Update emotion.py

emotion.py

@@ -16,12 +16,12 @@ EMA_ALPHA = 0.45
 CONF_TH = 40.0
 SWITCH_CONFIRM_SEC = 2.5
 IOU_TH = 0.25
-ZOOM_FACTOR = 1.5
+ZOOM_FACTOR = 1.3  # 微調縮放，讓使用者較容易對準
 DETECTOR_BACKEND = "mtcnn"
 ALIGN_FACE = True
 
 # =========================
-# 狀態與映射 (保持原本邏輯)
+# 狀態與映射
 # =========================
 EMO_ZH = {"angry": "生氣", "disgust": "厭惡", "fear": "害怕", "happy": "開心", "sad": "難過", "surprise": "驚訝", "neutral": "平靜", "unknown": "未知"}
 EMO_TO_SCORE = {"angry": 1, "disgust": 1, "fear": 1, "sad": 2, "neutral": 3, "surprise": 4, "happy": 5, "unknown": 3}
@@ -51,13 +51,10 @@ def _hint_html(msg: str) -> str:
     return f'<div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#000000;">{msg}</div>'
 
 def _camera_hint_before_start() -> str:
-    return _hint_html("請先按「Click to access webcam」開啟攝影機，接著按「錄製 (Record)」開始。")
+    return _hint_html("請將臉部對準螢幕中央的方框。")
 
 def _camera_hint_done() -> str:
-    return _hint_html("已完成辨識，可按「重新攝影機辨識」再次進行。")
-
-def _camera_hint_stopped() -> str:
-    return _hint_html("已停止辨識。")
+    return _hint_html("已完成辨識。")
 
 def _result_card_html(emo_key: str, conf: Optional[float]) -> str:
     zh = EMO_ZH.get(emo_key, emo_key)
@@ -91,43 +88,61 @@ def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
     new_h = max(1, int(h * scale))
     return np.array(Image.fromarray(frame).resize((target_w, new_h)))
 
-# 這是關鍵：新增繪圖函式，確保顏色與座標正確
-def _draw_ui_overlay(frame: np.ndarray, is_detected: bool):
+# 核心修改：繪製固定導引框
+def _draw_ui_overlay(frame: np.ndarray, is_aligned: bool):
     canvas = frame.copy()
     h, w = canvas.shape[:2]
     
-    # 框的大小 (寬50%, 高60%)
-    bw, bh = int(w * 0.5), int(h * 0.6)
+    # 1. 定義「固定導引框」的位置與大小 (置中)
+    bw, bh = int(w * 0.45), int(h * 0.55)  # 框的大小
     x1, y1 = (w - bw) // 2, (h - bh) // 2
     x2, y2 = x1 + bw, y1 + bh
     
-    # 顏色判定 (RGB 格式)
-    # 如果抓到臉 -> 綠色 (0, 255, 0)；沒抓到 -> 紅色 (255, 0, 0)
-    color = (0, 255, 0) if is_detected else (255, 0, 0)
-    text = "DETECTED" if is_detected else "ALIGN FACE"
-
-    # 1. 畫外框矩形
-    cv2.rectangle(canvas, (x1, y1), (x2, y2), color, 4)
+    # 2. 顏色：對準了變綠色，沒對準是紅色
+    # (注意：OpenCV 預設是 BGR，但 Gradio 通常是 RGB，所以這裡設 (R, G, B))
+    color = (0, 255, 0) if is_aligned else (255, 0, 0)
+    status_text = "SCANNING..." if is_aligned else "PLACE FACE HERE"
+
+    # 3. 繪製半透明遮罩 (讓框以外的地方變暗，更有提示感)
+    overlay = canvas.copy()
+    cv2.rectangle(overlay, (0, 0), (w, h), (0, 0, 0), -1)
+    alpha = 0.3 # 變暗程度
+    cv2.addWeighted(overlay, alpha, canvas, 1 - alpha, 0, canvas)
     
-    # 2. 畫四個角落增強視覺感 (可選)
-    length = 30
-    cv2.line(canvas, (x1, y1), (x1 + length, y1), color, 8)
-    cv2.line(canvas, (x1, y1), (x1, y1 + length), color, 8)
+    # 4. 把框框的部分「挖亮」(恢復原樣)
+    canvas[y1:y2, x1:x2] = frame[y1:y2, x1:x2]
+
+    # 5. 繪製導引矩形
+    cv2.rectangle(canvas, (x1, y1), (x2, y2), color, 3)
     
-    # 3. 加上文字
-    cv2.putText(canvas, text, (x1, y1 - 15), cv2.FONT_HERSHEY_DUPLEX, 1.0, color, 2)
+    # 6. 繪製角點強化
+    l = 30 # 角線長度
+    cv2.line(canvas, (x1, y1), (x1+l, y1), color, 6)
+    cv2.line(canvas, (x1, y1), (x1, y1+l), color, 6)
+    cv2.line(canvas, (x2, y2), (x2-l, y2), color, 6)
+    cv2.line(canvas, (x2, y2), (x2, y2-l), color, 6)
+
+    # 7. 加上提示文字
+    cv2.putText(canvas, status_text, (x1, y1 - 15), cv2.FONT_HERSHEY_DUPLEX, 0.9, color, 2)
     
     return canvas
 
-def _iou(a, b):
-    ax, ay, aw, ah = a
-    bx, by, bw, bh = b
-    ix1, iy1 = max(ax, bx), max(ay, by)
-    ix2, iy2 = min(ax + aw, bx + bw), min(ay + ah, by + bh)
-    iw, ih = max(0, ix2 - ix1), max(0, iy2 - iy1)
-    inter = iw * ih
-    if inter <= 0: return 0.0
-    return inter / (aw * ah + bw * bh - inter)
+def _is_face_in_guide(face_bbox, frame_shape):
+    """ 檢查人臉是否在中央引導框內 """
+    if face_bbox is None: return False
+    fx, fy, fw, fh = face_bbox
+    h, w = frame_shape[:2]
+    
+    # 引導框範圍 (需與 _draw_ui_overlay 一致)
+    bw, bh = int(w * 0.45), int(h * 0.55)
+    gx1, gy1 = (w - bw) // 2, (h - bh) // 2
+    gx2, gy2 = gx1 + bw, gy1 + bh
+    
+    # 計算人臉中心點
+    fcx, fcy = fx + fw // 2, fy + fh // 2
+    
+    # 判定標準：臉部中心點在引導框內
+    return (gx1 < fcx < gx2) and (gy1 < fcy < gy2)
 
 def _pick_face_by_tracking(faces, prev_bbox):
     if not faces: return None, None
@@ -137,39 +152,33 @@ def _pick_face_by_tracking(faces, prev_bbox):
         x, y, w, h = fa.get("x",0), fa.get("y",0), fa.get("w",0), fa.get("h",0)
         if w > 0 and h > 0: cand.append((f, (x, y, w, h), w * h))
     if not cand: return None, None
-    if prev_bbox:
-        best = max(cand, key=lambda c: _iou(prev_bbox, c[1]), default=(None, None, 0))
-        if best[0] and _iou(prev_bbox, best[1]) >= IOU_TH: return best[0], best[1]
     return sorted(cand, key=lambda x: x[2], reverse=True)[0][:2]
 
 # =========================
 # Camera streaming
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
-    if frame_rgb is None:
+    if frame_rgb is None or st.finished or (not st.running):
         return (None, gr.update(), gr.update(), gr.update(), st, gr.update())
 
-    # 如果已經結束，回傳空影像讓攝像頭不再更新
-    if st.finished or (not st.running):
-        return (None, gr.update(), gr.update(), gr.update(), st, gr.update())
-
-    # 1. 處理影像
+    # 1. 數位變焦
     frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
     now = time.time()
     
-    # 2. 快速檢測人臉 (每一幀都跑，確保框框顏色反應即時)
-    small_check = _downsample_rgb(frame_rgb, 400) # 用更小的圖加快速度
+    # 2. 快速人臉檢測 (判斷位置)
+    small_check = _downsample_rgb(frame_rgb, 400)
     faces_check = DeepFace.extract_faces(img_path=small_check, detector_backend="opencv", enforce_detection=False)
-    pick_check, _ = _pick_face_by_tracking(faces_check, st.track_bbox)
-    is_detected = (pick_check is not None)
+    pick_check, bbox_check = _pick_face_by_tracking(faces_check, st.track_bbox)
+    
+    # 3. 檢查人臉是否對準中央框
+    is_aligned = _is_face_in_guide(bbox_check, frame_rgb.shape)
     
-    # 3. 繪製導引框 (這張圖會回傳給 UI)
-    frame_with_box = _draw_ui_overlay(frame_rgb, is_detected)
+    # 4. 繪製導引畫面 (紅/綠框與遮罩)
+    frame_with_ui = _draw_ui_overlay(frame_rgb, is_aligned)
 
-    # 4. 深度辨識邏輯 (每 ANALYZE_EVERY_SEC 秒執行一次)
-    if is_detected and (now - st.last_analyze_t >= ANALYZE_EVERY_SEC):
+    # 5. 分析邏輯 (只有對準時才進行深度分析)
+    if is_aligned and (now - st.last_analyze_t >= ANALYZE_EVERY_SEC):
         st.last_analyze_t = now
-        # 正式分析
         small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
         faces = DeepFace.extract_faces(img_path=small, detector_backend=DETECTOR_BACKEND, enforce_detection=False, align=ALIGN_FACE)
         pick, bbox = _pick_face_by_tracking(faces, st.track_bbox)
@@ -184,9 +193,6 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
             
             if emo_dict:
                 top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
-                top_conf = float(emo_dict[top_key])
-                
-                # EMA & Stable 邏輯
                 keys = list(emo_dict.keys())
                 vec = np.array([float(emo_dict[k]) for k in keys])
                 if st.ema_scores is None: st.ema_scores, st.emo_keys = vec, keys
@@ -195,18 +201,16 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
                 stable_key = st.emo_keys[np.argmax(st.ema_scores)]
                 st.stable_emo = stable_key
                 
-                # 確認穩定度
                 if st.candidate_emo != stable_key:
                     st.candidate_emo, st.candidate_since = stable_key, now
                 elif st.candidate_since and (now - st.candidate_since >= SWITCH_CONFIRM_SEC):
-                    # 完成辨識
-                    st.final_emo, st.final_conf, st.running, st.finished = stable_key, top_conf, False, True
-                    return (frame_with_box, _result_card_html(stable_key, top_conf), _score_radio_value(EMO_TO_SCORE.get(stable_key, 3)), _camera_hint_done(), st, gr.update(value="重新攝影機辨識"))
+                    st.final_emo, st.final_conf, st.running, st.finished = stable_key, float(emo_dict[top_key]), False, True
+                    return (frame_with_ui, _result_card_html(stable_key, st.final_conf), _score_radio_value(EMO_TO_SCORE.get(stable_key, 3)), _camera_hint_done(), st, gr.update(value="重新攝影機辨識"))
 
-    # 持續回傳帶有 UI 框的畫面
+    # 顯示穩定情緒
     show_emo = st.stable_emo or "unknown"
     return (
-        frame_with_box, 
+        frame_with_ui, 
         gr.update(value=_result_card_html(show_emo, st.final_conf)), 
         gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show_emo, 3))), 
         gr.update(value=_camera_hint_before_start()), 
@@ -230,8 +234,6 @@ with gr.Blocks(title="Emotion Detector") as demo:
     state = gr.State(AppState())
     gr.Markdown("## 情緒辨識系統")
     hint = gr.HTML(_camera_hint_before_start())
-    
-    # 這裡的 cam 元件接收輸出的影像
     cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機預覽")
     
     with gr.Row():
@@ -241,7 +243,6 @@ with gr.Blocks(title="Emotion Detector") as demo:
     result = gr.HTML(_hint_html("等待串流..."))
     mood = gr.Radio(choices=SCORE_CHOICES, value=SCORE_LABELS[3], label="系統判定心情", interactive=False)
 
-    # 串流綁���
     cam.stream(on_stream, [cam, state], [cam, result, mood, hint, state, btn_restart], show_progress="minimal")
     btn_restart.click(on_restart, [state], [cam, result, mood, hint, state, btn_restart])
     btn_stop.click(on_stop, [state], [cam, result, mood, hint, state, btn_restart])