Help finding contours in grid image!

Python
1

I have this dilated mask and I’m trying to find a contour of the largest central square block.

mask
mask512×409 8.96 KB

here is the code I have, the issue is that it doesn’t return a region that fits the criteria and the contours that it does find are the smaller squares in the grid:

contours, _ = cv2.findContours(dilated_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    
    for i, contour in enumerate(contours):
        area = cv2.contourArea(contour)
        print(f"Contour {i + 1}: Area = {area}")
    
    # Loop through contours to find the central frame
    for contour in contours:
        # Approximate the contour to a polygon
        epsilon = 0.05 * cv2.arcLength(contour, True)
        approx = cv2.approxPolyDP(contour, epsilon, True)

        # Check if the polygon has 4 vertices (rectangle)
        if len(approx) == 4:
            x, y, w, h = cv2.boundingRect(approx)
            
            # Aspect ratio check
            aspect_ratio = w / float(h)
            if 0.8 < aspect_ratio < 1.2:  # Roughly square
            
                # **Size Constraints**
                if 100 < w < 1000 and 100 < h < 1000:  # Adjust these bounds
                    print(f"Detected frame with width={w}, height={h}")
                    
                    # Extract the region of interest
                    region = barnacles[y:y+h, x:x+w]
                    
                    # Display the region
                    region_rgb = cv2.cvtColor(region, cv2.COLOR_BGR2RGB)
                    plt.imshow(region_rgb)
                    plt.title("Cropped Frame")
                    plt.axis("off")
                    plt.show()
                    
                    return region
2

source image please.

what do you think, why does the code reject the big square?