konsepkoding opencv

opencv.py

import cv2
import numpy as np
import requests
from urllib.request import urlopen
from io import BytesIO
from IPython.display import Image, display

# Function to detect dominant colors in an image
def detect_colors(image_url, num_colors=5):
    # Download the image from the URL
    response = urlopen(image_url)
    image_data = BytesIO(response.read())
    image = cv2.imdecode(np.asarray(bytearray(image_data.read()), dtype=np.uint8), -1)

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

    # Reshape the image to a list of pixels
    pixels = image_rgb.reshape((-1, 3))

    # Perform k-means clustering to find dominant colors
    k = num_colors
    criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 200, 0.2)
    _, labels, centers = cv2.kmeans(pixels.astype(np.float32), k, None, criteria, 10, cv2.KMEANS_RANDOM_CENTERS)

    # Convert the color centers to uint8
    centers = np.uint8(centers)

    # Sort the colors by frequency
    unique_labels, counts = np.unique(labels, return_counts=True)
    color_counts = list(zip(unique_labels, counts, centers))
    color_counts.sort(key=lambda x: x[1], reverse=True)

    # Extract the dominant colors
    dominant_colors = [tuple(color[2]) for color in color_counts]

    return dominant_colors

# Input image URL
image_url = input("Enter the image URL: ")

# Detect dominant colors
num_colors = 5  # You can adjust this number as needed
dominant_colors = detect_colors(image_url, num_colors)

# Display the dominant colors
print("Dominant Colors:")
for i, color in enumerate(dominant_colors, start=1):
    print(f"Color {i}: RGB {color}")

# Display the image
display(Image(url=image_url))