A fun little variation on Perlin noise (with Python code)

[Michael Lee]

I was experimenting with Perlin-like (I call it Perloid) noise when I realized I could threshold a little bit harder than usual.

The first few images are "regular" sort of Perlin-like, but as you get 5-9, the thresholding is increase for each color channel and resolution channel. It ends producing almost natural-like features. It is it ITC, mathematics in action, or both?

Code: 

#---------------------------------
# Original author: Michael S. Lee
# Date: 8/27/2021
#---------------------------------

import numpy as np
import matplotlib.pyplot as plt
import cv2

N = 1024 # Image size
noise = np.random.rand(N,N,3) # White noise in RGB channels
noise2 = np.copy(noise) # setup output array

image = noise2
blur = np.copy(image)
sum1 = np.zeros_like(image)

for j,i in enumerate([512,256,128,64,32,16,8,4,2]):

   image = cv2.resize(noise2,(i,i),interpolation=cv2.INTER_LANCZOS4)
   blur2 = blur
   blur = cv2.resize(image,(N,N))
   diff = blur - blur2
   min1 = diff.mean() - 1.0*diff.std()
   max1 = diff.mean() + 1.0*diff.std()
   diff = np.clip((diff - min1)/(max1-min1),0,1)
   sum1 = sum1 + (j+1)*diff

min1 = sum1.mean() - 2.0*sum1.std()
max1 = sum1.mean() + 2.0*sum1.std()

sum1 = np.clip((sum1 - min1) / (max1-min1),0,1)
plt.imshow(sum1)

plt.show()

 

[Michael Lee]

a few more pictures

 

[Andres Ramos]

Wow! At least you found a way to create impressionist art with a mouseclick. Relly fascinating!. Picture 7 in your first posting is my favorite one, there are clearl shapes showing up -a bit like cubism. But also the last two images are wonderful! I saw similar patterns in reflections in water from trees with leafs in summer.

Could you explain your program in more detail please, specially what parameter defines the threshold?

[Michael Lee]

In my new version below, thresholding is controlled by "gamma" within the "shrink" function.

Mandatory face pictures  Same person with circular black sunglasses?

Code version 2 (for record keeping, and others to experiment with):

#---------------------------------
# Original author: Michael S. Lee
# Date: 8/27/2021
#---------------------------------

import numpy as np
import imageio
import cv2

def shrink(x, gamma = 30):
    beta = gamma / (x.std())
    y = 1.0 / (1.0 + np.exp(-beta*(x-x.mean())))
    return(y)
    
N = 1024 # Image size
noise = np.random.rand(N,N,3) # White noise in RGB channels
noise2 = np.copy(noise) # setup output array

image = noise2
blur = np.copy(image)
sum1 = np.zeros_like(image)
thresh = 0.375#375
for j,i in enumerate([512,256,128,64,32,16,8,4]):

   image = cv2.resize(noise2,(i,i),interpolation=cv2.INTER_LANCZOS4)
   blur2 = blur
   blur = cv2.resize(image,(N,N))
   
   diff = blur - blur2
   diff = shrink(diff, gamma = 10)
   sum1 = sum1 + (j+1)*(j+1)*diff
   #sum1 = sum1 + (j+1)*diff
   
min1 = sum1.mean() - 2*sum1.std()
max1 = sum1.mean() + 2*sum1.std()

sum1 = shrink(sum1, gamma=1) 

# Save on disk
index = np.random.randint(0,262144) # Random filename
imageio.imsave('temp.'+str(index)+'.png',sum1)

 

[Michael Lee]

I added a little bit of darkening in my algorithm to make it a little more like itc-station's Perlin images.

Also, I used my microphone to generate 20 seconds of ambient noise and reshape it into a 1024x1024x3 image.

This is the 3rd attempt using ambient noise (192 kHz for 20 seconds):

96 kHz for 40s:

[Andres Ramos]

Wow this is so cool Michael! You are really creating art out of sound. This is just beautiful and reminds me of hereafter descriptions I read from!

I identified a small face in your previous picture.

[Karyn]

Neat!  You have a new art form that pretty well shows the world in chaos.

 

 

[Andres Ramos]

17 minutes ago, Michael Lee said:

I added a little bit of darkening in my algorithm to make it a little more like itc-station's Perlin images.

Also, I used my microphone to generate 20 seconds of ambient noise and reshape it into a 1024x1024x3 image.

This is the 3rd attempt using ambient noise (192 kHz for 20 seconds):

96 kHz for 40s:

Your last picture is just amazing! It is somehow organic like plants or weed.

[Andres Ramos]

This looks like the outline of a being interwoven with the organic structure. You can see the head, hair and outlines of a right arm. From watching this I get the impression of the "green man", a mythological creature still known in the Irish culture, a humanoid being that is a plant.

 

[Andres Ramos]

And the holy grail is also there

So theoretically, following the Arthurian legend, this could be the image of the Fisher King Anforthas.

[Michael Lee]

If you load in a WAV file of ambient noise at say 192 KHz for about 20 seconds, this will be approximately 3 million samples. Then reshape the array to be a 1024x1024x3 image using numpy.reshape()