app.py

from __future__ import annotations
import os
import gc
import base64
import io
import time
import shutil
import numpy as np
import torch
import cv2
import ezdxf
import gradio as gr
from PIL import Image, ImageEnhance
from pathlib import Path
from typing import List, Union
from ultralytics import YOLOWorld, YOLO
from ultralytics.engine.results import Results
from ultralytics.utils.plotting import save_one_box
from transformers import AutoModelForImageSegmentation
from torchvision import transforms
from scalingtestupdated import calculate_scaling_factor
from shapely.geometry import Polygon, Point, MultiPolygon
from scipy.interpolate import splprep, splev
from scipy.ndimage import gaussian_filter1d
from u2net import U2NETP

# ---------------------
# Create a cache folder for models
# ---------------------
CACHE_DIR = os.path.join(os.path.dirname(__file__), ".cache")
os.makedirs(CACHE_DIR, exist_ok=True)

# ---------------------
# Custom Exceptions
# ---------------------
class DrawerNotDetectedError(Exception):
    """Raised when the drawer cannot be detected in the image"""
    pass

class ReferenceBoxNotDetectedError(Exception):
    """Raised when the reference box cannot be detected in the image"""
    pass

class BoundaryExceedsError(Exception):
    """Raised when the optional boundary dimensions exceed allowed image dimensions."""
    pass

class BoundaryOverlapError(Exception):
    """Raised when the optional boundary dimensions are too small and overlap with the inner contours."""
    pass

# ---------------------
# Global Model Initialization with caching and print statements
# ---------------------
print("Loading YOLOWorld model...")
start_time = time.time()
yolo_model_path = os.path.join(CACHE_DIR, "yolov8x-worldv2.pt")
if not os.path.exists(yolo_model_path):
    print("Caching YOLOWorld model to", yolo_model_path)
    shutil.copy("yolov8x-worldv2.pt", yolo_model_path)
drawer_detector_global = YOLOWorld(yolo_model_path)
drawer_detector_global.set_classes(["box"])
print("YOLOWorld model loaded in {:.2f} seconds".format(time.time() - start_time))

print("Loading YOLO reference model...")
start_time = time.time()
reference_model_path = os.path.join(CACHE_DIR, "last.pt")
if not os.path.exists(reference_model_path):
    print("Caching YOLO reference model to", reference_model_path)
    shutil.copy("last.pt", reference_model_path)
reference_detector_global = YOLO(reference_model_path)
print("YOLO reference model loaded in {:.2f} seconds".format(time.time() - start_time))

print("Loading U²-Net model for reference background removal (U2NETP)...")
start_time = time.time()
u2net_model_path = os.path.join(CACHE_DIR, "u2netp.pth")
if not os.path.exists(u2net_model_path):
    print("Caching U²-Net model to", u2net_model_path)
    shutil.copy("u2netp.pth", u2net_model_path)
u2net_global = U2NETP(3, 1)
u2net_global.load_state_dict(torch.load(u2net_model_path, map_location="cpu"))
device = "cpu"
u2net_global.to(device)
u2net_global.eval()
print("U²-Net model loaded in {:.2f} seconds".format(time.time() - start_time))

print("Loading BiRefNet model...")
start_time = time.time()
birefnet_global = AutoModelForImageSegmentation.from_pretrained(
    "zhengpeng7/BiRefNet", trust_remote_code=True, cache_dir=CACHE_DIR
)
torch.set_float32_matmul_precision("high")
birefnet_global.to(device)
birefnet_global.eval()
print("BiRefNet model loaded in {:.2f} seconds".format(time.time() - start_time))

# Define transform for BiRefNet
transform_image_global = transforms.Compose([
    transforms.Resize((1024, 1024)),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])

# ---------------------
# Model Reload Function (if needed)
# ---------------------
def unload_and_reload_models():
    global drawer_detector_global, reference_detector_global, birefnet_global, u2net_global
    print("Reloading models...")
    start_time = time.time()
    del drawer_detector_global, reference_detector_global, birefnet_global, u2net_global
    gc.collect()
    if torch.cuda.is_available():
        torch.cuda.empty_cache()
    gc.collect()
    new_drawer_detector = YOLOWorld(os.path.join(CACHE_DIR, "yolov8x-worldv2.pt"))
    new_drawer_detector.set_classes(["box"])
    new_reference_detector = YOLO(os.path.join(CACHE_DIR, "last.pt"))
    new_birefnet = AutoModelForImageSegmentation.from_pretrained(
        "zhengpeng7/BiRefNet", trust_remote_code=True, cache_dir=CACHE_DIR
    )
    new_birefnet.to(device)
    new_birefnet.eval()
    new_u2net = U2NETP(3, 1)
    new_u2net.load_state_dict(torch.load(os.path.join(CACHE_DIR, "u2netp.pth"), map_location="cpu"))
    new_u2net.to(device)
    new_u2net.eval()
    drawer_detector_global = new_drawer_detector
    reference_detector_global = new_reference_detector
    birefnet_global = new_birefnet
    u2net_global = new_u2net
    print("Models reloaded in {:.2f} seconds".format(time.time() - start_time))

# ---------------------
# Helper Function: resize_img (defined once)
# ---------------------
def resize_img(img: np.ndarray, resize_dim):
    return np.array(Image.fromarray(img).resize(resize_dim))

# ---------------------
# Other Helper Functions for Detection & Processing
# ---------------------
def yolo_detect(image: Union[str, Path, int, Image.Image, list, tuple, np.ndarray, torch.Tensor]) -> np.ndarray:
    t = time.time()
    results: List[Results] = drawer_detector_global.predict(image)
    if not results or len(results) == 0 or len(results[0].boxes) == 0:
        raise DrawerNotDetectedError("Drawer not detected in the image.")
    print("Drawer detection completed in {:.2f} seconds".format(time.time() - t))
    return save_one_box(results[0].cpu().boxes.xyxy, im=results[0].orig_img, save=False)

def detect_reference_square(img: np.ndarray):
    t = time.time()
    res = reference_detector_global.predict(img, conf=0.45)
    if not res or len(res) == 0 or len(res[0].boxes) == 0:
        raise ReferenceBoxNotDetectedError("Reference box not detected in the image.")
    print("Reference detection completed in {:.2f} seconds".format(time.time() - t))
    return (
        save_one_box(res[0].cpu().boxes.xyxy, res[0].orig_img, save=False),
        res[0].cpu().boxes.xyxy[0]
    )

# Use U2NETP for reference background removal.
def remove_bg_u2netp(image: np.ndarray) -> np.ndarray:
    t = time.time()
    image_pil = Image.fromarray(image)
    transform_u2netp = transforms.Compose([
        transforms.Resize((320, 320)),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
    ])
    input_tensor = transform_u2netp(image_pil).unsqueeze(0).to("cpu")
    with torch.no_grad():
        outputs = u2net_global(input_tensor)
    pred = outputs[0]
    pred = (pred - pred.min()) / (pred.max() - pred.min() + 1e-8)
    pred_np = pred.squeeze().cpu().numpy()
    pred_np = cv2.resize(pred_np, (image_pil.width, image_pil.height))
    pred_np = (pred_np * 255).astype(np.uint8)
    print("U2NETP background removal completed in {:.2f} seconds".format(time.time() - t))
    return pred_np

# Use BiRefNet for main object background removal.
def remove_bg(image: np.ndarray) -> np.ndarray:
    t = time.time()
    image_pil = Image.fromarray(image)
    input_images = transform_image_global(image_pil).unsqueeze(0).to("cpu")
    with torch.no_grad():
        preds = birefnet_global(input_images)[-1].sigmoid().cpu()
    pred = preds[0].squeeze()
    pred_pil = transforms.ToPILImage()(pred)
    scale_ratio = 1024 / max(image_pil.size)
    scaled_size = (int(image_pil.size[0] * scale_ratio), int(image_pil.size[1] * scale_ratio))
    result = np.array(pred_pil.resize(scaled_size))
    print("BiRefNet background removal completed in {:.2f} seconds".format(time.time() - t))
    return result

def make_square(img: np.ndarray):
    height, width = img.shape[:2]
    max_dim = max(height, width)
    pad_height = (max_dim - height) // 2
    pad_width = (max_dim - width) // 2
    pad_height_extra = max_dim - height - 2 * pad_height
    pad_width_extra = max_dim - width - 2 * pad_width
    if len(img.shape) == 3:
        padded = np.pad(img, ((pad_height, pad_height + pad_height_extra),
                              (pad_width, pad_width + pad_width_extra),
                              (0, 0)), mode="edge")
    else:
        padded = np.pad(img, ((pad_height, pad_height + pad_height_extra),
                              (pad_width, pad_width + pad_width_extra)), mode="edge")
    return padded

def shrink_bbox(image: np.ndarray, shrink_factor: float):
    height, width = image.shape[:2]
    center_x, center_y = width // 2, height // 2
    new_width = int(width * shrink_factor)
    new_height = int(height * shrink_factor)
    x1 = max(center_x - new_width // 2, 0)
    y1 = max(center_y - new_height // 2, 0)
    x2 = min(center_x + new_width // 2, width)
    y2 = min(center_y + new_width // 2, height)
    return image[y1:y2, x1:x2]

def exclude_scaling_box(image: np.ndarray, bbox: np.ndarray, orig_size: tuple, processed_size: tuple, expansion_factor: float = 1.2) -> np.ndarray:
    x_min, y_min, x_max, y_max = map(int, bbox)
    scale_x = processed_size[1] / orig_size[1]
    scale_y = processed_size[0] / orig_size[0]
    x_min = int(x_min * scale_x)
    x_max = int(x_max * scale_x)
    y_min = int(y_min * scale_y)
    y_max = int(y_max * scale_y)
    box_width = x_max - x_min
    box_height = y_max - y_min
    expanded_x_min = max(0, int(x_min - (expansion_factor - 1) * box_width / 2))
    expanded_x_max = min(image.shape[1], int(x_max + (expansion_factor - 1) * box_width / 2))
    expanded_y_min = max(0, int(y_min - (expansion_factor - 1) * box_height / 2))
    expanded_y_max = min(image.shape[0], int(y_max + (expansion_factor - 1) * box_height / 2))
    image[expanded_y_min:expanded_y_max, expanded_x_min:expanded_x_max] = 0
    return image

def resample_contour(contour):
    num_points = 1000
    smoothing_factor = 5
    spline_degree = 3
    if len(contour) < spline_degree + 1:
        raise ValueError(f"Contour must have at least {spline_degree + 1} points, but has {len(contour)} points.")
    contour = contour[:, 0, :]
    tck, _ = splprep([contour[:, 0], contour[:, 1]], s=smoothing_factor)
    u = np.linspace(0, 1, num_points)
    resampled_points = splev(u, tck)
    smoothed_x = gaussian_filter1d(resampled_points[0], sigma=1)
    smoothed_y = gaussian_filter1d(resampled_points[1], sigma=1)
    return np.array([smoothed_x, smoothed_y]).T

# ---------------------
# Add the missing extract_outlines function
# ---------------------
def extract_outlines(binary_image: np.ndarray) -> (np.ndarray, list):
    contours, _ = cv2.findContours(binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
    outline_image = np.zeros_like(binary_image)
    cv2.drawContours(outline_image, contours, -1, (255), thickness=2)
    return cv2.bitwise_not(outline_image), contours

# ---------------------
# Functions for Finger Cut Clearance
# ---------------------
def union_tool_and_circle(tool_polygon: Polygon, center_inch, circle_diameter=1.0):
    radius = circle_diameter / 2.0
    circle_poly = Point(center_inch).buffer(radius, resolution=64)
    union_poly = tool_polygon.union(circle_poly)
    return union_poly

def build_tool_polygon(points_inch):
    return Polygon(points_inch)

def polygon_to_exterior_coords(poly: Polygon):
    if poly.geom_type == "MultiPolygon":
        biggest = max(poly.geoms, key=lambda g: g.area)
        poly = biggest
    if not poly.exterior:
        return []
    return list(poly.exterior.coords)

def place_finger_cut_randomly(tool_polygon, points_inch, existing_centers, all_polygons, circle_diameter=1.0, min_gap=0.25, max_attempts=30):
    import random
    needed_center_distance = circle_diameter + min_gap
    radius = circle_diameter / 2.0
    for _ in range(max_attempts):
        idx = random.randint(0, len(points_inch) - 1)
        cx, cy = points_inch[idx]
        too_close = False
        for (ex_x, ex_y) in existing_centers:
            if np.hypot(cx - ex_x, cy - ex_y) < needed_center_distance:
                too_close = True
                break
        if too_close:
            continue
        circle_poly = Point((cx, cy)).buffer(radius, resolution=64)
        union_poly = tool_polygon.union(circle_poly)
        overlap_with_others = False
        too_close_to_others = False
        for poly in all_polygons:
            if union_poly.intersects(poly):
                overlap_with_others = True
                break
            if circle_poly.buffer(min_gap).intersects(poly):
                too_close_to_others = True
                break
        if overlap_with_others or too_close_to_others:
            continue
        existing_centers.append((cx, cy))
        return union_poly, (cx, cy)
    print("Warning: Could not place a finger cut circle meeting all spacing requirements.")
    return None, None

# ---------------------
# DXF Spline and Boundary Functions
# ---------------------
def save_dxf_spline(inflated_contours, scaling_factor, height, finger_clearance=False):
    degree = 3
    closed = True
    doc = ezdxf.new(units=0)
    doc.units = ezdxf.units.IN
    doc.header["$INSUNITS"] = ezdxf.units.IN
    msp = doc.modelspace()
    finger_cut_centers = []
    final_polygons_inch = []
    for contour in inflated_contours:
        try:
            resampled_contour = resample_contour(contour)
            points_inch = [(x * scaling_factor, (height - y) * scaling_factor) for x, y in resampled_contour]
            if len(points_inch) < 3:
                continue
            if np.linalg.norm(np.array(points_inch[0]) - np.array(points_inch[-1])) > 1e-2:
                points_inch.append(points_inch[0])
            tool_polygon = build_tool_polygon(points_inch)
            if finger_clearance:
                union_poly, center = place_finger_cut_randomly(tool_polygon, points_inch, finger_cut_centers, final_polygons_inch, circle_diameter=1.0, min_gap=0.25, max_attempts=30)
                if union_poly is not None:
                    tool_polygon = union_poly
            exterior_coords = polygon_to_exterior_coords(tool_polygon)
            if len(exterior_coords) < 3:
                continue
            msp.add_spline(exterior_coords, degree=degree, dxfattribs={"layer": "TOOLS"})
            final_polygons_inch.append(tool_polygon)
        except ValueError as e:
            print(f"Skipping contour: {e}")
    return doc, final_polygons_inch

def add_rectangular_boundary(doc, polygons_inch, boundary_length, boundary_width, offset_unit, annotation_text=""):
    msp = doc.modelspace()
    # First, if unit is mm, check if values seem too low (accidental inches) and convert them.
    if offset_unit.lower() == "mm":
        if boundary_length < 50:
            boundary_length = boundary_length * 25.4
        if boundary_width < 50:
            boundary_width = boundary_width * 25.4
        boundary_length_in = boundary_length / 25.4
        boundary_width_in = boundary_width / 25.4
    else:
        boundary_length_in = boundary_length
        boundary_width_in = boundary_width

    # Compute bounding box from inner contours.
    min_x = float("inf")
    min_y = float("inf")
    max_x = -float("inf")
    max_y = -float("inf")
    for poly in polygons_inch:
        b = poly.bounds
        min_x = min(min_x, b[0])
        min_y = min(min_y, b[1])
        max_x = max(max_x, b[2])
        max_y = max(max_y, b[3])
    if min_x == float("inf"):
        print("No tool polygons found, skipping boundary.")
        return None

    # Calculate inner bounding box dimensions.
    inner_width = max_x - min_x
    inner_length = max_y - min_y

    # Set clearance margins.
    clearance_side = 0.25    # Left and right clearance
    clearance_top = 0.25     # Top clearance
    # Bottom clearance: 0.75 if annotation text is provided; otherwise 0.25.
    clearance_bottom = 0.75 if annotation_text.strip() else 0.25

    # New check: if the provided boundary dimensions are too small relative to the inner contours, raise an error.
    if boundary_width_in <= inner_width + 2 * clearance_side or \
       boundary_length_in <= inner_length + clearance_top + clearance_bottom:
        raise BoundaryOverlapError("Error: The specified boundary dimensions are too small and overlap with the inner contours. Please provide larger values.")

    # Compute the boundary rectangle centered on the inner contours.
    shape_cx = (min_x + max_x) / 2
    left = shape_cx - boundary_width_in / 2
    right = shape_cx + boundary_width_in / 2
    # Align bottom to inner bounding box with the desired bottom clearance.
    bottom = min_y - clearance_bottom
    top = bottom + boundary_length_in

    rect_coords = [(left, bottom), (right, bottom), (right, top), (left, top), (left, bottom)]
    from shapely.geometry import Polygon as ShapelyPolygon
    boundary_polygon = ShapelyPolygon(rect_coords)
    msp.add_lwpolyline(rect_coords, close=True, dxfattribs={"layer": "BOUNDARY"})
    return boundary_polygon

def draw_polygons_inch(polygons_inch, image_rgb, scaling_factor, image_height, color=(0,0,255), thickness=2):
    for poly in polygons_inch:
        if poly.geom_type == "MultiPolygon":
            for subpoly in poly.geoms:
                draw_single_polygon(subpoly, image_rgb, scaling_factor, image_height, color, thickness)
        else:
            draw_single_polygon(poly, image_rgb, scaling_factor, image_height, color, thickness)

def draw_single_polygon(poly, image_rgb, scaling_factor, image_height, color=(0,0,255), thickness=2):
    ext = list(poly.exterior.coords)
    if len(ext) < 3:
        return
    pts_px = []
    for (x_in, y_in) in ext:
        px = int(x_in / scaling_factor)
        py = int(image_height - (y_in / scaling_factor))
        pts_px.append([px, py])
    pts_px = np.array(pts_px, dtype=np.int32)
    cv2.polylines(image_rgb, [pts_px], isClosed=True, color=color, thickness=thickness, lineType=cv2.LINE_AA)

# ---------------------
# Main Predict Function with Finger Cut Clearance, Boundary Box, Annotation and Sharpness Enhancement
# ---------------------
def predict(
    image: Union[str, bytes, np.ndarray],
    offset_value: float,
    offset_unit: str,         # "mm" or "inches"
    finger_clearance: str,    # "Yes" or "No"
    add_boundary: str,        # "Yes" or "No"
    boundary_length: float,
    boundary_width: float,
    annotation_text: str
):
    overall_start = time.time()
    # Convert image to NumPy array if needed.
    if isinstance(image, str):
        if os.path.exists(image):
            image = np.array(Image.open(image).convert("RGB"))
        else:
            try:
                image = np.array(Image.open(io.BytesIO(base64.b64decode(image))).convert("RGB"))
            except Exception:
                raise ValueError("Invalid base64 image data")

    # Apply sharpness enhancement.
    if isinstance(image, np.ndarray):
        pil_image = Image.fromarray(image)
        enhanced_image = ImageEnhance.Sharpness(pil_image).enhance(1)
        ei = ImageEnhance.Contrast(image).enhance(1.5)
        image = np.array(ei)

    # ---------------------
    # 1) Detect the drawer with YOLOWorld
    # ---------------------
    try:
        t = time.time()
        drawer_img = yolo_detect(image)
        print("Drawer detection completed in {:.2f} seconds".format(time.time() - t))
        t = time.time()
        shrunked_img = make_square(shrink_bbox(drawer_img, 0.90))
        del drawer_img
        gc.collect()
        print("Image shrinking completed in {:.2f} seconds".format(time.time() - t))
    except DrawerNotDetectedError:
        raise DrawerNotDetectedError("Drawer not detected! Please take another picture with a drawer.")

    # ---------------------
    # 2) Detect the reference box with YOLO
    # ---------------------
    try:
        t = time.time()
        reference_obj_img, scaling_box_coords = detect_reference_square(shrunked_img)
        print("Reference square detection completed in {:.2f} seconds".format(time.time() - t))
    except ReferenceBoxNotDetectedError:
        raise ReferenceBoxNotDetectedError("Reference box not detected! Please take another picture with a reference box.")

    # ---------------------
    # 3) Remove background of the reference box to compute scaling factor
    # ---------------------
    t = time.time()
    reference_obj_img = make_square(reference_obj_img)
    reference_square_mask = remove_bg_u2netp(reference_obj_img)
    print("Reference image processing completed in {:.2f} seconds".format(time.time() - t))

    t = time.time()
    try:
        cv2.imwrite("mask.jpg", cv2.cvtColor(reference_obj_img, cv2.COLOR_RGB2GRAY))
        scaling_factor = calculate_scaling_factor(
            reference_image_path="./Reference_ScalingBox.jpg",
            target_image=reference_square_mask,
            feature_detector="ORB",
        )
    except ZeroDivisionError:
        scaling_factor = None
        print("Error calculating scaling factor: Division by zero")
    except Exception as e:
        scaling_factor = None
        print(f"Error calculating scaling factor: {e}")

    if scaling_factor is None or scaling_factor == 0:
        scaling_factor = 1.0
        print("Using default scaling factor of 1.0 due to calculation error")
    gc.collect()
    print("Scaling factor determined: {}".format(scaling_factor))

    # ---------------------
    # 4) Optional boundary dimension checks
    # ---------------------
    if add_boundary.lower() == "yes":
        image_height_px, image_width_px = shrunked_img.shape[:2]
        image_height_in = image_height_px * scaling_factor
        image_width_in = image_width_px * scaling_factor
        # If units are mm, convert them to inches if the values look small
        if offset_unit.lower() == "mm":
            if boundary_length < 50:
                boundary_length = boundary_length * 25.4
            if boundary_width < 50:
                boundary_width = boundary_width * 25.4
            boundary_length_in = boundary_length / 25.4
            boundary_width_in = boundary_width / 25.4
        else:
            boundary_length_in = boundary_length
            boundary_width_in = boundary_width

        # Basic check so user doesn't request an impossible boundary
        if boundary_length_in > (image_height_in - 1) or boundary_width_in > (image_width_in - 1):
            raise BoundaryExceedsError(
                "Error: The specified boundary dimensions exceed the allowed image dimensions. Please enter smaller values."
            )

    # ---------------------
    # 5) Remove background from the shrunked drawer image (main objects)
    # ---------------------
    if offset_unit.lower() == "mm":
        if offset_value < 1:
            offset_value = offset_value * 25.4
        offset_inches = offset_value / 25.4
    else:
        offset_inches = offset_value

    t = time.time()
    orig_size = shrunked_img.shape[:2]
    objects_mask = remove_bg(shrunked_img)
    processed_size = objects_mask.shape[:2]

    # Exclude the reference box region from the mask
    objects_mask = exclude_scaling_box(objects_mask, scaling_box_coords, orig_size, processed_size, expansion_factor=1.2)
    objects_mask = resize_img(objects_mask, (shrunked_img.shape[1], shrunked_img.shape[0]))
    del scaling_box_coords
    gc.collect()
    print("Object masking completed in {:.2f} seconds".format(time.time() - t))

    # Dilate mask by offset_pixels
    t = time.time()
    offset_pixels = (offset_inches / scaling_factor) * 2 + 1 if scaling_factor != 0 else 1
    dilated_mask = cv2.dilate(objects_mask, np.ones((int(offset_pixels), int(offset_pixels)), np.uint8))
    del objects_mask
    gc.collect()
    print("Mask dilation completed in {:.2f} seconds".format(time.time() - t))

    Image.fromarray(dilated_mask).save("./outputs/scaled_mask_new.jpg")

    # ---------------------
    # 6) Extract outlines from the mask and convert them to DXF splines
    # ---------------------
    t = time.time()
    outlines, contours = extract_outlines(dilated_mask)
    print("Outline extraction completed in {:.2f} seconds".format(time.time() - t))

    output_img = shrunked_img.copy()
    del shrunked_img
    gc.collect()

    t = time.time()
    use_finger_clearance = True if finger_clearance.lower() == "yes" else False
    doc, final_polygons_inch = save_dxf_spline(
        contours, scaling_factor, processed_size[0], finger_clearance=use_finger_clearance
    )
    del contours
    gc.collect()
    print("DXF generation completed in {:.2f} seconds".format(time.time() - t))

    # ---------------------
    # Compute bounding box of inner tool contours BEFORE adding optional boundary
    # ---------------------
    inner_min_x = float("inf")
    inner_min_y = float("inf")
    inner_max_x = -float("inf")
    inner_max_y = -float("inf")
    for poly in final_polygons_inch:
        b = poly.bounds
        inner_min_x = min(inner_min_x, b[0])
        inner_min_y = min(inner_min_y, b[1])
        inner_max_x = max(inner_max_x, b[2])
        inner_max_y = max(inner_max_y, b[3])

    # ---------------------
    # 7) Add optional rectangular boundary (with the 0.75 bottom margin if annotation text is provided)
    # ---------------------
    boundary_polygon = None
    if add_boundary.lower() == "yes":
        boundary_polygon = add_rectangular_boundary(
            doc, final_polygons_inch, boundary_length, boundary_width, offset_unit, annotation_text
        )
        if boundary_polygon is not None:
            final_polygons_inch.append(boundary_polygon)

    # ---------------------
    # 8) Add annotation text (if provided) in the DXF
    #    - Text is 0.5 inches high
    #    - Placed so that its top edge is 0.125 inches below the inner tools' contour
    # ---------------------
    msp = doc.modelspace()
    if annotation_text.strip():
        # Use the inner contours bounding box computed earlier.
        text_x = (inner_min_x + inner_max_x) / 2.0  
        text_height_dxf = 0.5  
        # Place the text so that its top edge is 0.125 inches below the inner tool contour.
        # Since text height is 0.5 inches, the baseline is at inner_min_y - 0.125 - text_height_dxf.
        text_y_dxf = inner_min_y - 0.125 - text_height_dxf  
        text_entity = msp.add_text(
            annotation_text.strip(),
            dxfattribs={
                "height": text_height_dxf,
                "layer": "ANNOTATION",
                "style": "Bold"
            }
        )
        text_entity.dxf.insert = (text_x, text_y_dxf)

    # Save the DXF
    dxf_filepath = os.path.join("./outputs", "out.dxf")
    doc.saveas(dxf_filepath)

    # ---------------------
    # 9) For the preview images, draw the polygons and place text similarly
    # ---------------------
    draw_polygons_inch(final_polygons_inch, output_img, scaling_factor, processed_size[0], color=(0, 0, 255), thickness=2)
    new_outlines = np.ones_like(output_img) * 255
    draw_polygons_inch(final_polygons_inch, new_outlines, scaling_factor, processed_size[0], color=(0, 0, 255), thickness=2)

    if annotation_text.strip():
        # Use the same logic as DXF:
        # Text is 0.5 inches high, and its baseline is at inner_min_y - 0.125 - 0.5.
        text_height_cv = 0.5  # logical height in inches
        # Calculate horizontal center (in inches) and convert to pixels
        text_x_img = int(((inner_min_x + inner_max_x) / 2.0) / scaling_factor)
        # Baseline position in inches:
        text_y_in = inner_min_y - 0.125 - text_height_cv  
        # Convert the baseline from inches to pixel coordinate
        text_y_img = int(processed_size[0] - (text_y_in / scaling_factor))
        # Shift left to center the text approximately
        org = (text_x_img - int(len(annotation_text.strip()) * 6), text_y_img)

        cv2.putText(
            output_img,
            annotation_text.strip(),
            org,
            cv2.FONT_HERSHEY_SIMPLEX,
            1.3,          # scale factor
            (0, 0, 255),
            3,
            cv2.LINE_AA
        )
        cv2.putText(
            new_outlines,
            annotation_text.strip(),
            org,
            cv2.FONT_HERSHEY_SIMPLEX,
            1.3,
            (0, 0, 255),
            3,
            cv2.LINE_AA
        )

    outlines_color = cv2.cvtColor(new_outlines, cv2.COLOR_BGR2RGB)
    print("Total prediction time: {:.2f} seconds".format(time.time() - overall_start))

    return (
        cv2.cvtColor(output_img, cv2.COLOR_BGR2RGB),
        outlines_color,
        dxf_filepath,
        dilated_mask,
        str(scaling_factor)
    )

# ---------------------
# Gradio Interface
# ---------------------
if __name__ == "__main__":
    os.makedirs("./outputs", exist_ok=True)
    def gradio_predict(img, offset, offset_unit, finger_clearance, add_boundary, boundary_length, boundary_width, annotation_text):
        try:
            return predict(img, offset, offset_unit, finger_clearance, add_boundary, boundary_length, boundary_width, annotation_text)
        except Exception as e:
            return None, None, None, None, f"Error: {str(e)}"
    iface = gr.Interface(
        fn=gradio_predict,
        inputs=[
            gr.Image(label="Input Image"),
            gr.Number(label="Offset value for Mask", value=0.075),
            gr.Dropdown(label="Offset Unit", choices=["mm", "inches"], value="inches"),
            gr.Dropdown(label="Add Finger Clearance?", choices=["Yes", "No"], value="No"),
            gr.Dropdown(label="Add Rectangular Boundary?", choices=["Yes", "No"], value="No"),
            gr.Number(label="Boundary Length", value=300.0, precision=2),
            gr.Number(label="Boundary Width", value=200.0, precision=2),
            gr.Textbox(label="Annotation (max 20 chars)", max_length=20, placeholder="Type up to 20 characters")
        ],
        outputs=[
            gr.Image(label="Output Image"),
            gr.Image(label="Outlines of Objects"),
            gr.File(label="DXF file"),
            gr.Image(label="Mask"),
            gr.Textbox(label="Scaling Factor (inches/pixel)")
        ],
        examples=[
            ["./Test20.jpg", 0.075, "inches", "No", "No", 300.0, 200.0, "MyTool"],
            ["./Test21.jpg", 0.075, "inches", "Yes", "Yes", 300.0, 200.0, "Tool2"]
        ]
    )
    iface.launch(share=True)