增加几何校验

normalize_reference.py

@@ -3,14 +3,50 @@
 import argparse
 from pathlib import Path
 from PIL import Image
+import numpy as np
+import cv2
+
+
+def prepare_rgba(image, white_threshold=240):
+    """Keep existing alpha; remove only border-connected near-white background.
+
+    No crop or rescale here: semantic coordinates must retain the full canvas.
+    White regions enclosed by character outlines are deliberately preserved.
+    """
+    rgba = np.array(image.convert('RGBA'))
+    alpha = rgba[:, :, 3]
+    method = 'existing_alpha'
+    removed = 0
+    if not np.any(alpha == 0):
+        white = np.all(rgba[:, :, :3] >= white_threshold, axis=2).astype(np.uint8)
+        _, labels = cv2.connectedComponents(white, connectivity=4)
+        border = np.unique(np.concatenate((labels[0], labels[-1], labels[:, 0], labels[:, -1])))
+        background = np.isin(labels, border[border != 0])
+        removed = int(background.sum())
+        rgba[background, 3] = 0
+        method = 'border_connected_white'
+    foreground = rgba[:, :, 3] > 0
+    if not foreground.any():
+        raise ValueError('Reference has no foreground after background removal')
+    if foreground.all():
+        raise ValueError('No transparent background or border-connected white background; supply a cutout RGBA PNG')
+    return Image.fromarray(rgba), {
+        'method': method, 'white_threshold': white_threshold,
+        'removed_pixels': removed, 'foreground_pixels': int(foreground.sum()),
+        'width': image.width, 'height': image.height,
+        'needs_review': method != 'existing_alpha',
+    }
 
 def main():
     p = argparse.ArgumentParser()
     p.add_argument('--input', required=True)
     p.add_argument('--output', required=True)
     p.add_argument('--target', type=int, default=1024)
+    p.add_argument('--remove-background', action='store_true')
     a = p.parse_args()
     im = Image.open(a.input).convert('RGBA')
+    if a.remove_background:
+        im, _ = prepare_rgba(im)
     longest = max(im.width, im.height)
     if longest < a.target:
         scale = a.target / longest