optimize OCR for Skyjo

app.py

@@ -9,29 +9,45 @@ VALID_PATTERN = re.compile(r"-?\d+")
 
 def extract_skyjo_value(card_img):
     h, w, _ = card_img.shape
-    margin = 50
+    margin = int(min(h, w) * 0.1)  # Dynamic margin
     roi = card_img[margin:h-margin, margin:w-margin]
 
+    # Preprocessing
     gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
-    gray = cv2.GaussianBlur(gray, (3,3), 0)
-    thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)[1]
-
-    raw_text = pytesseract.image_to_string(
-        thresh,
-        config="--psm 6 -c tessedit_char_whitelist=-0123456789"
+    gray = cv2.GaussianBlur(gray, (3, 3), 0)
+    thresh = cv2.adaptiveThreshold(
+        gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
+        cv2.THRESH_BINARY_INV, 11, 2
     )
+    kernel = np.ones((2, 2), np.uint8)
+    thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
+
+    # Try OCR on both original and rotated card
+    for angle in [0, 180]:
+        if angle == 180:
+            rotated = cv2.rotate(thresh, cv2.ROTATE_180)
+            raw_text = pytesseract.image_to_string(
+                rotated,
+                config="--psm 10 --oem 3 -c tessedit_char_whitelist=-0123456789"
+            )
+        else:
+            raw_text = pytesseract.image_to_string(
+                thresh,
+                config="--psm 10 --oem 3 -c tessedit_char_whitelist=-0123456789"
+            )
+
+        # Extract numbers
+        matches = re.findall(r"-?\d+", raw_text)
+        for m in matches:
+            try:
+                val = int(m)
+                if -2 <= val <= 12:
+                    return val
+            except ValueError:
+                continue
 
-    matches = re.findall(r"-?\d+", raw_text)
-    for m in matches:
-        try:
-            val = int(m)
-            if -2 <= val <= 12:
-                return val
-        except ValueError:
-            continue
     return None
 
-
 def extract_flip7_value(card_img):
     h, w, _ = card_img.shape
     margin = 50
@@ -152,7 +168,7 @@ def detect_cards_and_sum(image, game):
             else:
                 tx, ty = int(cx), int(cy)
             cv2.putText(annotated, str(val), (tx-10, ty-10),
-                        cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 3)
+                        cv2.FONT_HERSHEY_SIMPLEX, 1.5, (0, 0, 255), 3)
 
         if not values:
             # return the annotated image anyway so you can see what was (not) detected