Large contour not found in binary image

Python
,
1

I have a binary image (binary_image_full_sizes.png) and I would like to find the large oval contour in the middle. The cv2.findContours() function does not return the contour I’m looking for but when I scale the image by 1/2, it finds the contour. How can I make it find the contour for the full size image?

    inverted_binary_image = cv2.imread('binary_image_full_scale.png')

    white_pixels = np.sum(inverted_binary_image == 255)

    # # Find Canny edges 
    edged = cv2.Canny(inverted_binary_image, 30, 200) 
    
    # Finding Contours 
    # Use a copy of the image e.g. edged.copy() 
    # since findContours alters the image 
    contours, _ = cv2.findContours(edged, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) 

    min_area = white_pixels / 10

    filtered_contours = [cnt for cnt in contours if cv2.contourArea(cnt) > min_area]

    # Convert inverted_binary_image to a color image
    inverted_binary_image = cv2.cvtColor(inverted_binary_image, cv2.COLOR_GRAY2BGR)

    cv2.drawContours(inverted_binary_image, filtered_contours, 0, (0, 255, 0), 3)

    # Save the image with drawn contours
    contour_image_path = 'binary_image_with_countours_half_scaled.png'
    cv2.imwrite(contour_image_path, inverted_binary_image)

binary_image_full_sizes
binary_image_full_sizes2448×2048 17.2 KB

2

print(inverted_binary_image.shape) for both input files

see also:

https://stackoverflow.com/staging-ground/79084102

3

fullscale_image.shape: (2048, 2448, 3)
half_scale_image.shape: (1024, 1224, 3)

4

keep debugging. compare the canny images.