Update emotion.py

emotion.py

@@ -4,685 +4,255 @@ from typing import Optional, Dict, Tuple, List
 
 import gradio as gr
 import numpy as np
-from PIL import Image, ImageDraw
+import cv2
+from PIL import Image
+import mediapipe as mp
+from mediapipe.tasks import python
+from mediapipe.tasks.vision import FaceDetector, FaceDetectorOptions, RunningMode
 
 from deepface import DeepFace
 
-
-# ✅ 避免 css 未定義造成 NameError
-css = ""
-
-
 # =========================
-# 參數（HF Space 建議偏順）
+# 參數與 MediaPipe 初始化
 # =========================
-ANALYZE_EVERY_SEC = 1.4
-DOWNSAMPLE_W = 480
+ANALYZE_EVERY_SEC = 0.6  # MediaPipe 很快，可以稍微縮短間隔
+DOWNSAMPLE_W = 720
 EMA_ALPHA = 0.45
 CONF_TH = 40.0
-SWITCH_CONFIRM_SEC = 2.2
+SWITCH_CONFIRM_SEC = 2.0
 IOU_TH = 0.25
-ZOOM_FACTOR = 1.25
-
-DETECTOR_BACKEND = "opencv"   # Space 上較順
-ALIGN_FACE = True
-
-MIN_FACE_AREA_RATIO = 0.04    # 人臉太小視為沒偵測到
-RECENT_FACE_SEC = 0.25        # ✅ 綠框快取時間：縮短避免空景綠框殘留
-
+ZOOM_FACTOR = 1.3
+
+# MediaPipe 設定
+MODEL_PATH = 'model/blaze_face_short_range.tflite'
+base_options = python.BaseOptions(model_asset_path=MODEL_PATH)
+options = FaceDetectorOptions(
+    base_options=base_options, 
+    running_mode=RunningMode.IMAGE
+)
+# 建立全域偵測器
+mp_detector = FaceDetector.create_from_options(options)
 
 # =========================
-# OpenCV 眼睛驗證（降低背景假臉）
-# =========================
-try:
-    import cv2
-    _HAS_CV2 = True
-    _EYE_CASCADE = cv2.CascadeClassifier(
-        cv2.data.haarcascades + "haarcascade_eye.xml"
-    )
-except Exception:
-    _HAS_CV2 = False
-    _EYE_CASCADE = None
-
-
-def _verify_face_has_eyes(face_rgb_uint8: np.ndarray) -> bool:
-    """
-    用眼睛 HaarCascade 做簡單驗證：
-    - 背景假臉通常偵測不到眼睛
-    - 真臉通常能偵測到 >= 1 個眼睛
-    """
-    if not _HAS_CV2 or _EYE_CASCADE is None:
-        # 沒有 cv2 就不做驗證（維持原行為）
-        return True
-
-    if face_rgb_uint8 is None or face_rgb_uint8.size == 0:
-        return False
-
-    # 影像太小就直接判 False
-    h, w = face_rgb_uint8.shape[:2]
-    if h < 40 or w < 40:
-        return False
-
-    gray = cv2.cvtColor(face_rgb_uint8, cv2.COLOR_RGB2GRAY)
-    gray = cv2.equalizeHist(gray)
-
-    # scaleFactor / minNeighbors 調得偏嚴格 → 更能擋掉背景假臉
-    eyes = _EYE_CASCADE.detectMultiScale(
-        gray,
-        scaleFactor=1.12,
-        minNeighbors=6,
-        minSize=(12, 12),
-    )
-    return len(eyes) >= 1
-
-
-# =========================
-# 情緒中文 + 分數映射
+# 情緒映射與標籤
 # =========================
 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",
+    "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,
+    "angry": 1, "disgust": 1, "fear": 1,
+    "sad": 2, "neutral": 3, "surprise": 4,
+    "happy": 5, "unknown": 3,
 }
 
 SCORE_LABELS = {
-    1: "1（心情差）",
-    2: "2（不太好）",
-    3: "3（普通）",
-    4: "4（不錯）",
-    5: "5（超棒）",
+    1: "1（心情差）", 2: "2（不太好）", 3: "3（普通）",
+    4: "4（不錯）", 5: "5（超棒）",
 }
 SCORE_CHOICES = [SCORE_LABELS[i] for i in [1, 2, 3, 4, 5]]
 
-def _score_radio_value(score: int) -> str:
-    score = int(score)
-    score = min(5, max(1, score))
-    return SCORE_LABELS[score]
-
-
-# =========================
-# 狀態
-# =========================
 @dataclass
 class AppState:
     running: bool = True
     finished: bool = False
     last_analyze_t: float = 0.0
-
     track_bbox: Optional[Tuple[int, int, int, int]] = None
-
     ema_scores: Optional[np.ndarray] = None
     emo_keys: List[str] = field(default_factory=list)
-
     stable_emo: str = "unknown"
     candidate_emo: Optional[str] = None
     candidate_since: Optional[float] = None
-
     final_emo: Optional[str] = None
     final_conf: Optional[float] = None
     final_score: int = 3
 
-    face_ok: bool = False
-    last_face_t: float = 0.0
-    face_in_box: bool = False
-
-
 # =========================
-# UI HTML
+# UI 工具與輔助函式
 # =========================
 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 / 允許」開啟攝影機；"
-        "接著，請按「錄製（Record）」開始。"
-    )
-
-def _camera_hint_done() -> str:
-    return _hint_html("已完成辨識，可按「重���攝影機辨識」再次進行辨識。")
-
-def _camera_hint_stopped() -> str:
-    return _hint_html("已停止辨識。可按「重新攝影機辨識」再試一次。")
+    return f'<div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#000000;">{msg}</div>'
 
 def _result_card_html(emo_key: str, conf: Optional[float]) -> str:
     zh = EMO_ZH.get(emo_key, emo_key)
     score = EMO_TO_SCORE.get(emo_key, 3)
     conf_txt = "" if conf is None else f"{conf:.1f}%"
     score_desc = SCORE_LABELS[score].split("（")[1].rstrip("）")
-
     return f"""
     <div style="border-radius:16px;padding:20px;border:1px solid #E6E6E6;background:#FFFFFF;color:#000000;">
-      <div style="font-size:14px;color:#000000;margin-bottom:8px;">辨識結果</div>
-      <div style="font-size:42px;font-weight:800;line-height:1.1;margin-bottom:14px;color:#000000;">{zh}</div>
-      <div style="font-size:16px;color:#000000;margin-bottom:6px;">心情分數：{score}（{score_desc}）</div>
-      <div style="font-size:14px;color:#000000;">信心值：{conf_txt}</div>
+      <div style="font-size:14px;margin-bottom:8px;">即時辨識結果</div>
+      <div style="font-size:42px;font-weight:800;line-height:1.1;margin-bottom:14px;">{zh}</div>
+      <div style="font-size:16px;margin-bottom:6px;">心情分數：{score}（{score_desc}）</div>
+      <div style="font-size:14px;">信心值：{conf_txt}</div>
     </div>
     """
 
+def _score_radio_value(score: int) -> str:
+    return SCORE_LABELS[min(5, max(1, int(score)))]
 
-# =========================
-# 影像工具
-# =========================
-def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
-    if frame is None:
-        return None
-    h, w = frame.shape[:2]
-    if w <= target_w:
-        return frame
-    scale = target_w / w
-    new_h = max(1, int(h * scale))
-    img = Image.fromarray(frame)
-    img = img.resize((target_w, new_h))
-    return np.array(img)
+def _iou(a, b) -> float:
+    ax, ay, aw, ah = a
+    bx, by, bw, bh = b
+    ix, iy = max(ax, bx), max(ay, by)
+    iw, ih = max(0, min(ax+aw, bx+bw)-ix), max(0, min(ay+ah, by+bh)-iy)
+    area_i = iw * ih
+    if area_i <= 0: return 0.0
+    return area_i / (aw*ah + bw*bh - area_i)
 
 def _zoom_center(frame: np.ndarray, zoom: float) -> np.ndarray:
-    if frame is None or zoom <= 1.0:
-        return frame
+    if frame is None or zoom <= 1.0: return frame
     h, w = frame.shape[:2]
-    new_w = int(w / zoom)
-    new_h = int(h / zoom)
-    start_x = (w - new_w) // 2
-    start_y = (h - new_h) // 2
-    return frame[start_y:start_y + new_h, start_x:start_x + new_w]
-
+    nw, nh = int(w / zoom), int(h / zoom)
+    sx, sy = (w - nw) // 2, (h - nh) // 2
+    return frame[sy:sy+nh, sx:sx+nw]
 
 # =========================
-# 引導框（固定位置）
+# MediaPipe 偵測邏輯
 # =========================
-GUIDE_W_RATIO = 0.60
-GUIDE_H_RATIO = 0.72
-GUIDE_Y_OFFSET = 0.00
-
-def _guide_box_xyxy(frame: np.ndarray) -> Tuple[int, int, int, int]:
+def get_face_mediapipe(frame: np.ndarray, prev_bbox: Optional[Tuple[int, int, int, int]]):
     h, w = frame.shape[:2]
-    gw = int(w * GUIDE_W_RATIO)
-    gh = int(h * GUIDE_H_RATIO)
-    cx = w // 2
-    cy = int(h * (0.5 + GUIDE_Y_OFFSET))
-    x1 = max(0, cx - gw // 2)
-    y1 = max(0, cy - gh // 2)
-    x2 = min(w - 1, cx + gw // 2)
-    y2 = min(h - 1, cy + gh // 2)
-    return x1, y1, x2, y2
-
-def _bbox_center_in_box(bbox_xywh: Tuple[float, float, float, float], box_xyxy: Tuple[int, int, int, int]) -> bool:
-    x, y, w, h = bbox_xywh
-    cx = x + w / 2.0
-    cy = y + h / 2.0
-    x1, y1, x2, y2 = box_xyxy
-    return (x1 <= cx <= x2) and (y1 <= cy <= y2)
-
-def _draw_guide_overlay(frame_rgb: np.ndarray, green: bool, msg: str) -> np.ndarray:
-    img = Image.fromarray(frame_rgb)
-    draw = ImageDraw.Draw(img)
-
-    x1, y1, x2, y2 = _guide_box_xyxy(frame_rgb)
-    color = (0, 200, 0) if green else (220, 0, 0)
-
-    h, w = frame_rgb.shape[:2]
-    thickness = max(3, int(min(w, h) * 0.008))
-
-    for t in range(thickness):
-        draw.rectangle([x1 - t, y1 - t, x2 + t, y2 + t], outline=color)
-
-    tx = x1
-    ty = max(0, y1 - int(thickness * 7))
-    draw.rectangle([tx, ty, min(w - 1, tx + 520), ty + 34], fill=(255, 255, 255))
-    draw.text((tx + 8, ty + 7), msg, fill=(0, 0, 0))
-
-    return np.array(img)
-
-
-# =========================
-# Tracking / IoU
-# =========================
-def _iou(a: Tuple[int, int, int, int], b: Tuple[int, int, int, int]) -> float:
-    ax, ay, aw, ah = a
-    bx, by, bw, bh = b
-    ax2, ay2 = ax + aw, ay + ah
-    bx2, by2 = bx + bw, by + bh
-
-    ix1, iy1 = max(ax, bx), max(ay, by)
-    ix2, iy2 = min(ax2, bx2), min(ay2, by2)
-    iw, ih = max(0, ix2 - ix1), max(0, iy2 - iy1)
-    inter = iw * ih
-    if inter <= 0:
-        return 0.0
-    union = aw * ah + bw * bh - inter
-    return inter / max(1e-6, union)
-
-def _pick_face_by_tracking(
-    faces: List[Dict],
-    prev_bbox: Optional[Tuple[int, int, int, int]]
-):
-    if not faces:
+    mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=frame)
+    res = mp_detector.detect(mp_image)
+    
+    if not res.detections:
         return None, None
 
-    cand = []
-    for f in faces:
-        fa = f.get("facial_area", {}) or {}
-        x = int(fa.get("x", 0) or 0)
-        y = int(fa.get("y", 0) or 0)
-        w = int(fa.get("w", 0) or 0)
-        h = int(fa.get("h", 0) or 0)
-        if w > 0 and h > 0 and f.get("face") is not None:
-            cand.append((f, (x, y, w, h), w * h))
-
-    if not cand:
+    candidates = []
+    for det in res.detections:
+        b = det.bounding_box
+        # 數值校正，避免超出邊界導致 DeepFace 報錯
+        nx, ny = max(0, b.origin_x), max(0, b.origin_y)
+        nw, nh = min(b.width, w - nx), min(b.height, h - ny)
+        if nw > 10 and nh > 10:
+            candidates.append(((nx, ny, nw, nh), frame[ny:ny+nh, nx:nx+nw]))
+
+    if not candidates:
         return None, None
 
-    if prev_bbox is not None:
-        best = None
-        best_i = 0.0
-        for f, bb, area in cand:
-            i = _iou(prev_bbox, bb)
-            if i > best_i:
-                best_i = i
-                best = (f, bb)
-        if best is not None and best_i >= IOU_TH:
-            return best[0], best[1]
-
-    cand.sort(key=lambda x: x[2], reverse=True)
-    return cand[0][0], cand[0][1]
-
-
-def _reset_state_for_camera(st: AppState) -> AppState:
-    st.running = True
-    st.finished = False
-    st.last_analyze_t = 0.0
-    st.track_bbox = None
-    st.ema_scores = None
-    st.emo_keys = []
-    st.stable_emo = "unknown"
-    st.candidate_emo = None
-    st.candidate_since = None
-    st.final_emo = None
-    st.final_conf = None
-    st.final_score = 3
-    st.face_ok = False
-    st.last_face_t = 0.0
-    st.face_in_box = False
-    return st
-
-
-def _is_face_big_enough(bbox_xywh: Tuple[float, float, float, float], frame_hw: Tuple[int, int]) -> bool:
-    fh, fw = frame_hw
-    x, y, w, h = bbox_xywh
-    area_ratio = (w * h) / max(1.0, float(fw * fh))
-    return area_ratio >= MIN_FACE_AREA_RATIO
+    # 優先匹配上一幀的位置
+    if prev_bbox:
+        best_match = max(candidates, key=lambda c: _iou(prev_bbox, c[0]), default=(None, None))
+        if best_match[0] and _iou(prev_bbox, best_match[0]) > IOU_TH:
+            return best_match
 
+    # 否則回傳面積最大者
+    return max(candidates, key=lambda c: c[0][2] * c[0][3])
 
 # =========================
-# Camera streaming（含紅/綠框 + 眼睛驗證）
+# Gradio 事件處理
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
-    if st.finished or (not st.running):
-        cam_visible = False
-        if st.final_emo:
-            return (
-                gr.update(visible=cam_visible),
-                gr.update(value=_result_card_html(st.final_emo, st.final_conf)),
-                gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))),
-                gr.update(value=_camera_hint_done()),
-                st,
-                gr.update(value="重新攝影機辨識"),
-            )
-        return (
-            gr.update(visible=cam_visible),
-            gr.update(value=_hint_html("尚未完成辨識。")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_stopped()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
+    if not st.running or st.finished:
+        res_html = _result_card_html(st.final_emo, st.final_conf) if st.final_emo else _hint_html("辨識停止")
+        return gr.update(visible=False), res_html, _score_radio_value(st.final_score), _hint_html("已完成"), st, gr.update()
 
     if frame_rgb is None:
-        return (
-            gr.update(visible=True, value=None),
-            gr.update(value=_hint_html("等待影像…（尚未開始串流）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
+        return gr.update(), gr.update(), gr.update(), _hint_html("等待攝影機..."), st, gr.update()
 
     frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
     now = time.time()
-
-    # ✅ 快取只留很短時間（避免空景也綠）
-    recent_face = st.face_ok and st.face_in_box and (now - st.last_face_t) < RECENT_FACE_SEC
-    msg_fast = "已偵測到人臉，開始辨識情緒中…" if recent_face else "未偵測到人臉，請把臉放進框內"
-    annotated_fast = _draw_guide_overlay(frame_rgb, green=recent_face, msg=msg_fast)
-
+    
+    # 頻率控制
     if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
-        if recent_face:
-            show = st.stable_emo or "unknown"
-            result_html = _result_card_html(show, st.final_conf)
-            mood_val = _score_radio_value(EMO_TO_SCORE.get(show, 3))
-        else:
-            result_html = _hint_html("未偵測到人臉，請把臉放進框內（紅框）")
-            mood_val = _score_radio_value(3)
-
-        return (
-            gr.update(visible=True, value=annotated_fast),
-            gr.update(value=result_html),
-            gr.update(value=mood_val),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
+        return gr.update(), gr.update(), gr.update(), gr.update(), st, gr.update()
+    
     st.last_analyze_t = now
-    small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
 
-    try:
-        faces = DeepFace.extract_faces(
-            img_path=small,
-            detector_backend=DETECTOR_BACKEND,
-            enforce_detection=False,
-            align=ALIGN_FACE,
-        )
-    except Exception:
-        faces = []
-
-    pick, bbox = _pick_face_by_tracking(faces, st.track_bbox)
-
-    # 沒臉
-    if pick is None or bbox is None or pick.get("face") is None:
-        st.track_bbox = None
-        st.face_ok = False
-        st.face_in_box = False
-        st.last_face_t = now
-        st.stable_emo = "unknown"   # ✅ 清掉殘留情緒
-
-        annotated = _draw_guide_overlay(frame_rgb, green=False, msg="未偵測到人臉，請把臉放進框內")
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("未偵測到人臉，請把臉放進框內（紅框）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    # bbox small -> full
-    sh, sw = small.shape[:2]
-    fh, fw = frame_rgb.shape[:2]
-    sx = fw / max(1, sw)
-    sy = fh / max(1, sh)
-    x, y, w, h = bbox
-    bbox_full = (x * sx, y * sy, w * sx, h * sy)
-
-    # 太小
-    if not _is_face_big_enough(bbox_full, (fh, fw)):
-        st.track_bbox = None
-        st.face_ok = False
-        st.face_in_box = False
-        st.last_face_t = now
-        st.stable_emo = "unknown"
-
-        annotated = _draw_guide_overlay(frame_rgb, green=False, msg="人臉太小/太遠，請靠近鏡頭並放進框內")
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("人臉太小/太遠，請靠近鏡頭並放進框內（紅框）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    guide = _guide_box_xyxy(frame_rgb)
-    in_box = _bbox_center_in_box(bbox_full, guide)
+    # 使用 MediaPipe 找臉
+    bbox, face_crop = get_face_mediapipe(frame_rgb, st.track_bbox)
+    
+    if face_crop is None:
+        return gr.update(), gr.update(), gr.update(), _hint_html("未偵測到人臉"), st, gr.update()
 
     st.track_bbox = bbox
-    st.last_face_t = now
-    st.face_ok = True
-    st.face_in_box = in_box
-
-    if not in_box:
-        st.stable_emo = "unknown"
-        annotated = _draw_guide_overlay(frame_rgb, green=False, msg="已偵測到人臉，請把臉移到框內")
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，但請把臉移到框內（紅框）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    # ✅ 眼睛驗證（關鍵）
-    face = pick["face"]
-    if face.dtype != np.uint8:
-        face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
-
-    if not _verify_face_has_eyes(face):
-        # 當作沒臉：避免背景假臉
-        st.track_bbox = None
-        st.face_ok = False
-        st.face_in_box = False
-        st.last_face_t = now
-        st.stable_emo = "unknown"
-
-        annotated = _draw_guide_overlay(frame_rgb, green=False, msg="未偵測到真實人臉（找不到眼睛），請對準鏡頭")
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("未偵測到真實人臉（找不到眼睛），請把臉放進框內（紅框）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    # ✅ 到這裡才算「真的有人臉」→ 綠框 + 情緒分析
-    annotated = _draw_guide_overlay(frame_rgb, green=True, msg="已偵測到人臉，開始辨識情緒中…")
 
+    # DeepFace 情緒分析 (傳入已裁切的人臉)
     try:
-        result = DeepFace.analyze(
-            img_path=face,
-            actions=["emotion"],
-            enforce_detection=False,
-        )
-    except Exception:
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，辨識中…（分析暫時失敗，請保持正面/光線亮一點）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    if isinstance(result, list):
-        result = result[0]
-    emo_dict = result.get("emotion", None)
-
-    if not isinstance(emo_dict, dict) or len(emo_dict) == 0:
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，辨識中…")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
+        res = DeepFace.analyze(face_crop, actions=['emotion'], enforce_detection=False, silent=True)
+        emo_dict = res[0]['emotion'] if isinstance(res, list) else res['emotion']
+    except:
+        return gr.update(), gr.update(), gr.update(), gr.update(), st, gr.update()
 
     top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
     top_conf = float(emo_dict[top_key])
 
-    if top_conf < CONF_TH:
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，辨識中…（信心偏低，請面向鏡頭/光線亮一點）")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    keys = list(emo_dict.keys())
-    vec = np.array([float(emo_dict[k]) for k in keys], dtype=np.float32)
-
-    if st.ema_scores is None or st.emo_keys != keys:
-        st.ema_scores = vec
-        st.emo_keys = keys
-    else:
-        st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
-
-    stable_idx = int(np.argmax(st.ema_scores))
-    stable_key = st.emo_keys[stable_idx]
-    st.stable_emo = stable_key
-
-    if st.candidate_emo != stable_key:
-        st.candidate_emo = stable_key
-        st.candidate_since = now
-    else:
-        if st.candidate_since is None:
-            st.candidate_since = now
-
-    confirmed = (
-        st.candidate_since is not None
-        and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC
-    )
-
-    if confirmed and st.final_emo is None:
-        st.final_emo = stable_key
-        st.final_conf = top_conf
-        st.final_score = EMO_TO_SCORE.get(stable_key, 3)
-        st.running = False
-        st.finished = True
-
-        return (
-            gr.update(visible=False, value=None),
-            gr.update(value=_result_card_html(stable_key, top_conf)),
-            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))),
-            gr.update(value=_camera_hint_done()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
+    # 平滑處理 (EMA)
+    if top_conf >= CONF_TH:
+        keys = list(emo_dict.keys())
+        vals = np.array([float(emo_dict[k]) for k in keys])
+        if st.ema_scores is None or st.emo_keys != keys:
+            st.ema_scores, st.emo_keys = vals, keys
+        else:
+            st.ema_scores = EMA_ALPHA * vals + (1.0 - EMA_ALPHA) * st.ema_scores
+        
+        st.stable_emo = st.emo_keys[int(np.argmax(st.ema_scores))]
+
+        # 穩定切換邏輯
+        if st.candidate_emo != st.stable_emo:
+            st.candidate_emo, st.candidate_since = st.stable_emo, now
+        elif st.candidate_since and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC:
+            st.final_emo, st.final_conf = st.stable_emo, top_conf
+            st.final_score = EMO_TO_SCORE.get(st.stable_emo, 3)
+            st.finished, st.running = True, False
 
     return (
-        gr.update(visible=True, value=annotated),
-        gr.update(value=_result_card_html(stable_key, top_conf)),
-        gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))),
-        gr.update(value=_camera_hint_before_start()),
+        gr.update(visible=not st.finished),
+        gr.update(value=_result_card_html(st.stable_emo, top_conf)),
+        gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.stable_emo, 3))),
+        gr.update(value=_hint_html("正在辨識中，請保持表情穩定...")),
         st,
-        gr.update(value="重新攝影機辨識"),
+        gr.update()
     )
 
-
-# =========================
-# Buttons
-# =========================
 def on_restart(st: AppState):
-    st = _reset_state_for_camera(st)
+    new_st = AppState()
     return (
-        gr.update(visible=True, value=None),
-        gr.update(value=_hint_html("等待影像…（尚未開始串流）")),
-        gr.update(value=_score_radio_value(3)),
-        gr.update(value=_camera_hint_before_start()),
-        st,
-        gr.update(value="重新攝影機辨識"),
+        gr.update(visible=True),
+        _hint_html("等待影像..."),
+        _score_radio_value(3),
+        _hint_html("請點擊 Record 開始"),
+        new_st,
+        gr.update()
     )
 
 def on_stop(st: AppState):
-    st.running = False
-    st.finished = True
-    if st.final_emo is None:
-        return (
-            gr.update(visible=False, value=None),
-            gr.update(value=_hint_html("已停止辨識。")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_stopped()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    return (
-        gr.update(visible=False, value=None),
-        gr.update(value=_result_card_html(st.final_emo, st.final_conf)),
-        gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))),
-        gr.update(value=_camera_hint_done()),
-        st,
-        gr.update(value="重新攝影機辨識"),
-    )
-
+    st.running, st.finished = False, True
+    return gr.update(visible=False), gr.update(), gr.update(), _hint_html("已手動停止"), st, gr.update()
 
 # =========================
-# Gradio UI
+# Gradio UI 介面
 # =========================
+css = ".gradio-container { background-color: #f7f9fc; }"
+
+with gr.Blocks(title="AI 情緒偵測系統", css=css) as demo:
+    state = gr.State(AppState())
+    
+    gr.Markdown("# 🎭 AI 情緒辨識評分系統")
+    status_hint = gr.HTML(_hint_html("請開啟攝影機並點擊錄製"))
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            webcam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機畫面")
+            with gr.Row():
+                btn_re = gr.Button("🔄 重新辨識", variant="primary")
+                btn_stop = gr.Button("🛑 停止", variant="secondary")
+        
+        with gr.Column(scale=1):
+            res_display = gr.HTML(_result_card_html("unknown", 0))
+            gr.Markdown("### 系統判定心情分數")
+            mood_radio = gr.Radio(choices=SCORE_CHOICES, value=SCORE_LABELS[3], interactive=False, label="")
+
+    # 事件綁定
+    webcam.stream(
+        fn=on_stream,
+        inputs=[webcam, state],
+        outputs=[webcam, res_display, mood_radio, status_hint, state, btn_re]
+    )
+    
+    btn_re.click(fn=on_restart, inputs=[state], outputs=[webcam, res_display, mood_radio, status_hint, state, btn_re])
+    btn_stop.click(fn=on_stop, inputs=[state], outputs=[webcam, res_display, mood_radio, status_hint, state, btn_re])
+
 if __name__ == "__main__":
-    with gr.Blocks(title="Emotion Detector", css=css) as demo:
-        st = gr.State(AppState())
-
-        gr.Markdown("## 第一步：測測你的心情能量")
-        gr.Markdown("讓 AI 看看你的表情，自動幫你決定心情分數！（辨識完畢會自動跳轉）")
-
-        hint = gr.HTML(_camera_hint_before_start())
-
-        cam = gr.Image(
-            sources=["webcam"],
-            streaming=True,
-            type="numpy",
-            label="攝影機畫面",
-            visible=True,
-        )
-
-        with gr.Row():
-            btn_restart = gr.Button("重新攝影機辨識", variant="primary")
-            btn_stop = gr.Button("停止", variant="secondary")
-
-        gr.Markdown("### 辨識結果")
-        result = gr.HTML(_hint_html("等待影像…（尚未開始串流）"))
-
-        gr.Markdown("### 心情分數（系統判定）")
-        mood = gr.Radio(
-            choices=SCORE_CHOICES,
-            value=_score_radio_value(3),
-            label="心情分數",
-            interactive=False,
-        )
-
-        cam.stream(
-            fn=on_stream,
-            inputs=[cam, st],
-            outputs=[cam, result, mood, hint, st, btn_restart],
-            show_progress="minimal",
-        )
-
-        btn_restart.click(
-            fn=on_restart,
-            inputs=[st],
-            outputs=[cam, result, mood, hint, st, btn_restart],
-            show_progress="minimal",
-        )
-
-        btn_stop.click(
-            fn=on_stop,
-            inputs=[st],
-            outputs=[cam, result, mood, hint, st, btn_restart],
-            show_progress="minimal",
-        )
-
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
+    demo.launch(server_name="0.0.0.0", server_port=7860)