Update app.py

app.py

@@ -48,15 +48,21 @@ def parse_xml_points(xml_file):
         points[pt_type] = (x, y)
     return points
 
-# ---------------- Padding Helper ----------------
-def pad_to_size(img, target_h, target_w):
+# ---------------- Fit-to-Box Helper ----------------
+def fit_to_box(img, target_h=600, target_w=600):
     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
+    scale = min(target_w/w, target_h/h)   # preserve aspect ratio
+    new_w, new_h = int(w*scale), int(h*scale)
+    resized = cv2.resize(img, (new_w, new_h))
+
+    # symmetric padding
+    top = (target_h - new_h) // 2
+    bottom = target_h - new_h - top
+    left = (target_w - new_w) // 2
+    right = target_w - new_w - left
+
+    canvas = np.ones((target_h, target_w, 3), dtype=np.uint8) * 255
+    canvas[top:top+new_h, left:left+new_w] = resized
     return canvas
 
 # ---------------- Main Function ----------------
@@ -81,46 +87,39 @@ def homography_all_detectors(flat_file, persp_file, json_file, xml_file):
         kp1,kp2,good_matches = detect_and_match(flat_gray,persp_gray,method)
         if kp1 is None or kp2 is None or len(good_matches)<4: continue
 
-        match_img = cv2.drawMatches(flat_img,kp1,persp_img,kp2,good_matches,None,flags=2)
+        # ---------------- Match Image (aligned sizes)
+        flat_box = fit_to_box(flat_img, 600, 600)
+        persp_box = fit_to_box(persp_img, 600, 600)
+        match_img = cv2.drawMatches(flat_box,kp1,persp_box,kp2,good_matches,None,flags=2)
 
+        # ---------------- Homography ROI
         src_pts = np.float32([kp1[m.queryIdx].pt for m in good_matches]).reshape(-1,1,2)
         dst_pts = np.float32([kp2[m.trainIdx].pt for m in good_matches]).reshape(-1,1,2)
         H,_ = cv2.findHomography(src_pts,dst_pts,cv2.RANSAC,5.0)
         if H is None: continue
 
-        # Homography ROI
         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()
         cv2.polylines(persp_roi,[roi_corners_persp.astype(int)],True,(0,255,0),2)
         for px,py in roi_corners_persp: cv2.circle(persp_roi,(int(px),int(py)),5,(255,0,0),-1)
 
-        # XML Ground-Truth overlay
+        # ---------------- XML Ground-Truth overlay
         xml_gt_img = persp_img.copy()
         ordered_pts = ['TopLeft', 'TopRight', 'BottomRight', 'BottomLeft']
         xml_polygon = [xml_points[pt] for pt in ordered_pts]
         pts = np.array(xml_polygon, np.int32).reshape((-1,1,2))
         cv2.polylines(xml_gt_img,[pts],isClosed=True,color=(255,0,0),thickness=3)
 
-        # 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)
-
-        # Determine max height and 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 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)
+        # Convert all to RGB & fit into boxes
+        flat_rgb = fit_to_box(cv2.cvtColor(flat_img,cv2.COLOR_BGR2RGB),600,600)
+        match_rgb = fit_to_box(cv2.cvtColor(match_img,cv2.COLOR_BGR2RGB),600,600)
+        roi_rgb = fit_to_box(cv2.cvtColor(persp_roi,cv2.COLOR_BGR2RGB),600,600)
+        xml_rgb = fit_to_box(cv2.cvtColor(xml_gt_img,cv2.COLOR_BGR2RGB),600,600)
 
         # Merge 2x2 grid
-        top = np.hstack([flat_pad, match_pad])
-        bottom = np.hstack([roi_pad, xml_pad])
+        top = np.hstack([flat_rgb, match_rgb])
+        bottom = np.hstack([roi_rgb, xml_rgb])
         combined_grid = np.vstack([top, bottom])
 
         # Save grid
@@ -152,7 +151,7 @@ iface = gr.Interface(
         gr.File(label="Download AKAZE Result")
     ],
     title="Homography ROI + Feature Matching + XML GT",
-    description="Flat + Perspective images with mockup.json & XML. Original resolution maintained. Grid aligned with white padding."
+    description="Flat + Perspective images with mockup.json & XML. Aspect ratio preserved, images centered in uniform boxes."
 )
 
 iface.launch()