We Keep Coding

Get mask of image without using OpenCV

I'm trying the following to get the mask out of this image, but unfortunately I fail.
import numpy as np
import skimage.color
import skimage.filters
import skimage.io
# get filename, sigma, and threshold value from command line
filename = 'pathToImage'
# read and display the original image
image = skimage.io.imread(fname=filename)
skimage.io.imshow(image)
# blur and grayscale before thresholding
blur = skimage.color.rgb2gray(image)
blur = skimage.filters.gaussian(blur, sigma=2)
# perform inverse binary thresholding
mask = blur < 0.8
# use the mask to select the "interesting" part of the image
sel = np.ones_like(image)
sel[mask] = image[mask]
# display the result
skimage.io.imshow(sel)
How can I obtain the mask?
Is there a general approach that would work for this image as well. without custom fine-tuning and changing parameters?

Apply high contrast (maximum possible value)
convert to black & white image using high threshold (I've used 250)
min filter (value=8)
max filter (value=8)

Here is how you can get a rough mask using only the skimage library methods:
import numpy as np
from skimage.io import imread, imsave
from skimage.feature import canny
from skimage.color import rgb2gray
from skimage.filters import gaussian
from skimage.morphology import dilation, erosion, selem
from skimage.measure import find_contours
from skimage.draw import polygon
def get_mask(img):
kernel = selem.rectangle(7, 6)
dilate = dilation(canny(rgb2gray(img), 0), kernel)
dilate = dilation(dilate, kernel)
dilate = dilation(dilate, kernel)
erode = erosion(dilate, kernel)
mask = np.zeros_like(erode)
rr, cc = polygon(*find_contours(erode)[0].T)
mask[rr, cc] = 1
return gaussian(mask, 7) > 0.74
def save_img_masked(file):
img = imread(file)[..., :3]
mask = get_mask(img)
result = np.zeros_like(img)
result[mask] = img[mask]
imsave("masked_" + file, result)
save_img_masked('belt.png')
save_img_masked('bottle.jpg')
Resulting masked_belt.png:
Resulting masked_bottle.jpg:

One approach uses the fact that the background changes color only very slowly. Here I apply the gradient magnitude to each of the channels and compute the norm of the result, giving me an image highlighting the quicker changes in color. The watershed of this (with sufficient tolerance) should have one or more regions covering the background and touching the image edge. After identifying those regions, and doing a bit of cleanup we get these results (red line is the edge of the mask, overlaid on the input image):
I did have to adjust the tolerance, with a lower tolerance in the first case, more of the shadow is seen as object. I think it should be possible to find a way to set the tolerance based on the statistics of the gradient image, I have not tried.
There are no other parameters to tweak here, the minimum object area, 300, is quite safe; an alternative would be to keep only the one largest object.
This is the code, using DIPlib (disclaimer: I'm an author). out is the mask image, not the outline as displayed above.
import diplib as dip
import numpy as np
# Case 1:
img = dip.ImageRead('Pa9DO.png')
img = img[362:915, 45:877] # cut out actual image
img = img(slice(0,2)) # remove alpha channel
tol = 7
# Case 2:
#img = dip.ImageRead('jTnVr.jpg')
#tol = 1
# Compute gradient
gm = dip.Norm(dip.GradientMagnitude(img))
# Compute watershed with tolerance
lab = dip.Watershed(gm, connectivity=1, maxDepth=tol, flags={'correct','labels'})
# Identify regions touching the image edge
ll = np.unique(np.concatenate((
np.unique(lab[:,0]),
np.unique(lab[:,-1]),
np.unique(lab[0,:]),
np.unique(lab[-1,:]))))
# Remove regions touching the image edge
out = dip.Image(lab.Sizes(), dt='BIN')
out.Fill(1)
for l in ll:
if l != 0: # label zero is for the watershed lines
out = out - (lab == l)
# Remove watershed lines
out = dip.Opening(out, dip.SE(3, 'rectangular'))
# Remove small regions
out = dip.AreaOpening(out, filterSize=300)
# Display
dip.Overlay(img, dip.Dilation(out, 3) - out).Show()

Why is output image black after normalization?

I have many grayscale images that I want to normalize by using mean and standard deviation. I use the following process:
Calculate the image's mean and standard deviation.
Subtract the mean from the image.
Divide the resulting image by the standard deviation.
However, I got a black image as a result. What is wrong in my code?
import cv2
img = cv2.imread('E.png') # read an image
gray_image = cv2.cvtColor(img , cv2.COLOR_BGR2GRAY) # converting the image to grayscale image
img = cv2.resize(gray_image, (60, 60)) # Resize the image to the size 60x60 pixels
cv2.imwrite("Grayscale Image.png",img) #To write the result
mean, stdDev = cv2.meanStdDev(img) #Get Mean and Standard-deviation
image = (img-mean)/stdDev #Normalization process
cv2.imwrite("Normalized Image.png",image) #To write the result
Input image :
Grayscale output:
Normalized image output:

When you save the image you need to consider the data type. To save the normalized image as png, you need to scale the normalized values to integer range (such as [0, 255]) or use image format that supports floating point format.
When using z-score normalization (as in your code), you could save it as png with
image -= image.min()
image /= image.max()
image *= 255 # [0, 255] range
cv2.imwrite("Normalized Image.png", image)

Incorrect number of indices while increasing brightness of a color image

Code works fine while reading a gray scale image to perform brightness. But same code doesn't work with color image.
How to perform brightness operation from a color image?
While reading the image using cv2.imread at the argument 0 works fine but I tried with 1 it doesn't work as 0 is for gray scale image and 1 for color image.
import numpy as np
import cv2
img = cv2.imread('image1.jpg',1)
height = img.shape[0]
width = img.shape[1]
brightness = 100
for i in np.arange(height):
for j in np.arange(width):
a = img.item(i,j)
b = a + brightness
if b > 255:
b = 255
img.itemset((i,j), b)
cv2.imwrite('brightness.jpg', img)
cv2.imshow('image',img)
cv2.waitKey(0)
cv2.destroyAllWindows()
I expect a color image to be read and perform brightness operation but it is showing ValueError: incorrect number of indices for array

The problem is a colored image has multiple channels for the different color (example, RGB or RGBA) so when you do img.item(i,j) you are missing the third dimension (the three color channels). You can add another for loop that loops over each of the color channels but you can also just use numpy's minimum function to make it more efficient (i.e. add 255 to the values of your image and if it's greater than 255 it will use 255).
import numpy as np
import cv2
img = cv2.imread('image1.jpg',1)
brightness = 100
np.minimum(img + brightness, 255)
cv2.imwrite('brightness.jpg', img)
cv2.imshow('image',img)
cv2.waitKey(0)
cv2.destroyAllWindows()

One solution is to use OpenCV normalize to stretch the image to full dynamic range (0 to 255).
Here are two output results depending upon the min and max stretch limits. Note that normalize works on float data and the min and max values are nominally stretched to full range of 0 to 1. But we ned to clip the results to this range and then scale them to the range 0 to 255 before saving as uint8 for output, if the min and max values are outside the range of 0 to 1.
The first result is stretched to min and max of 0 to 1.
The second result is stretched to min and max of 0 to 1.2 in order to make it even brighter.
Image:
#!/bin/python3.7
import cv2
import numpy as np
# read image
img = cv2.imread("zelda1_bm20_cm20.jpg", cv2.IMREAD_COLOR)
# normalize float versions
norm_img1 = cv2.normalize(img, None, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32F)
norm_img2 = cv2.normalize(img, None, alpha=0, beta=1.2, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32F)
# scale to uint8
norm_img1 = (255*norm_img1).astype(np.uint8)
norm_img2 = np.clip(norm_img2, 0, 1)
norm_img2 = (255*norm_img2).astype(np.uint8)
# write normalized output images
cv2.imwrite("zelda1_bm20_cm20_normalize1.jpg",norm_img1)
cv2.imwrite("zelda1_bm20_cm20_normalize2.jpg",norm_img2)
# display input and both output images
cv2.imshow('original',img)
cv2.imshow('normalized1',norm_img1)
cv2.imshow('normalized2',norm_img2)
cv2.waitKey(0)
cv2.destroyAllWindows()
Min and Max (0 to 1):
Min and Max (0 to 1.2):

MRI (brain tumor) image processing and segmentation, skull removing

I need help for image segmentation. I have a MRI image of brain with tumor. I need to remove cranium (skull) from MRI and then segment only tumor object. How could I do that in python? with image processing. I have tried make contours, but I don't know how to find and remove the largest contour and get only brain without a skull.
Thank's a lot.
def get_brain(img):
row_size = img.shape[0]
col_size = img.shape[1]
mean = np.mean(img)
std = np.std(img)
img = img - mean
img = img / std
middle = img[int(col_size / 5):int(col_size / 5 * 4), int(row_size / 5):int(row_size / 5 * 4)]
mean = np.mean(middle)
max = np.max(img)
min = np.min(img)
img[img == max] = mean
img[img == min] = mean
kmeans = KMeans(n_clusters=2).fit(np.reshape(middle, [np.prod(middle.shape), 1]))
centers = sorted(kmeans.cluster_centers_.flatten())
threshold = np.mean(centers)
thresh_img = np.where(img < threshold, 1.0, 0.0) # threshold the image
eroded = morphology.erosion(thresh_img, np.ones([3, 3]))
dilation = morphology.dilation(eroded, np.ones([5, 5]))
These images are similar to the ones I'm looking at:
Thanks for answers.

Preliminaries
Some preliminary code:
%matplotlib inline
import numpy as np
import cv2
from matplotlib import pyplot as plt
from skimage.morphology import extrema
from skimage.morphology import watershed as skwater
def ShowImage(title,img,ctype):
plt.figure(figsize=(10, 10))
if ctype=='bgr':
b,g,r = cv2.split(img) # get b,g,r
rgb_img = cv2.merge([r,g,b]) # switch it to rgb
plt.imshow(rgb_img)
elif ctype=='hsv':
rgb = cv2.cvtColor(img,cv2.COLOR_HSV2RGB)
plt.imshow(rgb)
elif ctype=='gray':
plt.imshow(img,cmap='gray')
elif ctype=='rgb':
plt.imshow(img)
else:
raise Exception("Unknown colour type")
plt.axis('off')
plt.title(title)
plt.show()
For reference, here's one of the brain+skulls you linked to:
#Read in image
img = cv2.imread('brain.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
ShowImage('Brain with Skull',gray,'gray')
Extracting a Mask
If the pixels in the image can be classified into two different intensity classes, that is, if they have a bimodal histogram, then Otsu's method can be used to threshold them into a binary mask. Let's check that assumption.
#Make a histogram of the intensities in the grayscale image
plt.hist(gray.ravel(),256)
plt.show()
Okay, the data is nicely bimodal. Let's apply the threshold and see how we do.
#Threshold the image to binary using Otsu's method
ret, thresh = cv2.threshold(gray,0,255,cv2.THRESH_OTSU)
ShowImage('Applying Otsu',thresh,'gray')
Things are easier to see if we overlay our mask onto the original image
colormask = np.zeros(img.shape, dtype=np.uint8)
colormask[thresh!=0] = np.array((0,0,255))
blended = cv2.addWeighted(img,0.7,colormask,0.1,0)
ShowImage('Blended', blended, 'bgr')
Extracting the Brain
The overlap of the brain (shown in red) with the mask is so perfect, that we'll stop right here. To do so, let's extract the connected components and find the largest one, which will be the brain.
ret, markers = cv2.connectedComponents(thresh)
#Get the area taken by each component. Ignore label 0 since this is the background.
marker_area = [np.sum(markers==m) for m in range(np.max(markers)) if m!=0]
#Get label of largest component by area
largest_component = np.argmax(marker_area)+1 #Add 1 since we dropped zero above
#Get pixels which correspond to the brain
brain_mask = markers==largest_component
brain_out = img.copy()
#In a copy of the original image, clear those pixels that don't correspond to the brain
brain_out[brain_mask==False] = (0,0,0)
ShowImage('Connected Components',brain_out,'rgb')
Considering the Second Brain
Running this again with your second image produces a mask with many holes:
We can close many of these holes using a closing transformation:
brain_mask = np.uint8(brain_mask)
kernel = np.ones((8,8),np.uint8)
closing = cv2.morphologyEx(brain_mask, cv2.MORPH_CLOSE, kernel)
ShowImage('Closing', closing, 'gray')
We can now extract the brain:
brain_out = img.copy()
#In a copy of the original image, clear those pixels that don't correspond to the brain
brain_out[closing==False] = (0,0,0)
ShowImage('Connected Components',brain_out,'rgb')
If you need to cite this for some reason:
Richard Barnes. (2018). Using Otsu's method for skull-brain segmentation (v1.0.1). Zenodo. https://doi.org/10.5281/zenodo.6042312

Have you perhaps tried to use python skull_stripping.py
You can modify the parameters but it normally works good.
There are some new studies using deep learning for skull stripping which I found it interesting:
https://github.com/mateuszbuda/brain-segmentation/tree/master/skull-stripping

# -*- coding: utf-8 -*-
"""
Created on Wed Jul 28 17:10:56 2021
#author: K Somasundaram, ka.somasundaram#gmail.com
"""
import numpy as npy
from skimage.filters import threshold_otsu
from skimage import measure
# import image reading module image from matplotlib
import matplotlib.image as img
#import image ploting module pyplot from matplotlib
import matplotlib.pyplot as plt
inim=img.imread('015.bmp')
#Find the dimension of the input image
dimn=inim.shape
print('dim=',dimn)
plt.figure(1)
plt.imshow(inim)
#-----------------------------------------------
# Find a threshold for the image using Otsu method in filters
th=threshold_otsu(inim)
print('Threshold = ',th)
# Binarize using threshold th
binim1=inim>th
plt.figure(2)
plt.imshow(binim1)
#--------------------------------------------------
# Erode the binary image with a structuring element
from skimage.morphology import disk
import skimage.morphology as morph
#Erode it with a radius of 5
eroded_image=morph.erosion(binim1,disk(3))
plt.figure(3)
plt.imshow(eroded_image)
#---------------------------------------------
#------------------------------------------------
# label the binar image
labelimg=measure.label(eroded_image,background=0)
plt.figure(4)
plt.imshow(labelimg)
#--------------------------------------------------
# Find area of the connected regiond
prop=measure.regionprops(labelimg)
# Find the number of objecte in the image
ncount=len(prop)
print ( 'Number of regions=',ncount)
#-----------------------------------------------------
# Find the LLC index
argmax=0
maxarea=0
#Find the largets connected region
for i in range(ncount):
if(prop[i].area >maxarea):
maxarea=prop[i].area
argmax=i
print('max area=',maxarea,'arg max=',argmax)
print('values=',[region.area for region in prop])
# Take only the largest connected region
# Generate a mask of size of th einput image with all zeros
bmask=npy.zeros(inim.shape,dtype=npy.uint8)
# Set all pixel values in whole image to the LCC index to 1
bmask[labelimg == (argmax+1)] =1
plt.figure(5)
plt.imshow(bmask)
#------------------------------------------------
#Dilate the isolated region to recover the pixels lost in erosion
dilated_mask=morph.dilation(bmask,disk(6))
plt.figure(6)
plt.imshow(dilated_mask)
#---------------------------------------
# Extract the brain using the barinmask
brain=inim*dilated_mask
plt.figure(7)
plt.imshow(brain)
-----------------------------------------
Input Image
--------------------

Normalizing images in OpenCV produces black image?

I wrote the following code to normalize an image using NORM_L1 in OpenCV. But the output image was just black. How to solve this?
import cv2
import numpy as np
import Image
img = cv2.imread('img7.jpg')
gray_image = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
a = np.asarray(gray_image)
dst = np.zeros(shape=(5,2))
b=cv2.normalize(a,dst,0,255,cv2.NORM_L1)
im = Image.fromarray(b)
im.save("img50.jpg")
cv2.waitKey(0)
cv2.destroyAllWindows()

If you want to change the range to [0, 1], make sure the output data type is float.
image = cv2.imread("lenacolor512.tiff", cv2.IMREAD_COLOR) # uint8 image
norm_image = cv2.normalize(image, None, alpha=0, beta=1, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32F)

The other answers normalize an image based on the entire image. But if your image has a predominant color (such as black), it will mask out the features that you're trying to enhance since it will not be as pronounced. To get around this limitation, we can normalize the image based on a subsection region of interest (ROI). Essentially we will normalize based on the section of the image that we want to enhance instead of equally treating each pixel with the same weight. Take for instance this earth image:
Input image -> Normalization based on entire image
If we want to enhance the clouds by normalizing based on the entire image, the result will not be very sharp and will be over saturated due to the black background. The features to enhance are lost. So to obtain a better result we can crop a ROI, normalize based on the ROI, and then apply the normalization back onto the original image. Say we crop the ROI highlighted in green:
This gives us this ROI
The idea is to calculate the mean and standard deviation of the ROI and then clip the frame based on the lower and upper range. In addition, we could use an offset to dynamically adjust the clip intensity. From here we normalize the original image to this new range. Here's the result:
Before -> After
Code
import cv2
import numpy as np
# Load image as grayscale and crop ROI
image = cv2.imread('1.png', 0)
x, y, w, h = 364, 633, 791, 273
ROI = image[y:y+h, x:x+w]
# Calculate mean and STD
mean, STD = cv2.meanStdDev(ROI)
# Clip frame to lower and upper STD
offset = 0.2
clipped = np.clip(image, mean - offset*STD, mean + offset*STD).astype(np.uint8)
# Normalize to range
result = cv2.normalize(clipped, clipped, 0, 255, norm_type=cv2.NORM_MINMAX)
cv2.imshow('image', image)
cv2.imshow('ROI', ROI)
cv2.imshow('result', result)
cv2.waitKey()
The difference between normalizing based on the entire image vs a specific section of the ROI can be visualized by applying a heatmap to the result. Notice the difference on how the clouds are defined.
Input image -> heatmap
Normalized on entire image -> heatmap
Normalized on ROI -> heatmap
Heatmap code
import matplotlib.pyplot as plt
import numpy as np
import cv2
image = cv2.imread('result.png', 0)
colormap = plt.get_cmap('inferno')
heatmap = (colormap(image) * 2**16).astype(np.uint16)[:,:,:3]
heatmap = cv2.cvtColor(heatmap, cv2.COLOR_RGB2BGR)
cv2.imshow('image', image)
cv2.imshow('heatmap', heatmap)
cv2.waitKey()
Note: The ROI bounding box coordinates were obtained using how to get ROI Bounding Box Coordinates without Guess & Check and heatmap code was from how to convert a grayscale image to heatmap image with Python OpenCV

When you normalize a matrix using NORM_L1, you are dividing every pixel value by the sum of absolute values of all the pixels in the image.
As a result, all pixel values become much less than 1 and you get a black image. Try NORM_MINMAX instead of NORM_L1.