filter less the cards

app.py

@@ -85,47 +85,47 @@ def detect_cards_and_sum(image, game):
         H, W = annotated.shape[:2]
         img_area = float(H * W)
 
-        # --- robust edge map for rectangles ---
+        # --- edge map ---
         gray = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY)
-        gray = cv2.GaussianBlur(gray, (5, 5), 0)
-        edges = cv2.Canny(gray, 60, 160)
+        blur = cv2.GaussianBlur(gray, (5, 5), 0)
+        edges = cv2.Canny(blur, 50, 150)
         edges = cv2.dilate(edges, np.ones((3, 3), np.uint8), iterations=1)
 
         contours, _ = cv2.findContours(edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
 
+        # sort largest to smallest
+        contours = sorted(contours, key=cv2.contourArea, reverse=True)
+
         values = []
-        drawn_boxes = 0
 
         for cnt in contours:
-            # geometric filtering
-            rect = cv2.minAreaRect(cnt)              # (center, (w, h), angle)
+            rect = cv2.minAreaRect(cnt)
             (cx, cy), (rw, rh), _ = rect
             if rw == 0 or rh == 0:
                 continue
 
-            box = cv2.boxPoints(rect)                # 4 points, unordered
+            box = cv2.boxPoints(rect)
             box = np.int32(box)
 
-            # use bounding area (more stable with edges than contour area)
             box_area = rw * rh
-            if box_area < 0.01 * img_area or box_area > 0.8 * img_area:
+            if box_area < 0.002 * img_area or box_area > 0.9 * img_area:
                 continue  # too small or too big to be a card
 
-            # aspect ratio (card ~ 1.4–1.8 between long/short edges)
+            # aspect ratio (card ~ 1.4�1.8 between long/short edges)
             long_side = max(rw, rh)
             short_side = min(rw, rh)
             ratio = long_side / short_side
-            if ratio < 1.2 or ratio > 1.9:
+            if ratio < 1.1 or ratio > 2.2:
                 continue
 
             # rectangularity: contour area close to its minAreaRect area
             cnt_area = cv2.contourArea(cnt)
-            if cnt_area / box_area < 0.65:
+            if cnt_area / box_area < 0.5:
                 continue
 
             # perspective warp to a canonical card size (2:3 ratio)
             dst_w, dst_h = 300, 450
-            M = cv2.getPerspectiveTransform(order_points(box), 
+            M = cv2.getPerspectiveTransform(order_points(box),
                                             np.array([[0, 0],
                                                       [dst_w-1, 0],
                                                       [dst_w-1, dst_h-1],
@@ -151,9 +151,8 @@ def detect_cards_and_sum(image, game):
                 ty = int(moments["m01"] / moments["m00"])
             else:
                 tx, ty = int(cx), int(cy)
-            cv2.putText(annotated, str(val), (tx - 10, ty - 10),
+            cv2.putText(annotated, str(val), (tx-10, ty-10),
                         cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 3)
-            drawn_boxes += 1
 
         if not values:
             # return the annotated image anyway so you can see what was (not) detected
@@ -166,6 +165,7 @@ def detect_cards_and_sum(image, game):
 
 
 
+
 # Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown("## Card Value Detector (Skyjo / Flip7)")