Update app.py

app.py

@@ -45,25 +45,25 @@ 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)
 
-# ---------------- Padding Helper ----------------
+# ---------------- Padding Helpers ----------------
 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
 
-# ---------------- Resize feature-match to original reference size ----------------
 def match_img_to_reference(match_img, ref_h, ref_w):
     h, w = match_img.shape[:2]
-    scale = min(ref_w/w, ref_h/h)
-    new_w, new_h = int(w*scale), int(h*scale)
+    scale = ref_w / w
+    new_w = ref_w
+    new_h = int(h * scale)
     resized = cv2.resize(match_img, (new_w,new_h))
-    padded = pad_to_size(resized, ref_h, ref_w)
-    return padded
+    if new_h < ref_h:
+        canvas = np.ones((ref_h, ref_w,3), dtype=np.uint8)*255
+        canvas[:new_h,:new_w] = resized
+        return canvas
+    else:
+        return resized
 
 # ---------------- Main Function ----------------
 def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
@@ -110,22 +110,26 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
         roi_rgb = cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB)
         xml_rgb = cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB)
 
-        # Resize feature-match image to match original flat/perspective
-        match_rgb = match_img_to_reference(cv2.cvtColor(match_img, cv2.COLOR_BGR2RGB), flat_rgb.shape[0], flat_rgb.shape[1])
+        # Resize match_img to flat image width, maintain aspect ratio
+        match_rgb = match_img_to_reference(cv2.cvtColor(match_img, cv2.COLOR_BGR2RGB),
+                                           flat_rgb.shape[0], flat_rgb.shape[1])
 
-        # Determine max height and width for grid (all images now same)
+        # Determine max height and width for grid
         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
         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)
         xml_pad = pad_to_size(xml_rgb, max_h, max_w)
 
         # Merge 2x2 grid
-        top = np.hstack([flat_pad, match_rgb])
+        top = np.hstack([flat_pad, match_pad])
         bottom = np.hstack([roi_pad, xml_pad])
         combined_grid = np.vstack([top, bottom])
 
+        # Save combined grid
         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))
@@ -135,6 +139,7 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
     while len(download_files)<5: download_files.append(None)
     return gallery_paths, download_files[0], download_files[1], download_files[2], download_files[3], download_files[4]
 
+# ---------------- Gradio UI ----------------
 iface = gr.Interface(
     fn=homography_all_detectors,
     inputs=[
@@ -152,7 +157,7 @@ iface = gr.Interface(
         gr.File(label="Download AKAZE Result")
     ],
     title="Homography ROI Projection with Feature Matching & XML GT",
-    description="Flat + Perspective images with mockup.json & XML. Feature-match aligned with original images using white padding."
+    description="Flat + Perspective images with mockup.json & XML. Original resolution maintained. Grid aligned with white padding."
 )
 
 iface.launch()