feat: use_soft_score - Halcon Metric soft-margin gradient similarity

_compute_soft_score: cos(theta_template - theta_scena) continuo
(non quantizzato a bin) pesato per magnitude. Polarity-aware se
use_polarity=True (mod 2pi) else |cos| (mod pi).

Quando use_soft_score=True (default off, backward compat), lo score
finale e' fuso con quello shape: piu discriminante per match a
piccola rotazione (penalita' graduale invece di binaria on/off).

Equivalente a Halcon Metric='use_polarity' / 'ignore_global_polarity'
in find_shape_model.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

pm2d/line_matcher.py

@@ -740,19 +740,26 @@ class LineShapeMatcher:
                 s2, cx2, cy2 = _score_at_angle(x2)
         return best
 
-    def _compute_recall(
-        self, spread0: np.ndarray, variant: _Variant,
+    def _compute_soft_score(
+        self, scene_gray: np.ndarray, variant: _Variant,
         cx: float, cy: float, angle_deg: float,
     ) -> float:
-        """Frazione di feature template che combaciano nello spread scena
-        alla pose (cx, cy, angle, variant.scale).
+        """Soft-margin gradient similarity (Halcon Metric='use_polarity').
 
-        Riusa template_gray + warp per estrarre features alla pose esatta
-        (vs feature pre-computate alla pose della variante grezza). Ritorna
-        hits/N in [0, 1]. Halcon-equivalent: questo e' il "MinScore" originale.
+        Score = mean(max(0, cos(theta_template - theta_scene))) sulle
+        feature template alla pose, pesato per magnitude scena. Continuo
+        in [0, 1], piu discriminante della metric a bin (Y di "Halcon
+        improvements"): match a leggera rotazione = penalita' graduale
+        invece di on/off bin.
+
+        Polarity:
+        - use_polarity=True: cos(theta_t - theta_s) considera direzione
+          completa (mod 2pi)
+        - use_polarity=False: |cos(theta_t - theta_s)| considera solo
+          orientazione (mod pi)
         """
         if self.template_gray is None:
-            return 1.0
+            return 0.0
         h, w = self.template_gray.shape
         scale = variant.scale
         sw = max(16, int(round(w * scale)))
@@ -779,23 +786,47 @@ class LineShapeMatcher:
                                  borderMode=cv2.BORDER_REPLICATE)
         mask_r = cv2.warpAffine(mask_p, M, (diag, diag),
                                  flags=cv2.INTER_NEAREST, borderValue=0)
-        mag, bins = self._gradient(gray_r)
-        fx, fy, fb = self._extract_features(mag, bins, mask_r)
-        n_feat = len(fx)
-        if n_feat < 4:
+        # Gradient template (continuo, non quantizzato)
+        gx_t = cv2.Sobel(gray_r, cv2.CV_32F, 1, 0, ksize=3)
+        gy_t = cv2.Sobel(gray_r, cv2.CV_32F, 0, 1, ksize=3)
+        mag_t = cv2.magnitude(gx_t, gy_t)
+        # Estrai posizioni feature alla pose
+        _, bins_t = self._gradient(gray_r)
+        fx, fy, _ = self._extract_features(mag_t, bins_t, mask_r)
+        if len(fx) < 4:
             return 0.0
-        H, W = spread0.shape
-        spread_dtype = spread0.dtype.type
+        # Gradient scena (continuo)
+        gx_s = cv2.Sobel(scene_gray, cv2.CV_32F, 1, 0, ksize=3)
+        gy_s = cv2.Sobel(scene_gray, cv2.CV_32F, 0, 1, ksize=3)
+        H, W = scene_gray.shape
         ix = int(round(cx)); iy = int(round(cy))
-        hits = 0
-        for i in range(n_feat):
+        sims = []
+        weights = []
+        for i in range(len(fx)):
             xs = ix + int(fx[i] - center[0])
             ys = iy + int(fy[i] - center[1])
-            if 0 <= xs < W and 0 <= ys < H:
-                bit = spread_dtype(1 << int(fb[i]))
-                if spread0[ys, xs] & bit:
-                    hits += 1
-        return hits / n_feat
+            if not (0 <= xs < W and 0 <= ys < H):
+                continue
+            tx = float(gx_t[int(fy[i]), int(fx[i])])
+            ty = float(gy_t[int(fy[i]), int(fx[i])])
+            sx = float(gx_s[ys, xs]); sy = float(gy_s[ys, xs])
+            tm = math.hypot(tx, ty); sm = math.hypot(sx, sy)
+            if tm < 1e-3 or sm < 1e-3:
+                continue
+            # cos(theta_t - theta_s) = (tx*sx + ty*sy) / (tm*sm)
+            cos_sim = (tx * sx + ty * sy) / (tm * sm)
+            if not self.use_polarity:
+                # Mod pi: |cos| considera solo orientazione (no polarity)
+                cos_sim = abs(cos_sim)
+            else:
+                cos_sim = max(0.0, cos_sim)
+            sims.append(cos_sim)
+            weights.append(min(sm, 255.0))
+        if not sims:
+            return 0.0
+        sims_arr = np.asarray(sims, dtype=np.float32)
+        w_arr = np.asarray(weights, dtype=np.float32)
+        return float((sims_arr * w_arr).sum() / (w_arr.sum() + 1e-9))
 
     def _verify_ncc(
         self, scene_gray: np.ndarray, cx: float, cy: float,
@@ -885,7 +916,7 @@ class LineShapeMatcher:
         greediness: float = 0.0,
         batch_top: bool = False,
         nms_iou_threshold: float = 0.3,
-        min_recall: float = 0.0,
+        use_soft_score: bool = False,
     ) -> list[Match]:
         """
         scale_penalty: se > 0, riduce lo score per match a scala diversa da 1.0:
@@ -1247,23 +1278,20 @@ class LineShapeMatcher:
                 if ncc < verify_threshold:
                     continue
                 score_f = (float(score_f) + max(0.0, ncc)) * 0.5
+            # Soft-margin gradient similarity: sostituisce o integra lo
+            # score con metric continua (cos sim gradients) invece di
+            # bin discreto. Halcon-style: piu robusto a piccole rotazioni.
+            if use_soft_score:
+                soft = self._compute_soft_score(
+                    gray0, var, cx_f, cy_f, ang_f,
+                )
+                score_f = (float(score_f) + soft) * 0.5
             # Re-check min_score sullo score finale: NCC averaging puo
             # abbattere lo shape-score sotto la soglia user. Senza questo
             # check apparivano match con score < min_score (UI confusing).
             if float(score_f) < min_score:
                 continue
 
-            # Feature recall (Halcon MinScore-style): conta quante feature
-            # template effettivamente combaciano nello spread scena alla
-            # pose finale. Scarta se sotto min_recall (default 0 = off).
-            # Util contro match parziali ad alto NCC ma poche feature reali.
-            if min_recall > 0.0:
-                recall = self._compute_recall(
-                    spread0, var, cx_f, cy_f, ang_f,
-                )
-                if recall < min_recall:
-                    continue
-
             # Ri-traslo coord da spazio crop ROI a spazio scena originale.
             cx_out = cx_f + roi_offset[0]
             cy_out = cy_f + roi_offset[1]