I have pictures containing ArUco markers but I am unable to detect all of them with the detectMarkers function. Actually, I have many pictures : in some of them I can detect all the markers, in others I cannot and I don't really understand why.
I thought it was because of the quality of the photo, but it seems to be not so simple. Here's an example of my code :
import cv2
import matplotlib.pyplot as plt
from cv2 import aruco
aruco_dict = aruco.Dictionary_get(aruco.DICT_4X4_1000)
inputfile = 'EOS-1D-X-Mark-II_1201-ConvertImage.jpg'
frame = cv2.imread(inputfile)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
parameters = aruco.DetectorParameters_create()
corners, ids, rejectedImgPoints = aruco.detectMarkers(frame, aruco_dict, parameters=parameters)
frame_markers = aruco.drawDetectedMarkers(frame.copy(),rejectedImgPoints)
plt.figure(figsize=(20,10))
plt.imshow(frame_markers)
for i in range(len(ids)):
c = corners[i][0]
plt.plot([c[:, 0].mean()], [c[:, 1].mean()], "o", label = "id={0}".format(ids[i]))
plt.legend()
plt.show()
In this picture, 1 marker is not detected and I don't understand why.
I tried to tune the parameters of detectMarkers function manually with an interactive method thanks to jupyter notebook. There are many parameters and I found nothing that really helped me, except in some photos the reduction of polygonalApproxAccuracyRate.
The photo is orginally in 5472 x 3648 pixels but the one I send in this post is 2189 x 1459 pixels. Note that it doesn't work with the better resolution neither. Actually, I found in some photos that reducing the resolution help to detect the markers ... It's a contradiction but I think this is because the default parameters of the function are not adapted to my pictures, but I found no solution when tuning the parameters.
Another idea is to use the refineDetectMarkers function after calling detectMarkers. It uses the candidates that were found in detectMarkers but failed to be identified, and try to refine their identification. However, as far as I understood, I need to know where my markers should be in the picture and put it in refineDetectMarkers (as a board). In my situation, I don't know where the markers should be, otherwise I wouldn't take photos. The photos are used to observe precisely the evolution of their positions.
I am interested in any ideas you may have, thanks for reading !
Related
I'm currently trying to perform a Polar to Cartesian Coordinate Image transformation, to display a raw sonar image into a 'fan-display'.
Initially I have a Numpy Array image of type np.float64, that can be seen below:
After doing some searching, I came across this StackOverflow post Inverse transform an image from Polar to Cartesian in OpenCV with a very similar problem, in which the poster seemed to have solved his/her issue by using the Python Wand library (http://docs.wand-py.org/en/0.5.9/index.html), specifically using their set of Distortion functions.
However, when I tried to use Wand and read the image in, I instead ended up with Wand getting the image below, which seems to be smaller than the original one. However, the weird thing is that img.size still gives the same size number as the original image's shape.
The code for this transformation can be seen below:
print(raw_img.shape)
wand_img = Image.from_array(raw_img.astype(np.uint8), channel_map="I") #=> (369, 256)
display(wand_img)
print("Current image size", wand_img.size) #=> "Current image size (369, 256)"
This is definitely quite problematic as Wand will automatically give the wrong 'fan image'. Is anybody familiar with this kind of problem with the Wand library previously, and if yes, may I ask what is the recommended solution to fix this issue?
If this issue isn't resolved soon I have an alternative backup of using OpenCV's cv::remap function (https://docs.opencv.org/4.1.2/da/d54/group__imgproc__transform.html#ga5bb5a1fea74ea38e1a5445ca803ff121). However the problem with this is that I'm not sure what mapping arrays (i.e. map_x and map_y) to use to perform the Polar->Cartesian transformation, as using a mapping matrix that implements the transformation equations below:
r = polar_distances(raw_img)
x = r * cos(theta)
y = r * sin(theta)
didn't seem to work and instead threw out errors from OpenCV as well.
Any kind of help and insight into this issue is greatly appreciated. Thank you!
- NickS
EDIT I've tried on another image example as well, and it still shows a similar problem. So first, I imported the image into Python using OpenCV, using these lines of code:
import matplotlib.pyplot as plt
from wand.image import Image
from wand.display import display
import cv2
img = cv2.imread("Test_Img.jpg")
img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
plt.figure()
plt.imshow(img_rgb)
plt.show()
which showed the following display as a result:
However, as I continued and tried to open the img_rgb object with Wand, using the code below:
wand_img = Image.from_array(img_rgb)
display(img_rgb)
I'm getting the following result instead.
I tried to open the image using wand.image.Image() on the file directly, which is able to display the image correctly when using display() function, so I believe that there isn't anything wrong with the wand library installation on the system.
Is there a missing step that I required to convert the numpy into Wand Image that I'm missing? If so, what would it be and what is the suggested method to do so?
Please do keep in mind that I'm stressing the conversion of Numpy to Wand Image quite crucial, the raw sonar images are stored as binary data, thus the required use of Numpy to convert them to proper images.
Is there a missing step that I required to convert the numpy into Wand Image that I'm missing?
No, but there is a bug in Wand's Numpy implementation in Wand 0.5.x. The shape of OpenCV's ndarray is (ROWS, COLUMNS, CHANNELS), but Wand's ndarray is (WIDTH, HEIGHT, CHANNELS). I believe this has been fixed for the future 0.6.x releases.
If so, what would it be and what is the suggested method to do so?
Swap the values in img_rgb.shape before passing to Wand.
img_rgb.shape = (img_rgb.shape[1], img_rgb.shape[0], img_rgb.shape[2],)
with Image.from_array(img_rgb) as img:
display(img)
I recently ran across the PhotUtils package and am trying to use it to perform PSF Photometry on some images I have. However, when I try to run the code, I get very strange results. When I plot the image generated by get_residual_image(), the stars are not removed well. Some sample images are shown below.
The first image has sigma set to 2.05, as it is in one of the sample programs in the PhotUtils documentation:
However, the stars only appear to be removed in their center.
The second image has sigma set to 5.0. This one is especially strange. Some stars are way over-removed, some are under removed, some black squares are added to the image, etc.
Here is my code:
import photutils
from photutils.psf import DAOPhotPSFPhotometry as DAOP
from photutils.psf import IntegratedGaussianPRF as PRF
from photutils.background import MMMBackground
bkg = MMMBackground()
background = 2.5*bkg(img)
gaussian_prf = PRF(sigma=5.0)
gaussian_prf.sigma.fixed = False
photTester = DAOP(8,background,5,gaussian_prf,31)
photResults = photTester(imgStars)
finalImg = photTester.get_residual_image()
After this, I simply plot the original and final image in MatPlotLib. I use a greyscale colormap. The reason that the left images appear slightly darker is that they use a different color scaling.
Perhaps I have set one of the parameters incorrectly?
Could someone help me out with this? Thank you!
Looking at the residual image instantly told me that the background subtraction might be wrong. I could reproduce the result and wondered, if MMMBackground did not do the job correctly.
After taking a closer look at the documentation, Getting startet with Photutils finally gave the essential hint:
image -= np.median(image)
I have an image where I want to detect aruco markers DICT_4X4_50. However, the image resolution seems to present itself as a major problem. But it is rather strange, since aruco detection function is able to detect markers on much difficult images, but not this one. Is there any way to detect them?
I already tried changing some parameter values of detector parameters, but it didn't help, and modifying values randomly does not seem to be the best option at all. This is the image:
This was my basic code:
import cv2
from cv2 import aruco
img = cv2.imread('image.png')
aruco_dict = aruco.Dictionary_get(aruco.DICT_4X4_50)
parameters = aruco.DetectorParameters_create()
# Detect the markers.
corners, ids, rejectedImgPoints = aruco.detectMarkers(img,aruco_dict,parameters=parameters)
out = aruco.drawDetectedMarkers(img, corners, ids)
cv2.imshow("out",out)
cv2.waitKey(0)
cv2.destroyAllWindows()
Thank you!
In you code you have not defined the detect markers code
cv2.detectMarkers()
Found the problem. Symbols are vertically rotated. If the image is flipped, it will be fine. :P No wonder Aruco could not solve that.
Indeed, this question has been answered many times. However, as I am not allowed to add a comment to an answer due to "too low" reputation, I would like to discuss the solution presented in the most comprehensive answer.
Wouldn't the solution:
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt #Used in the comparison below
im = Image.open('file.png').convert('RGB') #Opens a picture in grayscale
pic = np.array(im)
im.close()
work properly? I am wondering whether unacceptable changes in the quality occur. I have noticed some differences (i.e. black rows at the top in plt.imshow()) when I display the image:
im.show() #Before closing
plt.imshow(pic)
but I don't know whether they are only inevitable consequences of converting to np.array.
PS - If it is important, I would mention that I prepare the image for color quantization (KMeans) and Floyd dithering.
PPS - If you advised me how not to post duplicate question but discuss answers directly - it would be really appreciated.
Try it and see!
from PIL import Image
import numpy as np
# Other answer method
im1 = Image.open('gray.png').convert('L')
im1 = np.stack((im1,)*3, axis=-1)
# Your method
im2 = Image.open('gray.png').convert('RGB')
im2 = np.array(im2)
# Test if identical
print(np.array_equal(im1,im2))
Sample Output
True
I would say the one aspect that is different, is that the method in the other answer will work (insofar as it actually makes a greyscale image where R=G=B) even if the input image is colour, whereas your method will produce a colour image.
I was working on doing a similar thing, and I'm not sure why but I ran into a bunch of issues. In the end this worked for me pretty well without loss of any data.
from PIL import Image
import numpy as np
img=np.array(Image.open(filename).convert('L'))
and to convert back:
import imageio
array = array.astype(np.uint8)
imageio.imwrite(newfilename, array)
edit: this only works for black and white images. Color images need 3D arrays rather than 2D arrays
The goal is to identify that the input scanned image is passport or PAN card using Opencv.
I have used structural_similarity(compare_ssim) method of skimage to compare input scan image with the images of template of Passport and PAN card.
But in both cases i got low score.
Here is the code that i have tried
from skimage.measure import compare_ssim as ssim
import matplotlib.pyplot as plt
import numpy as np
import cv2enter code here
img1 = cv2.imread('PAN_Template.jpg', 0)
img2 = cv2.imread('PAN_Sample1.jpg', 0)
def prepare_img(im):
size = 300, 200
im = cv2.resize(im, size)
return im
img1 = prepare_img(img1)
img2 = prepare_img(img2)
def compare_images(imageA, imageB):
s = ssim(imageA, imageB)
return s
ssim = compare_images(img1, img2)
print(ssim)
Comparing the PAN Card Template with Passport i have got ssim score of 0.12
and Comparing the PAN Card template with a PAN Card the score was 0.20
Since both the score were very close i wast not able to distinguish between them through the code.
If anyone got any other solution or approach then please help.
Here is a sample image
PAN Scanned Image
You can also compare 2 images by the mean square error (MSE) of those 2 images.
def mse(imageA, imageB):
# the 'Mean Squared Error' between the two images is the
# sum of the squared difference between the two images;
# NOTE: the two images must have the same dimension
err = np.sum((imageA.astype("float") - imageB.astype("float")) ** 2)
err /= float(imageA.shape[0] * imageA.shape[1])
# return the MSE, the lower the error, the more "similar"
# the two images are
return err
As per my understanding Pan card and Passport images contain different text data, so i believe OCR can solve this problem.
All you need to do is- extract the text data from the images using any OCR library like Tesseract and look for a few predefined key words in the text data to differentiate the images.
Here is simple Python script showing the image pre-processing and OCR using pyteseract module:
img = cv2.imread("D:/pan.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,th1 = cv2.threshold(gray,127,255,cv2.THRESH_BINARY)
cv2.imwrite('filterImg.png', th1)
pilImg = Image.open('filterimg.png')
text = pytesseract.image_to_string(pilImg)
print(text.encode("utf-8"))
Below is the binary image used for OCR:
I got the below string data after doing the OCR on the above image:
esraax fram EP aca ae
~ INCOME TAX DEPARTMENT Ld GOVT. OF INDIA
wrtterterad sg
Permanent Account Number. Card \xe2\x80\x98yf
KFWPS6061C
PEF vom ; ae
Reviavs /Father's Name. e.
SUDHIR SINGH : . ,
Though this text data contains noises but i believe it is more than enough to get the job done.
Another OCR solution is to use TextCleaner ImageMagick script from Fred's Scripts. A tutorial which explain how to install and use it (on Windows) is available here.
Script used:
C:/cygwin64/bin/textcleaner -g -e normalize -f 20 -o 20 -s 20 C:/Users/Link/Desktop/id.png C:/Users/Link/Desktop/out.png
Result:
I applied OCR on this with Tesseract (I am using version 4) and that's the result:
fart
INCOME TAX DEPARTMENT : GOVT. OF INDIA
wort cra teat ears -
Permanent Account Number Card
KFWPS6061C
TT aa
MAYANK SUDHIR SINGH el
far aT ary /Father's Name
SUDHIR SINGH
Wa RT /Date of Birth den. +
06/01/1997 genge / Signature
Code for OCR:
import cv2
from PIL import Image
import tesserocr as tr
number_ok = cv2.imread("C:\\Users\\Link\\Desktop\\id.png")
blur = cv2.medianBlur(number_ok, 1)
cv2.imshow('ocr', blur)
pil_img = Image.fromarray(cv2.cvtColor(blur, cv2.COLOR_BGR2RGB))
api = tr.PyTessBaseAPI()
try:
api.SetImage(pil_img)
boxes = api.GetComponentImages(tr.RIL.TEXTLINE, True)
text = api.GetUTF8Text()
finally:
api.End()
print(text)
cv2.waitKey(0)
Now, this don't answer at your question (passport or PAN card) but it's a good point where you can start.
Doing OCR might be a solution for this type of image classification but it might fail for the blurry or not properly exposed images. And it might be slower than newer deep learning methods.
You can use Object detection (Tensorflow or any other library) to train two separate class of image i.e PAN and Passport. For fine-tuning pre-trained models, you don't need much data too. And as per my understanding, PAN and passport have different background color so I guess it will be really accurate.
Tensorflow Object Detection: Link
Nowadays OpenCV also supports object detection without installing any new libraries(i.e.Tensorflow, caffee, etc.). You can refer this article for YOLO based object detection in OpenCV.
We can use:
Histogram Comparison - Simplest & fastest methods, using this we will get the similarity between histograms.
Template Matching - Searching and finding the location of a template image, using this we can find smaller image parts in a bigger one. (like some common patterns in PAN card).
Feature Matching - Features extracted from one image and the same feature will be recognised in another image even if the image rotated or skewed.