structuring element shape:
structuringElementShape = cv2.MORPH_RECT
# Get the Structuring Element:
structuringElement = cv2.getStructuringElement(structuringElementShape, structuringElementSize)
# Perform Dilate:
dilateImg = cv2.morphologyEx(binaryImage, cv2.MORPH_DILATE, structuringElement, None, None, opIterations, cv2.BORDER_REFLECT101)
# Show the image:
cv2.imshow("dilateImg", dilateImg)
cv2.waitKey(0)
This is the result:
Related
I'm new to opencv and I m trying to remove all these diagonal parallel lines that are noise in my image.
I have tried using HoughLinesP after some erosion/dilatation but the result is poo (and keeping only the one with a near 135 degree angle).
img = cv2.imread('images/dungeon.jpg')
ret,img = cv2.threshold(img,180,255,0)
element = cv2.getStructuringElement(cv2.MORPH_CROSS,(5,5))
eroded = cv2.erode(img,element)
dilate = cv2.dilate(eroded, element)
skeleton = cv2.subtract(img, dilate)
gray = cv2.cvtColor(skeleton,cv2.COLOR_BGR2GRAY)
minLineLength = 10
lines = cv2.HoughLinesP(gray, 1, np.pi/180, 1, 10, 0.5)
for line in lines:
for x1,y1,x2,y2 in line:
angle = math.atan2(y2-y1,x2-x1)
if (angle > -0.1 and angle < 0.1):
cv2.line(img,(x1,y1),(x2,y2),(0,255,0),1)
cv2.imshow("result", img)
cv2.waitKey(0)
cv2.destroyAllWindows()
My thinking here was to detect these lines in order to remove them afterwards but I m not even sure that's the good way to do this.
I guess you are trying to get the contours of the walls, right? Here’s a possible path to the solution using mainly spatial filtering. You will still need to clean the results to get where you want. The idea is to try and compute a mask of the parallel lines (high-frequency noise) of the image and calculate the difference between the (binary) input and this mask. These are the steps:
Convert the input image to grayscale
Apply Gaussian Blur to get rid of the high-frequency noise you are trying to eliminate
Get a binary image of the blurred image
Apply area filters to get rid of everything that is not noise, to get a noise mask
Compute the difference between the original binary mask and the noise mask
Clean up the difference image
Compute contours on this image
Let’s see the code:
import cv2
import numpy as np
# Set image path
path = "C://opencvImages//"
fileName = "map.png"
# Read Input image
inputImage = cv2.imread(path+fileName)
# Convert BGR to grayscale:
grayscaleImage = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Apply Gaussian Blur:
blurredImage = cv2.GaussianBlur(grayscaleImage, (3, 3), cv2.BORDER_DEFAULT)
# Threshold via Otsu:
_, binaryImage = cv2.threshold(blurredImage, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# Save a copy of the binary mask
binaryCopy = cv2.cvtColor(binaryImage, cv2.COLOR_GRAY2BGR)
This is the output:
Up until now you get this binary mask. The process so far has smoothed the noise and is creating thick black blobs where the noise is located. Again, the idea is to generate a noise mask that can be subtracted to this image.
Let’s apply an area filter and try to remove the big white blobs, which are NOT the noise we are interested to preserve. I’ll define the function towards the end, for now I just want to present the general idea:
# Set the minimum pixels for the area filter:
minArea = 50000
# Perform an area filter on the binary blobs:
filteredImage = areaFilter(minArea, binaryImage)
The filter will suppress every white blob that is above the minimum threshold. The value is big because in this particular case we are interested in preserving only the black blobs. This is the result:
We have a pretty solid mask. Let’s subtract this from the original binary mask we created earlier:
# Get the difference between the binary image and the mask:
imgDifference = binaryImage - filteredImage
This is what we get:
The difference image has some small noise. Let’s apply the area filter again to get rid of it. This time with a more traditional threshold value:
# Set the minimum pixels for the area filter:
minArea = 20
# Perform an area filter on the binary blobs:
filteredImage = areaFilter(minArea, imgDifference)
Cool. This is the final mask:
Just for completeness. Let’s compute contours on this input, which is very straightforward:
# Find the big contours/blobs on the filtered image:
contours, hierarchy = cv2.findContours(filteredImage, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
# Draw the contours on the mask image:
cv2.drawContours(binaryCopy, contours, -1, (0, 255, 0), 3)
Let’s see the result:
As you see it is not perfect. However, there’s still some room for improvement, perhaps you can polish a little bit more this idea to get a potential solution. Here's the definition and implementation of the areaFilter function:
def areaFilter(minArea, inputImage):
# Perform an area filter on the binary blobs:
componentsNumber, labeledImage, componentStats, componentCentroids = \
cv2.connectedComponentsWithStats(inputImage, connectivity=4)
# Get the indices/labels of the remaining components based on the area stat
# (skip the background component at index 0)
remainingComponentLabels = [i for i in range(1, componentsNumber) if componentStats[i][4] >= minArea]
# Filter the labeled pixels based on the remaining labels,
# assign pixel intensity to 255 (uint8) for the remaining pixels
filteredImage = np.where(np.isin(labeledImage, remainingComponentLabels) == True, 255, 0).astype('uint8')
return filteredImage
I am really new to opencv and a beginner to python.
I have this image:
I want to somehow apply proper thresholding to keep nothing but the 6 digits.
The bigger picture is that I intend to try to perform manual OCR to the image for each digit separately, using the k-nearest neighbours algorithm on a per digit level (kNearest.findNearest)
The problem is that I cannot clean up the digits sufficiently, especially the '7' digit which has this blue-ish watermark passing through it.
The steps I have tried so far are the following:
I am reading the image from disk
# IMREAD_UNCHANGED is -1
image = cv2.imread(sys.argv[1], cv2.IMREAD_UNCHANGED)
Then I'm keeping only the blue channel to get rid of the blue watermark around digit '7', effectively converting it to a single channel image
image = image[:,:,0]
# openned with -1 which means as is,
# so the blue channel is the first in BGR
Then I'm multiplying it a bit to increase contrast between the digits and the background:
image = cv2.multiply(image, 1.5)
Finally I perform Binary+Otsu thresholding:
_,thressed1 = cv2.threshold(image,0,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)
As you can see the end result is pretty good except for the digit '7' which has kept a lot of noise.
How to improve the end result? Please supply the image example result where possible, it is better to understand than just code snippets alone.
You can try to medianBlur the gray(blur) image with different kernels(such as 3, 51), divide the blured results, and threshold it. Something like this：
#!/usr/bin/python3
# 2018/09/23 17:29 (CST)
# (中秋节快乐)
# (Happy Mid-Autumn Festival)
import cv2
import numpy as np
fname = "color.png"
bgray = cv2.imread(fname)[...,0]
blured1 = cv2.medianBlur(bgray,3)
blured2 = cv2.medianBlur(bgray,51)
divided = np.ma.divide(blured1, blured2).data
normed = np.uint8(255*divided/divided.max())
th, threshed = cv2.threshold(normed, 100, 255, cv2.THRESH_OTSU)
dst = np.vstack((bgray, blured1, blured2, normed, threshed))
cv2.imwrite("dst.png", dst)
The result：
Why not just keep values in the image that are above a certain threshold?
Like this:
import cv2
import numpy as np
img = cv2.imread("./a.png")[:,:,0] # the last readable image
new_img = []
for line in img:
new_img.append(np.array(list(map(lambda x: 0 if x < 100 else 255, line))))
new_img = np.array(list(map(lambda x: np.array(x), new_img)))
cv2.imwrite("./b.png", new_img)
Looks great:
You could probably play with the threshold even more and get better results.
It doesn't seem easy to completely remove the annoying stamp.
What you can do is flattening the background intensity by
computing a lowpass image (Gaussian filter, morphological closing); the filter size should be a little larger than the character size;
dividing the original image by the lowpass image.
Then you can use Otsu.
As you see, the result isn't perfect.
I tried a slightly different approach then Yves on the blue channel:
Apply median filter (r=2):
Use Edge detection (e.g. Sobel operator):
Automatic thresholding (Otsu)
Closing of the image
This approach seems to make the output a little less noisy. However, one has to address the holes in the numbers. This can be done by detecting black contours which are completely surrounded by white pixels and simply filling them with white.
For my project i'm trying to binarize an image with openCV in python. I used the adaptive gaussian thresholding from openCV to convert the image with the following result:
I want to use the binary image for OCR but it's too noisy. Is there any way to remove the noise from the binary image in python? I already tried fastNlMeansDenoising from openCV but it doesn't make a difference.
P.S better options for binarization are welcome as well
You should start by adjusting the parameters to the adaptive threshold so it uses a larger area. That way it won't be segmenting out noise. Whenever your output image has more noise than the input image, you know you're doing something wrong.
I suggest as an adaptive threshold to use a closing (on the input grey-value image) with a structuring element just large enough to remove all the text. The difference between this result and the input image is exactly all the text. You can then apply a regular threshold to this difference.
It is also possible using GraphCuts for this kind of task. You will need to install the maxflow library in order to run the code. I quickly copied the code from their tutorial and modified it, so you could run it more easily. Just play around with the smoothing parameter to increase or decrease the denoising of the image.
import cv2
import numpy as np
import matplotlib.pyplot as plt
import maxflow
# Important parameter
# Higher values means making the image smoother
smoothing = 110
# Load the image and convert it to grayscale image
image_path = 'your_image.png'
img = cv2.imread('image_path')
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img = 255 * (img > 128).astype(np.uint8)
# Create the graph.
g = maxflow.Graph[int]()
# Add the nodes. nodeids has the identifiers of the nodes in the grid.
nodeids = g.add_grid_nodes(img.shape)
# Add non-terminal edges with the same capacity.
g.add_grid_edges(nodeids, smoothing)
# Add the terminal edges. The image pixels are the capacities
# of the edges from the source node. The inverted image pixels
# are the capacities of the edges to the sink node.
g.add_grid_tedges(nodeids, img, 255-img)
# Find the maximum flow.
g.maxflow()
# Get the segments of the nodes in the grid.
sgm = g.get_grid_segments(nodeids)
# The labels should be 1 where sgm is False and 0 otherwise.
img_denoised = np.logical_not(sgm).astype(np.uint8) * 255
# Show the result.
plt.subplot(121)
plt.imshow(img, cmap='gray')
plt.title('Binary image')
plt.subplot(122)
plt.title('Denoised binary image')
plt.imshow(img_denoised, cmap='gray')
plt.show()
# Save denoised image
cv2.imwrite('img_denoised.png', img_denoised)
Result
You could try the morphological transformation close to remove small "holes".
First define a kernel using numpy, you might need to play around with the size. Choose the size of the kernel as big as your noise.
kernel = np.ones((5,5),np.uint8)
Then run the morphologyEx using the kernel.
denoised = cv2.morphologyEx(image, cv2.MORPH_CLOSE, kernel)
If text gets removed you can try to erode the image, this will "grow" the black pixels. If the noise is as big as the data, this method will not help.
erosion = cv2.erode(img,kernel,iterations = 1)
I have two images, one with only background and the other with background + detectable object (in my case its a car). Below are the images
I am trying to remove the background such that I only have car in the resulting image. Following is the code that with which I am trying to get the desired results
import numpy as np
import cv2
original_image = cv2.imread('IMG1.jpg', cv2.IMREAD_COLOR)
gray_original = cv2.cvtColor(original_image, cv2.COLOR_BGR2GRAY)
background_image = cv2.imread('IMG2.jpg', cv2.IMREAD_COLOR)
gray_background = cv2.cvtColor(background_image, cv2.COLOR_BGR2GRAY)
foreground = np.absolute(gray_original - gray_background)
foreground[foreground > 0] = 255
cv2.imshow('Original Image', foreground)
cv2.waitKey(0)
The resulting image by subtracting the two images is
Here is the problem. The expected resulting image should be a car only.
Also, If you take a deep look in the two images, you'll see that they are not exactly same that is, the camera moved a little so background had been disturbed a little. My question is that with these two images how can I subtract the background. I do not want to use grabCut or backgroundSubtractorMOG algorithm right now because I do not know right now whats going on inside those algorithms.
What I am trying to do is to get the following resulting image
Also if possible, please guide me with a general way of doing this not only in this specific case that is, I have a background in one image and background+object in the second image. What could be the best possible way of doing this. Sorry for such a long question.
I solved your problem using the OpenCV's watershed algorithm. You can find the theory and examples of watershed here.
First I selected several points (markers) to dictate where is the object I want to keep, and where is the background. This step is manual, and can vary a lot from image to image. Also, it requires some repetition until you get the desired result. I suggest using a tool to get the pixel coordinates.
Then I created an empty integer array of zeros, with the size of the car image. And then I assigned some values (1:background, [255,192,128,64]:car_parts) to pixels at marker positions.
NOTE: When I downloaded your image I had to crop it to get the one with the car. After cropping, the image has size of 400x601. This may not be what the size of the image you have, so the markers will be off.
Afterwards I used the watershed algorithm. The 1st input is your image and 2nd input is the marker image (zero everywhere except at marker positions). The result is shown in the image below.
I set all pixels with value greater than 1 to 255 (the car), and the rest (background) to zero. Then I dilated the obtained image with a 3x3 kernel to avoid losing information on the outline of the car. Finally, I used the dilated image as a mask for the original image, using the cv2.bitwise_and() function, and the result lies in the following image:
Here is my code:
import cv2
import numpy as np
import matplotlib.pyplot as plt
# Load the image
img = cv2.imread("/path/to/image.png", 3)
# Create a blank image of zeros (same dimension as img)
# It should be grayscale (1 color channel)
marker = np.zeros_like(img[:,:,0]).astype(np.int32)
# This step is manual. The goal is to find the points
# which create the result we want. I suggest using a
# tool to get the pixel coordinates.
# Dictate the background and set the markers to 1
marker[204][95] = 1
marker[240][137] = 1
marker[245][444] = 1
marker[260][427] = 1
marker[257][378] = 1
marker[217][466] = 1
# Dictate the area of interest
# I used different values for each part of the car (for visibility)
marker[235][370] = 255 # car body
marker[135][294] = 64 # rooftop
marker[190][454] = 64 # rear light
marker[167][458] = 64 # rear wing
marker[205][103] = 128 # front bumper
# rear bumper
marker[225][456] = 128
marker[224][461] = 128
marker[216][461] = 128
# front wheel
marker[225][189] = 192
marker[240][147] = 192
# rear wheel
marker[258][409] = 192
marker[257][391] = 192
marker[254][421] = 192
# Now we have set the markers, we use the watershed
# algorithm to generate a marked image
marked = cv2.watershed(img, marker)
# Plot this one. If it does what we want, proceed;
# otherwise edit your markers and repeat
plt.imshow(marked, cmap='gray')
plt.show()
# Make the background black, and what we want to keep white
marked[marked == 1] = 0
marked[marked > 1] = 255
# Use a kernel to dilate the image, to not lose any detail on the outline
# I used a kernel of 3x3 pixels
kernel = np.ones((3,3),np.uint8)
dilation = cv2.dilate(marked.astype(np.float32), kernel, iterations = 1)
# Plot again to check whether the dilation is according to our needs
# If not, repeat by using a smaller/bigger kernel, or more/less iterations
plt.imshow(dilation, cmap='gray')
plt.show()
# Now apply the mask we created on the initial image
final_img = cv2.bitwise_and(img, img, mask=dilation.astype(np.uint8))
# cv2.imread reads the image as BGR, but matplotlib uses RGB
# BGR to RGB so we can plot the image with accurate colors
b, g, r = cv2.split(final_img)
final_img = cv2.merge([r, g, b])
# Plot the final result
plt.imshow(final_img)
plt.show()
If you have a lot of images you will probably need to create a tool to annotate the markers graphically, or even an algorithm to find markers automatically.
The problem is that you're subtracting arrays of unsigned 8 bit integers. This operation can overflow.
To demonstrate
>>> import numpy as np
>>> a = np.array([[10,10]],dtype=np.uint8)
>>> b = np.array([[11,11]],dtype=np.uint8)
>>> a - b
array([[255, 255]], dtype=uint8)
Since you're using OpenCV, the simplest way to achieve your goal is to use cv2.absdiff().
>>> cv2.absdiff(a,b)
array([[1, 1]], dtype=uint8)
I recommend using OpenCV's grabcut algorithm. You first draw a few lines on the foreground and background, and keep doing this until your foreground is sufficiently separated from the background. It is covered here: https://docs.opencv.org/trunk/d8/d83/tutorial_py_grabcut.html
as well as in this video: https://www.youtube.com/watch?v=kAwxLTDDAwU
I have to make dilation on binary images
My problem is adapting dilation operation on difference sizes of binary images.
large image
large image dilated
small image
small image dilated
I want to apply proportionally dilation operation to all images and prevent that a small image like a wheel become a white circle.
#image dilation
import cv2
path "pathimage"
gray = cv2.imread(path,0)
element = cv2.getStructuringElement(cv2.MORPH_CROSS,(6,6))
graydilate = cv2.erode(gray, element) #imgbnbin
graydilate = cv2.erode(graydilate, element)
#graydilate = cv2.erode(graydilate, element)
cv2.imshow('erode',graydilate)
cv2.waitKey()
ret,thresh = cv2.threshold(graydilate,127,255,cv2.THRESH_BINARY_INV)
imgbnbin = thresh
print("shape imgbnbin")
print(imgbnbin.shape)
cv2.imshow('binaria',imgbnbin)
cv2.waitKey()
May I have to rescale images?
You can do either of the following:
Re-scale the images to the same size.
OR
If the object in the image is not directly proportional to the size of the image, then extract a bounding box for the object, and then determine the size of the structural element (currently always 6x6) relative to the size of the object's bounding box. That way you're sure that the morphology is proportional to the object size.