Skip to content
TheChatArchiveThe Chat Archive
gpt-3.5-turbo-0613· OpenAIAi2 WildChat-4.8M (AI2)

i have an image with different geometrical figures with different colors on white…

  1. User

    i have an image with different geometrical figures with different colors on white background. write a python script that extracts those objects based on color and saves them as different images

  2. Assistant

    Sure! Here's a Python script that extracts objects based on color from an image and saves them as separate images.

    import cv2
    import numpy as np
    
    def extract_objects(image_path):
        # Load the image
        image = cv2.imread(image_path)
        
        # Convert the image to HSV color space
        hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
        
        # Define color ranges for different objects
        color_ranges = {
            'red': ([0, 50, 50], [10, 255, 255]),
            'green': ([50, 50, 50], [70, 255, 255]),
            'blue': ([110, 50, 50], [130, 255, 255]),
        }
        
        # Extract objects based on color
        for color, (lower, upper) in color_ranges.items():
            lower = np.array(lower, dtype=np.uint8)
            upper = np.array(upper, dtype=np.uint8)
            
            mask = cv2.inRange(hsv, lower, upper)
            contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
            
            # Save extracted objects as separate images
            for i, contour in enumerate(contours):
                x, y, w, h = cv2.boundingRect(contour)
                object_image = image[y:y+h, x:x+w]
                cv2.imwrite(f'{color}_object_{i+1}.png', object_image)
    
        print('Objects extracted and saved as separate images.')
    
    # Provide the path to the image
    image_path = 'path_to_your_image.png'
    
    # Call the function to extract objects based on color
    extract_objects(image_path)
    

    Make sure to replace 'path_to_your_image.png' with the actual path to your image file. The script extracts three different colors, red, green, and blue, by specifying their respective color ranges in the color_ranges dictionary.

    When you run the script, it will extract objects of each color, save them as separate images with appropriate names (color_object_{number}.png), and print a message indicating that the objects have been extracted and saved.