CODEWITHSUNDEEP
python-3.xmatplotlibpython-imaging-libraryscikit-imagesuperpixels
eric lardon
eric lardon

Reputation: 359

Reconstruct and display an image from its superpixels representation

I would like to reconstruct and display an image from its superpixel representation.

Let's illustrate it with a simple example :

l have a (224,224,3) image. I apply on it superpixel SLIC algorithm to get superpixels.

Here is my code :

from PIL import Image
import numpy as np
import matplotlib.pyplot as plt


def sp_idx(s, index=True):
    u = np.unique(s)
    return [np.where(s == i) for i in u]

    image_index=[] # store the index of pixels affected to each superpixel
    image_superpixels=[] # store the RGB pixel values of the pixels of all superpixels
    img = skimageIO.imread(image_1)
    segments_slic = slic(img, n_segments=1000, compactness=0.01, sigma=1)
    superpixel_list = sp_idx(segments_slic)# get pixel and superpixel index
    image_index.append(superpixel_list)
    superpixel = [img[idx] for idx in superpixel_list]
    superpixel = np.asarray(superpixel)
    image_superpixels.append(superpixel)

Now given the superpixels of the image :

How can display the image in superpixel format ?

l would like to get something like the following :

`plt.imshow(image_1)` and `plt.imshow(image_superpixels)`

display the same thing (at least visually comparable)

Upvotes: 0

Views: 235

Answers (0)

Related Questions