This image is divided into 3 colors, but I would like to be able to identify the color of the image in Python3.
Please teach.
from PIL import Image
import PIL
import numpy as np
png_path = 'test.png'
img_array = np.asarray(Image.open(png_path))
Image.fromarray(img_array).show()
img_array = np.asarray(Image.open(png_path))[:,:,3]
print(np.unique(img_array))
##### I want to know the condition judgment method######
img_array_2 = np.where((img_array >=1) & (img_array <= 150), 0 , img_array)
##################
# check
imgPIL = Image.fromarray(img_array_2)
imgPIL.show()
Once you have the list in the color palette, it will be easier to separate them.
Image.getpalette() Returns the image palette as a list.
Returns: A list of color values [r, g, b, ...], or None if the image
has no palette.
https://pillow.readthedocs.io/en/4.1.x/reference/Image.html#PIL.Image.Image.getpalette
I have set of 17 images and one of them has a highlighted pixel for my use. But, when I merge these 17 images, I get the color but it diffuses out of the pixel boundaries and I start seeing some colored pixel in black background.
I am using PIL library for the merging. I am attaching my code and the images for the reference. Any help would be appreciated.
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Cretaing the Pixel array
from PIL import Image
from PIL import ImageColor
img_path = '/Volumes/MY_PASSPORT/JRF/cancer_genome/gopal_gen/png_files/'
image_list = []
for entry in os.listdir(img_path):
if entry.endswith('.png'):
entry = int(entry.rstrip('.csv.png'))
image_list.append(entry)
image_list.sort()
list_img = []
for j in range(len(image_list)):
stuff = str(image_list[j])+'.csv.png'
list_img.append(stuff)
#print(list_img[0])
images = [Image.open(img_path+x) for x in list_img]
widths, heights = zip(*(i.size for i in images))
total_width = sum(widths)
max_height = max(heights)
#print(total_width, max_height)
new_im = Image.new('RGB', (total_width, max_height))
x_offset = 0
for im in images:
new_im.paste(im, (x_offset,0))
#print(im.size)
x_offset += im.size[0]
#print(x_offset)
new_im.save(img_path+'final_result_image.jpg')
Here is the combined image:
The third column has a pixel highlighted.
Here is the zoomed in part with the problem.
The JPEG format is lossy - it is allowed to change your pixels to make the file smaller. If your image is a conventional photo of a real-life scene, this doesn't normally matter. If your data is a blocky, computer-generated image, or a set of classes from a classification process, it can go horribly wrong if you use JPEG.
So, the answer is to use PNG (or potentially TIFF) format for images that need to be lossless.
I am new to OpenCV and trying to see if I can find a way to detect vertical text for the image attached.
In this case on row 3 , I would like to get the bounding box around Original Cost and the amount below ($200,000.00).
Similarly I would like to get the bounding box around Amount Existing Liens and the associated amount below. I then would use this data to send to an OCR engine to read text. Traditional OCR engines go line by line and extract and loses the context.
Here is what I have tried so far -
import cv2
import numpy as np
img = cv2.imread('Test3.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray,100,100,apertureSize = 3)
cv2.imshow('edges',edges)
cv2.waitKey(0)
minLineLength = 20
maxLineGap = 10
lines = cv2.HoughLinesP(edges,1,np.pi/180,15,minLineLength=minLineLength,maxLineGap=maxLineGap)
for x in range(0, len(lines)):
for x1,y1,x2,y2 in lines[x]:
cv2.line(img,(x1,y1),(x2,y2),(0,255,0),2)
cv2.imshow('hough',img)
cv2.waitKey(0)
Here is my solution based on Kanan Vyas and Adrian Rosenbrock
It's probably not as "canonical" as you'd wish.
But it seems to work (more or less...) with the image you provided.
Just a word of CAUTION: The code looks within the directory from which it is running, for a folder named "Cropped" where cropped images will be stored. So, don't run it in a directory which already contains a folder named "Cropped" because it deletes everything in this folder at each run. Understood? If you're unsure run it in a separate folder.
The code:
# Import required packages
import cv2
import numpy as np
import pathlib
###################################################################################################################################
# https://www.pyimagesearch.com/2015/04/20/sorting-contours-using-python-and-opencv/
###################################################################################################################################
def sort_contours(cnts, method="left-to-right"):
# initialize the reverse flag and sort index
reverse = False
i = 0
# handle if we need to sort in reverse
if method == "right-to-left" or method == "bottom-to-top":
reverse = True
# handle if we are sorting against the y-coordinate rather than
# the x-coordinate of the bounding box
if method == "top-to-bottom" or method == "bottom-to-top":
i = 1
# construct the list of bounding boxes and sort them from top to
# bottom
boundingBoxes = [cv2.boundingRect(c) for c in cnts]
(cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
key=lambda b:b[1][i], reverse=reverse))
# return the list of sorted contours and bounding boxes
return (cnts, boundingBoxes)
###################################################################################################################################
# https://medium.com/coinmonks/a-box-detection-algorithm-for-any-image-containing-boxes-756c15d7ed26 (with a few modifications)
###################################################################################################################################
def box_extraction(img_for_box_extraction_path, cropped_dir_path):
img = cv2.imread(img_for_box_extraction_path, 0) # Read the image
(thresh, img_bin) = cv2.threshold(img, 128, 255,
cv2.THRESH_BINARY | cv2.THRESH_OTSU) # Thresholding the image
img_bin = 255-img_bin # Invert the imagecv2.imwrite("Image_bin.jpg",img_bin)
# Defining a kernel length
kernel_length = np.array(img).shape[1]//200
# A verticle kernel of (1 X kernel_length), which will detect all the verticle lines from the image.
verticle_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, kernel_length))
# A horizontal kernel of (kernel_length X 1), which will help to detect all the horizontal line from the image.
hori_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_length, 1))
# A kernel of (3 X 3) ones.
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))# Morphological operation to detect verticle lines from an image
img_temp1 = cv2.erode(img_bin, verticle_kernel, iterations=3)
verticle_lines_img = cv2.dilate(img_temp1, verticle_kernel, iterations=3)
#cv2.imwrite("verticle_lines.jpg",verticle_lines_img)# Morphological operation to detect horizontal lines from an image
img_temp2 = cv2.erode(img_bin, hori_kernel, iterations=3)
horizontal_lines_img = cv2.dilate(img_temp2, hori_kernel, iterations=3)
#cv2.imwrite("horizontal_lines.jpg",horizontal_lines_img)# Weighting parameters, this will decide the quantity of an image to be added to make a new image.
alpha = 0.5
beta = 1.0 - alpha
# This function helps to add two image with specific weight parameter to get a third image as summation of two image.
img_final_bin = cv2.addWeighted(verticle_lines_img, alpha, horizontal_lines_img, beta, 0.0)
img_final_bin = cv2.erode(~img_final_bin, kernel, iterations=2)
(thresh, img_final_bin) = cv2.threshold(img_final_bin, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)# For Debugging
# Enable this line to see verticle and horizontal lines in the image which is used to find boxes
#cv2.imwrite("img_final_bin.jpg",img_final_bin)
# Find contours for image, which will detect all the boxes
contours, hierarchy = cv2.findContours(
img_final_bin, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
# Sort all the contours by top to bottom.
(contours, boundingBoxes) = sort_contours(contours, method="top-to-bottom")
idx = 0
for c in contours:
# Returns the location and width,height for every contour
x, y, w, h = cv2.boundingRect(c)# If the box height is greater then 20, widht is >80, then only save it as a box in "cropped/" folder.
if (w > 50 and h > 20):# and w > 3*h:
idx += 1
new_img = img[y:y+h, x:x+w]
cv2.imwrite(cropped_dir_path+str(x)+'_'+str(y) + '.png', new_img)
###########################################################################################################################################################
def prepare_cropped_folder():
p=pathlib.Path('./Cropped')
if p.exists(): # Cropped folder non empty. Let's clean up
files = [x for x in p.glob('*.*') if x.is_file()]
for f in files:
f.unlink()
else:
p.mkdir()
###########################################################################################################################################################
# MAIN
###########################################################################################################################################################
prepare_cropped_folder()
# Read image from which text needs to be extracted
img = cv2.imread("dkesg.png")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Performing OTSU threshold
ret, thresh1 = cv2.threshold(gray, 0, 255, cv2.THRESH_OTSU | cv2.THRESH_BINARY_INV)
thresh1=255-thresh1
bin_y=np.zeros(thresh1.shape[0])
for x in range(0,len(bin_y)):
bin_y[x]=sum(thresh1[x,:])
bin_y=bin_y/max(bin_y)
ry=np.where(bin_y>0.995)[0]
for i in range(0,len(ry)):
cv2.line(img, (0, ry[i]), (thresh1.shape[1], ry[i]), (0, 0, 0), 1)
# We need to draw abox around the picture with a white border in order for box_detection to work
cv2.line(img,(0,0),(0,img.shape[0]-1),(255,255,255),2)
cv2.line(img,(img.shape[1]-1,0),(img.shape[1]-1,img.shape[0]-1),(255,255,255),2)
cv2.line(img,(0,0),(img.shape[1]-1,0),(255,255,255),2)
cv2.line(img,(0,img.shape[0]-1),(img.shape[1]-1,img.shape[0]-1),(255,255,255),2)
cv2.line(img,(0,0),(0,img.shape[0]-1),(0,0,0),1)
cv2.line(img,(img.shape[1]-3,0),(img.shape[1]-3,img.shape[0]-1),(0,0,0),1)
cv2.line(img,(0,0),(img.shape[1]-1,0),(0,0,0),1)
cv2.line(img,(0,img.shape[0]-2),(img.shape[1]-1,img.shape[0]-2),(0,0,0),1)
cv2.imwrite('out.png',img)
box_extraction("out.png", "./Cropped/")
Now... It puts the cropped regions in the Cropped folder. They are named as x_y.png with (x,y) the position on the original image.
Here are two examples of the outputs
and
Now, in a terminal. I used pytesseract on these two images.
The results are the following:
1)
Original Cost
$200,000.00
2)
Amount Existing Liens
$494,215.00
As you can see, pytesseract got the amount wrong in the second case... So, be careful.
Best regards,
Stéphane
I assume the bounding box is fix (rectangle that able to fit in "Original Amount and the amount below). You can use text detection to detect the "Original Amount" and "Amount Existing Liens" using OCR and crop out the image based on the detected location for further OCR on the amount. You can refer this link for text detection
Try to divide the image into different cells using the lines in the image.
For example, first divide the input into rows by detecting the horizontal lines. This can be done by using cv.HoughLinesP and checking for each line if the difference between y-coordinate of the begin and end point is smaller than a certain threshold abs(y2 - y1) < 10. If you have a horizontal line, it's a separator for a new row. You can use the y-coordinates of this line to split the input horizontally.
Next, for the row you're interested in, divide the region into columns using the same technique, but now make sure the difference between the x-coordinates of the begin and end point are smaller than a certain threshold, since you're now looking for the vertical lines.
You can now crop the image to different cells using the y-coordinates of the horizontal lines and the x-coordinates of the vertical lines. Pass these cropped regions one by one to the OCR engine and you'll have for each cell the corresponding text.
I want to be able to detect a certain area of pixels based on their RGB values and change them to some other color (not black/white).
I have tried changing these values in the code, but my resulting images always show black pixels replacing the specified locations:
pixelMap[i,j]= (255,255,255)
from PIL import Image
im = Image.open('Bird.jpg')
pixelMap = im.load()
img = Image.new(im.mode, im.size)
pixelsNew = img.load()
for i in range(img.size[0]):
for j in range(img.size[1]):
toup = pixelMap[i,j]
if(int(toup[0]>175) and int(toup[1]<100 and int(toup[2])<100) ):
pixelMap[i,j]= (255,255,255)
else:
pixelsNew[i,j] = pixelMap[i,j]
img.show()
You will find that iterating over images with Python loops is really slow and should get in the habit of using Numpy or optimised OpenCV or skimage code.
So, starting with this image:
from PIL import Image
import numpy as np
# Open image
im = Image.open('bird.jpg')
# Make into Numpy array
imnp = np.array(im)
# Make all reddish pixels white
imnp[(imnp[:,:,0]>170) & (imnp[:,:,1]<100) & (imnp[:,:,2]<100)] = [255,255,255]
# Convert back to PIL and save
Image.fromarray(imnp).save('result.jpg')
It looks like a tiny bug:
Instead of: pixelMap[i,j]= (255,255,255)
Use: pixelsNew[i,j] = (255,255,255)
I have to extract this:
from the given image:
I tried contour detection but that gives all the contours. But I specifically need that object in that image.
My idea is to:
Find the objects in the image
Draw bounding box around them
Crop them and save them individually.
I am working with opencv and using python3, which I am fairly new to.
As seen there are three objects similar to given template but of different sizes. Also there are other boxes which are not the area of interest. After cropping I want to save them as three separate images. Is there a solution to this situation ?
I tried multi-scale template matching with the cropped template.
Here is an attempt:
# import the necessary packages
import numpy as np
import argparse
import imutils
import glob
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-t", "--template", required=True, help="Path to template image")
args = vars(ap.parse_args())
# load the image image, convert it to grayscale, and detect edges
template = cv2.imread(args["template"])
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
(tH, tW) = template.shape[:2]
image = cv2.imread('input.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# loop over the scales of the image
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
# resize the image according to the scale, and keep track
# of the ratio of the resizing
resized = imutils.resize(gray, width = int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
# if the resized image is smaller than the template, then break
# from the loop
if resized.shape[0] < tH or resized.shape[1] < tW:
break
# detect edges in the resized, grayscale image and apply template
# matching to find the template in the image
edged = cv2.Canny(resized, 50, 200)
res = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
loc = np.where( res >= 0.95)
for pt in zip(*loc[::-1]):
cv2.rectangle(image, int(pt*r), (int((pt[0] + tW)*r), int((pt[1] + tH)*r)), (0,255,0), 2)
cv2.imwrite('re.png',image)
Result that I am getting:
Expected result is bounding boxes around all the post-it boxes
I'm currently on mobile so I can't really write code, but this link does exactly what you're looking for!
If anything isn't clear I can adapt the code to your example later this evening, when I have acces to a laptop.
In your case I would crop out the content of the shape (the post-it) and template match just on the edges. That'll make sure it's not thrown off by the text inside.
Good luck!