I have PIL Image in binary and I need to convert it in RGB. I did this diskew image
binary image
I need this way:
I already tried this which is not working
from PIL import Image as im
img = im.fromarray((255 * Image).astype("uint8")).convert("RGB")
I still don't understand why you convert to RGBA if you want RGB, but this code converts your image to RGB as you ask:
#!/usr/local/bin/python3
import numpy as np
from PIL import Image
# Open input image
im = Image.open('text.png').convert('RGB')
# Invert
npim = 255 - np.array(im)
# Save
Image.fromarray(npim).save('result.png')
Related
To load my image dataset, I have done following coding
X=[]
for i in range(1,682):
image=Image.open(str(i)+'.jpg')
image=image.resize((100,100))
temp=asarray(image)
X.append(temp)
Shape of X is (681,100,100,3) but I want shape of X to be (681,100,100). How can I do that?
You can use opencv to read images it reads images as numpy arrays
import cv2
X=[]
for i in range(1,682):
temp = cv2.imread(str(i)+'.jpg', cv2.IMREAD_GRAYSCALE)
temp = cv2.resize(temp, (100,100))
X.append(temp)
I have following Image file:
Image
I used PIL and Skimage to open it but I get following errors
First with PIL (tried with and without trucate option):
Code:
from PIL import Image, ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
img = Image.open("image_output.pgm")
Erorr:
OSError: cannot identify image file 'image_output.pgm'
And with Skimage:
Code:
from skimage import io
img = io.imread("image_output.pgm")
Error:
OSError: cannot identify image file <_io.BufferedReader name='image_output.pgm'>
I can open the file with GUI applications like system photo viewer and Matlab.
How can I diagnose what is wrong with image? I compared the byte data with other PGM files which I can open in Python, but could not identify the difference.
Thanks.
Your file is P2 type PGM, which means it is in ASCII - you can view it in a normal text editor. It seems neither PIL, nor skimage want to read that, but are happy to read the corresponding P5 type which is identical except it is written in binary, rather than ASCII.
There are a few options...
1) You could use OpenCV to read it:
import cv2
im = cv2.imread('a.pgm')
2) You could convert it to P5 with ImageMagick and then read the output.pgm file with skimage or PIL:
magick input.pgm output.pgm
3) If adding OpenCV, or ImageMagick as a dependency is a real pain for you, it is possible to read a PGM image yourself:
#!/usr/bin/env python3
import re
import numpy as np
# Open image file, slurp the lot
with open('input.pgm') as f:
s = f.read()
# Find anything that looks like numbers
# Technically, there could be comments that should be ignored
l=re.findall(r'[0-9P]+',s)
# List "l" will contain: P5, width, height, 255, pixel1, pixel2, pixel3...
# Technically, if l[3]>255, you should change the type of the Numpy array to uint16, but that is not the case
w, h = int(l[1]), int(l[2])
# Make Numpy image from data
ni = np.array(l[4:],dtype=np.uint8).reshape((h,w))
import time
# cv2.cvtColor takes a numpy ndarray as an argument
import numpy as nm
import pytesseract
# importing OpenCV
import cv2
from PIL import ImageGrab, Image
bboxes = [(1469, 1014, 1495, 1029)]
def imToString():
# Path of tesseract executable
pytesseract.pytesseract.tesseract_cmd = 'D:\Program Files (x86)\Tesseract-OCR' + chr(92) + 'tesseract.exe'
while (True):
for box in bboxes:
# ImageGrab-To capture the screen image in a loop.
# Bbox used to capture a specific area.
cap = ImageGrab.grab(bbox=box)
# Converted the image to monochrome for it to be easily
# read by the OCR and obtained the output String.
tesstr = pytesseract.image_to_string(
cv2.cvtColor(nm.array(cap), cv2.COLOR_BGR2GRAY), lang='eng', config='digits') # ,lang='eng')
cap.show()
#input()
time.sleep(5)
print(tesstr)
# Calling the function
imToString()
It captures an image like this:
It isn't always two digits it can be one or three digits too.
Pytesseract returns values like: asi and oli
So, which Image To Text (OCR) Algorithm should I use for this problem? And, how to use that? I need a very precise value in this example it's 53 so the output should be around 50.
i can show the image using image.open, but how do i display from the binary data?
trying to use plot gets: ValueError: x and y can be no greater than 2-D, but have shapes (64,) and (64, 64, 3). this makes sense as that is what the result is supposed to be, but how do i display it?
import pathlib
import glob
from os.path import join
import matplotlib.pyplot as plt
from PIL import Image
import tensorflow as tf
def parse(image): # my like ings, but with .png instead of .jpeg.
image_string = tf.io.read_file(image)
image = tf.image.decode_png(image_string, channels=3)
image = tf.image.convert_image_dtype(image, tf.float32)
image = tf.image.resize(image, [64, 64])
return image
root = "in/flower_photos/tulips"
path = join(root,"*.jpg")
files = sorted(glob.glob(path))
file=files[0]
image = Image.open(file)
image.show()
binary=parse(file)
print(type(binary))
# how do i see this?
#plt.plot(binary) # does not seem to work
#plt.show() # does not seem to work
found a nice pillow tutorial.
from matplotlib import image
from matplotlib import pyplot
from PIL import Image
# load the image
filename='Sydney-Opera-House.jpg'
im = Image.open(filename)
# summarize some details about the image
print(im.format)
print(im.mode)
print(im.size)
# show the image
#image.show()
# load image as pixel array
data = image.imread(filename)
# summarize shape of the pixel array
print(data.dtype)
print(data.shape)
# display the array of pixels as an image
pyplot.imshow(data)
pyplot.show()
I want to analyze infrared images of solar panels and cut the panels from the images. As a first step I need to threshold the image. But if I do it with a example image from google like the one below I only get a black image. What I can do to improve?
import cv2
import numpy as np
img = cv2.imread('GooglePanelIR.png')
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
ret,thresh1 = cv2.threshold(hsv[:,:,0],100,255,cv2.THRESH_BINARY)
cv2.imshow('cont imge', thresh1)
cv2.waitKey(0)
print(ret)
Since you need to threshold and its a grayscale image, import your image in grayscale.
This is what you are looking for.
import cv2
import numpy as np
img = cv2.imread('GooglePanelIR.png', 0)
ret,thresh1 = cv2.threshold(img,100,255,cv2.THRESH_BINARY)
cv2.imshow('cont imge', thresh1)
cv2.waitKey(0)
print(ret)