I have an image and I want to filter it to split the text from the background:
and after applying below code:
from skimage import filters
from skimage.filters import threshold_otsu
from skimage import io as skimage_io # So as not to clash with builtin io
dir = r"image_path/a.jpg"
img = skimage_io.imread(dir, as_gray=True, plugin='imageio')
blurred = filters.gaussian(img, sigma=2.0)
sobel = filters.sobel_h(blurred)
blurred += sobel
blurred += sobel
thresh = threshold_otsu(blurred)
# skimage_io.imshow(blurred)
print(thresh)
binary = img < thresh-0.1
skimage_io.imshow(binary)
The image became
Is there a way to make the result better ??
Yes, you can get a better result:
You do account for the noise, but the gaussian blur you apply is much too strong; it starts to dull out the features you are interested in (the letters).
As #Ziri pointed out in a comment, you are not accounting for the uneven exposure that is present in your image. There is many ways to do that; I will use a rolling ball filter to smooth out the background and combine it with a global thresholding method. Note that this is currently (August 2020) a PR in skimage, but will hopefully get merged soon.
import numpy as np
import matplotlib.pyplot as plt
from skimage import util
from skimage import filters
from skimage import io
from skimage import exposure
# PR 4851; will hopefully be in the library soon(TM)
from skimage.morphology import rolling_ellipsoid
img = io.imread("test.jpg", as_gray=True)
img_inv = util.invert(util.img_as_float(img))
# blurr the image slightly to remove noise
blurred = filters.gaussian(img_inv, sigma=1.0)
# remove background
background = rolling_ellipsoid(blurred, kernel_size=(50, 50), intensity_vertex=0.1)
normalized = blurred - background
# re-normalize intensity
normalized = exposure.rescale_intensity(normalized)
# binarize
binary = normalized > 0.38
binary = util.invert(binary)
plt.imshow(binary, cmap="gray")
plt.gca().axis("off")
plt.show()
Sidenote: It may not be wise to upload an uncensored picture of a passport to SO where it is freely accessible to anybody.
Related
I'm placeing a rotated image on top of another image of different anchor point in the same figure. However the top image partially covers the bottom image, shown below. Is there a way to remove the black border of the rotated image?
Sample codes here:
from bokeh.server.server import Server
from bokeh.application import Application
from bokeh.application.handlers.function import FunctionHandler
from bokeh.plotting import figure, ColumnDataSource, show
from bokeh.layouts import column
from bokeh.models.tools import PanTool, BoxZoomTool, WheelZoomTool, \
UndoTool, RedoTool, ResetTool, SaveTool, HoverTool
import numpy as np
from collections import namedtuple
from scipy import ndimage
def make_document(doc):
p = figure(match_aspect=True)
Anchor = namedtuple('Anchor', ['x', 'y'])
img1 = np.random.rand(256, 256)
anchor1 = Anchor(x=0, y=0)
img2= np.random.rand(256, 256)
anchor2 = Anchor(x=100, y=100)
img2 = ndimage.rotate(img2, 45, reshape=True)
p.image(image=[img1], x=anchor1.x, y=anchor1.y,
dw=img1.shape[0], dh=img1.shape[1], palette="Greys256")
p.image(image=[img2], x=anchor2.x, y=anchor2.y,
dw=img2.shape[0], dh=img2.shape[1], palette="Greys256")
doc.add_root(column(p, sizing_mode='stretch_both'))
apps = {'/': make_document}
server = Server(apps)
server.start()
server.io_loop.add_callback(server.show, "/")
try:
server.io_loop.start()
except KeyboardInterrupt:
print('keyboard interruption')
print('Done')
When you rotate an image, the new empty regions (black triangles on your image) are by default initialized with 0 (check out the mode and cval options at https://docs.scipy.org/doc/scipy/reference/generated/scipy.ndimage.rotate.html).
If you have a value that you know for sure will never be used in an image, you can pass it as cval. Then, you should be able to manually create a color mapper that maps that value to a transparent pixel and use the mapper instead of the palette (the arg name would be color_mapper).
If you don't have such a value, then you will have to use image_rgba and just make sure that whatever cval you decide to use will result in a transparent pixel.
So my problem is generating an animation from the list img_array. The code above that is basically used to get an image from the folder, annotate it and then save it into the array. Was wondering if anyone would have any suggestions on how to convert the images in the image array into an animation. Any help is appreciated! TIA.
I tried FFmepg and what not but none of them seem to work. I also tried videowriter in OpenCV but when I tried to open the file I get that this file type is not supported or corrupt.
import cv2
import numpy as np
import glob
import matplotlib.pyplot as plt
from skimage import io
import trackpy as tp
import pims
import pylab as pl
##########
pixel_min=23
min_mass=5000
Selector1=[1,2,3,4,5,6,7,11]
##########
frames = pims.ImageSequence('/Users/User/Desktop/eleventh_trial_2/*.tif', as_grey=True)
f1 = tp.locate(frames[0], pixel_min,minmass=min_mass)
plt.figure(1)
ax3=tp.annotate(f1,frames[0])
ax = plt.subplot()
ax.hist(f1['mass'], bins=20)
ax.set(xlabel='mass', ylabel='count');
f = tp.batch(frames[:], pixel_min, minmass=min_mass);
#f = tp.batch(frames[lower_frame:upper_frame], pixel, minmass=min_mass);
t=tp.link_df(f,10,memory=3)
##############
min_mass=8000#12000 #3000#2000 #6000#3000
pixel_min=23;
count=0
img_array = []
for filename in glob.glob('/Users/User/Desktop/eleventh_trial_2/*.tif'):
img = cv2.imread(filename)
height, width, layers = img.shape
size = (width,height)
img2 = io.imread(filename, as_gray=True)
fig, ax = plt.subplots()
ax.imshow(img)
#ax=pl.text(T1[i,1]+13,T1[i,0],str(int(T1[i,9])),color="red",fontsize=18)
T1=t.loc[t['frame']==count]
T1=np.array(T1.sort_values(by='particle'))
for i in Selector1:
pl.text(T1[i,1]+13,T1[i,0],str(int(T1[i,9])),color="red",fontsize=18)
circle2 = plt.Circle((T1[i,1], T1[i,0]), 5, color='r', fill=False)
ax.add_artist(circle2)
count=count+1
img_array.append(fig)
ani = animation.ArtistAnimation(fig, img_array, interval=50, blit=True,repeat_delay=1000)
When I run this I don't get an an error however I can't save the ani as tried in the past either using OpenCV videoWriter.
I found a work around although not the most efficient one. I saved the figures in a separate directory using os and plt.savefig() and then use ImageJ to automatically convert the sequentially numbered and saved figures into an animation. It ain't efficient but gets the job done. I am still open to more efficient answers. Thanks
I am was trying out one of the sample Python scripts available from the web site of Scikit Image. This script demonstrates Otsu segmentation at a local level. The script works with pictures loaded using
data.page()
but not using
io.imread
. Any suggestions?
https://scikit-image.org/docs/dev/auto_examples/applications/plot_thresholding.html#sphx-glr-auto-examples-applications-plot-thresholding-py
Picture file
Actual output - the Local thresholding window is empty
As you can see, Global thresholding has worked.But Local Thresholding has failed to produce any results.
Strangely, if I use data.page() then everything works fine.
Script
from skimage import io
from skimage.color import rgb2gray
import matplotlib.pyplot as plt
from skimage.filters import threshold_otsu,threshold_local
import matplotlib
from skimage import data
from skimage.util import img_as_ubyte
filename="C:\\Lenna.png"
mypic= img_as_ubyte (io.imread(filename))
#image = data.page() #This works - why not io.imread ?
imagefromfile=io.imread(filename)
image = rgb2gray(imagefromfile)
global_thresh = threshold_otsu(image)
binary_global = image > global_thresh
block_size = 35
local_thresh = threshold_local(image, block_size, offset=10)
binary_local = image > local_thresh
fig, axes = plt.subplots(nrows=3, figsize=(7, 8))
ax = axes.ravel()
plt.gray()
ax[0].imshow(image)
ax[0].set_title('Original')
ax[1].imshow(binary_global)
ax[1].set_title('Global thresholding')
ax[2].imshow(binary_local)
ax[2].set_title('Local thresholding')
for a in ax:
a.axis('off')
plt.show()
If you load the lenna.png and print its shape you will see it is a 4-channel RGBA image rather than a 3-channel RGB image.
print mypic.shape
(512, 512, 4)
I am not sure which parts of your code apply to which image, so I am not sure where to go next, but I guess you want to just get the RGB part and discard the alpha:
RGB = mypic[...,:3]
Keras provides an ImageDataGenerator class for realtime augmentation, but it does not include contrast adjustment and addition of noise.
How can we apply a random level of noise and a random contrast adjustment during training? Could these functions be added to the 'preprocessing_function' parameter in the datagen?
Thank you.
You could indeed add noise with preprocessing_function.
Example script:
import random
import numpy as np
def add_noise(img):
'''Add random noise to an image'''
VARIABILITY = 50
deviation = VARIABILITY*random.random()
noise = np.random.normal(0, deviation, img.shape)
img += noise
np.clip(img, 0., 255.)
return img
# Prepare data-augmenting data generator
from keras.preprocessing.image import ImageDataGenerator
datagen = ImageDataGenerator(
rescale=1./255,
rotation_range=40,
width_shift_range=0.2,
height_shift_range=0.2,
zoom_range=0.2,
preprocessing_function=add_noise,
)
# Load a single image as our example
from keras.preprocessing import image
img_path = 'cat_by_irene_mei_flickr.png'
img = image.load_img(img_path, target_size=(299,299))
# Generate distorted images
images = [img]
img_arr = image.img_to_array(img)
img_arr = img_arr.reshape((1,) + img_arr.shape)
for batch in datagen.flow(img_arr, batch_size=1):
images.append( image.array_to_img(batch[0]) )
if len(images) >= 4:
break
# Display
import matplotlib.pyplot as plt
f, xyarr = plt.subplots(2,2)
xyarr[0,0].imshow(images[0])
xyarr[0,1].imshow(images[1])
xyarr[1,0].imshow(images[2])
xyarr[1,1].imshow(images[3])
plt.show()
Example images generated by the script:
From the Keras docs:
preprocessing_function: function that will be implied on each input. The function will run before any other modification on it. The function should take one argument: one image (Numpy tensor with rank 3), and should output a Numpy tensor with the same shape.
So, I created a simple function and then used the image augmentation functions from the imgaug module. Note that imgaug requires images to be rank 4.
I found in this blog that you can do something as simple as:
from keras.layers import GaussianNoise
model.add(Dense(32))
model.add(GaussianNoise(0.1))
model.add(Activation('relu'))
model.add(Dense(32))
...
Unfortunately, I can't find an analogous way to adjust/augment the contrast. But you can, according to this post, augment the brightness with
from keras.preprocessing.image import ImageDataGenerator
ImageDataGenerator(brightness_range=[range_min,range_max])
Using python code we are able to create image segments as shown in the screenshot. our requirement is how to select specific segment in the image and apply different color to it ?
The following is our python snippet
from skimage.segmentation import felzenszwalb, slic,quickshift
from skimage.segmentation import mark_boundaries
from skimage.util import img_as_float
import matplotlib.pyplot as plt
from skimage import measure
from skimage import restoration
from skimage import img_as_float
image = img_as_float(io.imread("leaf.jpg"))
segments = quickshift(image, ratio=1.0, kernel_size=20, max_dist=10,return_tree=False, sigma=0, convert2lab=True, random_seed=42)
fig = plt.figure("Superpixels -- %d segments" % (500))
ax = fig.add_subplot(1, 1, 1)
ax.imshow(mark_boundaries(image, segments))
plt.axis("off")
plt.show()
do this:
seg_num = 64 # desired segment to be colored
color = float64([1,0,0]) # red color
image[segments == 64] = color # assign color to the segment
You can use OpenCV python module - example: