Update app.py

app.py

@@ -4,6 +4,7 @@ import json
 import gradio as gr
 import os
 import xml.etree.ElementTree as ET
+from lxml import etree
 
 # ---------------- Helper functions ----------------
 def get_rotated_rect_corners(x, y, w, h, rotation_deg):
@@ -45,25 +46,33 @@ def parse_xml_points(xml_file):
         points.append([float(elem.get("x")), float(elem.get("y"))])
     return np.array(points,dtype=np.float32).reshape(-1,2)
 
+def extract_four_points_from_xml(xml_path):
+    tree = etree.parse(xml_path)
+    root = tree.getroot()
+    transform = root.find('.//transform')
+    points = {}
+    for pt in transform.findall('.//point'):
+        pt_type = pt.attrib['type']
+        x = int(float(pt.attrib['x']))
+        y = int(float(pt.attrib['y']))
+        points[pt_type] = (x, y)
+    return points
+
+def draw_polygon_overlay(img, points_dict):
+    ordered_points = ['TopLeft','TopRight','BottomRight','BottomLeft']
+    polygon = [points_dict[pt] for pt in ordered_points]
+    pts = np.array(polygon, np.int32).reshape((-1,1,2))
+    img_overlay = img.copy()
+    cv2.polylines(img_overlay, [pts], isClosed=True, color=(255,0,0), thickness=3)
+    return img_overlay
+
 # ---------------- Padding Helper ----------------
 def pad_to_size(img, target_h, target_w):
     h, w = img.shape[:2]
-    top_pad = 0
-    left_pad = 0
-    bottom_pad = target_h - h
-    right_pad = target_w - w
     canvas = np.ones((target_h, target_w,3), dtype=np.uint8)*255
-    canvas[top_pad:top_pad+h, left_pad:left_pad+w] = img
+    canvas[:h, :w] = img
     return canvas
 
-# ---------------- Draw XML Ground-Truth ----------------
-def draw_xml_gt(img, xml_points):
-    for px,py in xml_points:
-        cv2.circle(img,(int(px),int(py)),5,(0,0,255),-1)
-    # Draw polygon
-    cv2.polylines(img,[xml_points.astype(np.int32)],True,(255,0,0),2)
-    return img
-
 # ---------------- Main Function ----------------
 def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
     flat_img = cv2.imread(flat_file)
@@ -77,6 +86,7 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
     flat_gray = preprocess_gray_clahe(flat_img)
     persp_gray = preprocess_gray_clahe(persp_img)
     xml_points = parse_xml_points(xml_file.name)
+    xml_dict = extract_four_points_from_xml(xml_file.name)
 
     methods = ["SIFT","ORB","BRISK","KAZE","AKAZE"]
     gallery_paths = []
@@ -93,7 +103,7 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
         H,_ = cv2.findHomography(src_pts,dst_pts,cv2.RANSAC,5.0)
         if H is None: continue
 
-        # ROI homography projection
+        # Homography-based ROI overlay
         roi_corners_flat = get_rotated_rect_corners(roi_x,roi_y,roi_w,roi_h,roi_rot_deg)
         roi_corners_persp = cv2.perspectiveTransform(roi_corners_flat.reshape(-1,1,2),H).reshape(-1,2)
         persp_roi = persp_img.copy()
@@ -101,20 +111,19 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
         for px,py in roi_corners_persp: cv2.circle(persp_roi,(int(px),int(py)),5,(255,0,0),-1)
 
         # XML GT overlay
-        xml_gt_img = persp_img.copy()
-        xml_gt_img = draw_xml_gt(xml_gt_img, xml_points)
+        xml_gt_img = draw_polygon_overlay(persp_img, xml_dict)
 
         # Convert to RGB
-        flat_rgb = cv2.cvtColor(flat_img,cv2.COLOR_BGR2RGB)
-        match_rgb = cv2.cvtColor(match_img,cv2.COLOR_BGR2RGB)
-        roi_rgb = cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB)
-        xml_rgb = cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB)
+        flat_rgb = cv2.cvtColor(flat_img, cv2.COLOR_BGR2RGB)
+        match_rgb = cv2.cvtColor(match_img, cv2.COLOR_BGR2RGB)
+        roi_rgb = cv2.cvtColor(persp_roi, cv2.COLOR_BGR2RGB)
+        xml_rgb = cv2.cvtColor(xml_gt_img, cv2.COLOR_BGR2RGB)
 
-        # Determine max height and width for padding
+        # Determine max height/width
         max_h = max(flat_rgb.shape[0], match_rgb.shape[0], roi_rgb.shape[0], xml_rgb.shape[0])
         max_w = max(flat_rgb.shape[1], match_rgb.shape[1], roi_rgb.shape[1], xml_rgb.shape[1])
 
-        # Pad all images to same size
+        # Pad all images
         flat_pad = pad_to_size(flat_rgb, max_h, max_w)
         match_pad = pad_to_size(match_rgb, max_h, max_w)
         roi_pad = pad_to_size(roi_rgb, max_h, max_w)
@@ -125,10 +134,10 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
         bottom = np.hstack([roi_pad, xml_pad])
         combined_grid = np.vstack([top, bottom])
 
-        # Save combined grid
+        # Save
         base_name = os.path.splitext(os.path.basename(persp_file))[0]
         file_name = f"{base_name}_{method.lower()}.png"
-        cv2.imwrite(file_name, cv2.cvtColor(combined_grid,cv2.COLOR_RGB2BGR))
+        cv2.imwrite(file_name, cv2.cvtColor(combined_grid, cv2.COLOR_RGB2BGR))
         gallery_paths.append(file_name)
         download_files.append(file_name)
 
@@ -152,8 +161,8 @@ iface = gr.Interface(
         gr.File(label="Download KAZE Result"),
         gr.File(label="Download AKAZE Result")
     ],
-    title="Homography ROI Projection with Feature Matching & XML GT",
-    description="Flat + Perspective images with mockup.json & XML. Original resolution maintained. Grid aligned with white padding. XML GT overlaid."
+    title="Homography ROI + Feature Matching + XML GT",
+    description="Shows Flat, Feature-Matched, Homography ROI (green), and XML Ground-Truth (red) overlay in a 2x2 grid with same size."
 )
 
 iface.launch()