feat: duplicate detection via perceptual hashing

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

analyzer.py

@@ -1,6 +1,8 @@
 import cv2
 import numpy as np
 from PIL import Image
+import imagehash
+from typing import List
 
 
 def is_blurry(path: str, threshold: float = 100.0) -> bool:
@@ -27,3 +29,37 @@ def is_overexposed(path: str, threshold: float = 240.0) -> bool:
 def is_underexposed(path: str, threshold: float = 30.0) -> bool:
     """Gibt True zurueck, wenn das Bild unterbelichtet ist."""
     return _mean_brightness(path) < threshold
+
+
+def find_duplicates(paths: List[str], threshold: int = 8) -> List[List[str]]:
+    """
+    Findet Gruppen aehnlicher Bilder via perceptual hashing.
+    Das erste Element jeder Gruppe gilt als Original, der Rest als Duplikate.
+    """
+    hashes = {}
+    for path in paths:
+        try:
+            h = imagehash.phash(Image.open(path))
+            hashes[path] = h
+        except Exception:
+            continue
+
+    groups = []
+    used = set()
+    path_list = list(hashes.keys())
+
+    for i, p1 in enumerate(path_list):
+        if p1 in used:
+            continue
+        group = [p1]
+        for p2 in path_list[i + 1:]:
+            if p2 in used:
+                continue
+            if abs(hashes[p1] - hashes[p2]) <= threshold:
+                group.append(p2)
+                used.add(p2)
+        if len(group) > 1:
+            used.add(p1)
+            groups.append(group)
+
+    return groups