Working with TIFF in Python using EasyOCR - python

I use a Python Module EasyOCR for extracting text from image. This Method works for PNG Format but in TIFF Situation give me a error
Code look like this:
import easyocr
import cv2
from matplotlib import pyplot as plt
import numpy as np
IMAGE_PATH = 'IMG_4022.tif'
reader = easyocr.Reader(['en'], gpu=False)
result = reader.readtext(IMAGE_PATH)
result
I work with Juypter Notebook

You are not reading the image. Please use opencv to read the image. Ensure that the image is in the current directory or provide the absolute path of the image.
from easyocr import Reader
import cv2
from matplotlib import pyplot as plt
import numpy as np
IMAGE_PATH = "IMG_4022.tif"
image = cv2.imread(IMAGE_PATH)
languages = ['en']
reader = Reader(languages, gpu = False)
results = reader.readtext(image)

Related

Loading non RGBA 4-tile multi page tiff images with skimage into dask array

I need to read a folder full of multi-page tiffs generated by the Suite2p neurobiology package.
From the Suite2p source code the multi-tiffs are created as follows:
import numpy as np
from tifffile import TiffWriter
# fake example images
img_5_tiles = np.random.randint(0,65535,(5,10,20), dtype='uint16')
img_4_tiles = img_5_tiles[1:,...]
# save fake images
with TiffWriter(r'D:\5tiles.tiff') as tif:
for frame in img_5_tiles:
tif.save(frame)
with TiffWriter(r'D:\4tiles.tiff') as tif:
for frame in img_4_tiles:
tif.save(frame)
When I try to read them into dask, skimage.io default tifffile plugin fails to get the correct shape:
from dask.array.image import imread
from skimage import io
def read_with_tifffile(path):
return io.imread(path, plugin='tifffile')
# should produce (5,10,20) instead of (1,10,20)
imread(r'D:\5tiles.tiff', imread=read_with_tifffile).shape
I can overcome this by using the non-default skimage.io.imread plugin 'pil'
def read_with_pil(path):
return io.imread(path, plugin='pil', mode='L')
# gives (1,5,10,20) which is acceptable
imread(r'D:\5tiles.tiff', imread=read_with_pil).shape
Unfortunately, if the number of tiles equals to 4, skimage starts to handle the shape differently:
# gives (1,10,20,4) instead of (1,4,10,20)
imread(r'D:\4tiles.tiff', imread=read_with_pil).shape
From reading skimage docs, it's probably trying to interpret my image as RGBA and then fails.
Is there a solution to force 'uint16' multipage read for all image shapes?
Any advice is appreciated!
Based on cgohlke's comment:
from dask.array.image import imread
import numpy as np
from skimage import io
import tifffile
# fake data
img_with_4_tiles = np.random.randint(0,65535,(4,10,20), dtype='uint16')
with tifffile.TiffWriter(r'D:\4tiles.tiff') as tif:
for frame in img_with_4_tiles:
tif.save(frame)
# my original bad solution
def read_with_pil(path):
return io.imread(path, plugin='pil', mode='L')
print(imread(r'D:\4tiles.tiff', imread=read_with_pil).shape)
# a good solution from the horse's mouth (https://pypi.org/user/cgohlke/)
def read_with_tifffile(path):
return tifffile.imread(path, is_shaped=False)
print(imread(r'D:\4tiles.tiff', imread=read_with_tifffile).shape)

Extract from zip file to a list

I'm trying to extract a set of photos from a zip file using python
and then saving those pictures to an image list to do some work on each.
I tried a lot, but nothing was useful to me.
Try this:
import zipfile
path = 'path_to_zip.zip'
input_zip = zipfile.ZipFile(path)
l = [input_zip.read(name) for name in input_zip.namelist()]
To Display one of the images you can do:
import io
import matplotlib.pyplot as plt
from PIL import Image
image = Image.open(io.BytesIO(l[0]))
plt.imshow(image)

ValueError: Could not find a format to write the specified file in single-image mode

I am trying to read an image using skimage package, then crop it and then save it.
Till cropping it works fine. While saving, it throws the below error
ValueError: Could not find a format to write the specified file in
single-image mode
Below is my code. Any help is highly appreciated.
thanks
import os
import numpy as np
import matplotlib.pyplot as plt
import skimage
import dataloader
from utility import To_csv
path='D:\\beantech_Data\\objtect_detection'
def crop(img):
return skimage.util.crop(img, ((0,500),(0,0),(0,0)))
images, boxes, labels = dataloader.train_loader(path)
os.makedirs(os.path.join(path, 'train','cropped'), exist_ok=True)
for i in range(len(images)):
croped_image = crop(images[i])
skimage.io.imsave(os.path.join(path, 'train','cropped',f'img{str(i)}'), croped_image)
box = boxes[i]
To_csv(box, i,os.path.join(path, 'train','cropped'), Aug= True )
The problem is, no file format is given in the code i.e. (.png, .jpeg etc).
By correcting this line the code works fine-
skimage.io.imsave(os.path.join(path, 'train','cropped',f'img{str(i)}.png'), croped_image)
thanks

Importing PNG files into Numpy?

I have about 200 grayscale PNG images stored within a directory like this.
1.png
2.png
3.png
...
...
200.png
I want to import all the PNG images as NumPy arrays.
How can I do this?
According to the doc, scipy.misc.imread is deprecated starting SciPy 1.0.0, and will be removed in 1.2.0. Consider using imageio.imread instead.
Example:
import imageio
im = imageio.imread('my_image.png')
print(im.shape)
You can also use imageio to load from fancy sources:
im = imageio.imread('http://upload.wikimedia.org/wikipedia/commons/d/de/Wikipedia_Logo_1.0.png')
Edit:
To load all of the *.png files in a specific folder, you could use the glob package:
import imageio
import glob
for im_path in glob.glob("path/to/folder/*.png"):
im = imageio.imread(im_path)
print(im.shape)
# do whatever with the image here
Using just scipy, glob and having PIL installed (pip install pillow) you can use scipy's imread method:
from scipy import misc
import glob
for image_path in glob.glob("/home/adam/*.png"):
image = misc.imread(image_path)
print image.shape
print image.dtype
UPDATE
According to the doc, scipy.misc.imread is deprecated starting SciPy 1.0.0, and will be removed in 1.2.0. Consider using imageio.imread instead. See the answer by Charles.
This can also be done with the Image class of the PIL library:
from PIL import Image
import numpy as np
im_frame = Image.open(path_to_file + 'file.png')
np_frame = np.array(im_frame.getdata())
Note: The .getdata() might not be needed - np.array(im_frame) should also work
Using a (very) commonly used package is prefered:
import matplotlib.pyplot as plt
im = plt.imread('image.png')
If you are loading images, you are likely going to be working with one or both of matplotlib and opencv to manipulate and view the images.
For this reason, I tend to use their image readers and append those to lists, from which I make a NumPy array.
import os
import matplotlib.pyplot as plt
import cv2
import numpy as np
# Get the file paths
im_files = os.listdir('path/to/files/')
# imagine we only want to load PNG files (or JPEG or whatever...)
EXTENSION = '.png'
# Load using matplotlib
images_plt = [plt.imread(f) for f in im_files if f.endswith(EXTENSION)]
# convert your lists into a numpy array of size (N, H, W, C)
images = np.array(images_plt)
# Load using opencv
images_cv = [cv2.imread(f) for f in im_files if f.endswith(EXTENSION)]
# convert your lists into a numpy array of size (N, C, H, W)
images = np.array(images_cv)
The only difference to be aware of is the following:
opencv loads channels first
matplotlib loads channels last.
So a single image that is 256*256 in size would produce matrices of size (3, 256, 256) with opencv and (256, 256, 3) using matplotlib.
To read in one image:
import PIL.Image
im = PIL.Image.open('path/to/your/image')
im = np.array(im)
Iterate to read in multiple images.
This answer is similar to this but simpler (no need for .getdata()).
I changed a bit and it worked like this, dumped into one single array, provided all the images are of same dimensions.
png = []
for image_path in glob.glob("./train/*.png"):
png.append(misc.imread(image_path))
im = np.asarray(png)
print 'Importing done...', im.shape
I like the build-in pathlib libary because of quick options like directory= Path.cwd()
Together with opencv it's quite easy to read pngs to numpy arrays.
In this example you can even check the prefix of the image.
from pathlib import Path
import cv2
prefix = "p00"
suffix = ".png"
directory= Path.cwd()
file_names= [subp.name for subp in directory.rglob('*') if (prefix in subp.name) & (suffix == subp.suffix)]
file_names.sort()
print(file_names)
all_frames= []
for file_name in file_names:
file_path = str(directory / file_name)
frame=cv2.imread(file_path)
all_frames.append(frame)
print(type(all_frames[0]))
print(all_frames[0] [1][1])
Output:
['p000.png', 'p001.png', 'p002.png', 'p003.png', 'p004.png', 'p005.png', 'p006.png', 'p007.png', 'p008.png', 'p009.png']
<class 'numpy.ndarray'>
[255 255 255]
If you prefer the standard library:
#IMPORTANT: This Code only works with Python>=3.6
Directory="."#Your directory
import os
import tkinter
import numpy
tk=tkinter.Tk()
tk.overrideredirect(1)
tk.geometry("0x0")
Items=[]
for i in os.listdir(Directory):
fn=Directory+os.sep+i
imgArray=[]
image=tkinter.PhotoImage(file=fn)
for w in range(image.width()):
entry=[]
for h in range(image.height()):
entry.append(image.get(w,h))
imgArray.append(entry)
imgArray=numpy.array(imgArray)
Items.append(imgArray)
tk.destroy()

Scale imread matrix in python

I am looking for a way to rescale the matrix given by reading in a png file using the matplotlib routine imread,
e.g.
from pylab import imread, imshow, gray, mean
from matplotlib.pyplot import show
a = imread('spiral.png')
#generates a RGB image, so do
show()
but actually I want to manually specify the dimension of $a$, say 200x200 entries, so I need some magic command (which I assume exists but cannot be found by myself) to interpolate the matrix.
Thanks for any useful comments : )
Cheers
You could try using the PIL (Image) module instead, together with numpy. Open and resize the image using Image then convert to array using numpy. Then display the image using pylab.
import pylab as pl
import numpy as np
from PIL import Image
path = r'\path\to\image\file.jpg'
img = Image.open(path)
img.resize((200,200))
a = np.asarray(img)
pl.imshow(a)
pl.show()
Hope this helps.

Categories

Resources