Code for How to Use K-Means Clustering for Image Segmentation using OpenCV in Python

You can also view the full code on github.

kmeans_segmentation.py

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

# read the image
image = cv2.imread(sys.argv[1])

# convert to RGB
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

# reshape the image to a 2D array of pixels and 3 color values (RGB)
pixel_values = image.reshape((-1, 3))
# convert to float
pixel_values = np.float32(pixel_values)

# define stopping criteria
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 100, 0.2)

# number of clusters (K)
k = 3
compactness, labels, (centers) = cv2.kmeans(pixel_values, k, None, criteria, 10, cv2.KMEANS_RANDOM_CENTERS)

# convert back to 8 bit values
centers = np.uint8(centers)

# flatten the labels array
labels = labels.flatten()

# convert all pixels to the color of the centroids
segmented_image = centers[labels]

# reshape back to the original image dimension
segmented_image = segmented_image.reshape(image.shape)

# show the image
plt.imshow(segmented_image)
plt.show()

# disable only the cluster number 2 (turn the pixel into black)
masked_image = np.copy(image)
# convert to the shape of a vector of pixel values
masked_image = masked_image.reshape((-1, 3))
# color (i.e cluster) to disable
cluster = 2
masked_image[labels == cluster] = [0, 0, 0]

# convert back to original shape
masked_image = masked_image.reshape(image.shape)
# show the image
plt.imshow(masked_image)
plt.show()

live_kmeans_segmentation.py (using live cam)

import cv2
import numpy as np

cap = cv2.VideoCapture(0)
k = 5

# define stopping criteria
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 100, 0.2)

while True:
    # read the image
    _, image = cap.read()

    # reshape the image to a 2D array of pixels and 3 color values (RGB)
    pixel_values = image.reshape((-1, 3))
    # convert to float
    pixel_values = np.float32(pixel_values)

    # number of clusters (K)
    _, labels, (centers) = cv2.kmeans(pixel_values, k, None, criteria, 10, cv2.KMEANS_RANDOM_CENTERS)

    # convert back to 8 bit values
    centers = np.uint8(centers)

    # convert all pixels to the color of the centroids
    segmented_image = centers[labels.flatten()]

    # reshape back to the original image dimension
    segmented_image = segmented_image.reshape(image.shape)

    # reshape labels too
    labels = labels.reshape(image.shape[0], image.shape[1])

    cv2.imshow("segmented_image", segmented_image)
    # visualize each segment

    if cv2.waitKey(1) == ord("q"):
        break

cap.release()
cv2.destroyAllWindows()