Update emotion.py

emotion.py

@@ -4,28 +4,36 @@ from typing import Optional, Dict, Tuple, List
 
 import gradio as gr
 import numpy as np
-from PIL import Image
+from PIL import Image, ImageDraw
 
 from deepface import DeepFace
 
 
+# ✅ 避免 css 未定義造成 NameError
+css = ""
+
+
 # =========================
-# 參數（可微調）
+# 參數（HF Space 建議偏順）
 # =========================
-ANALYZE_EVERY_SEC = 0.8
-DOWNSAMPLE_W = 720
+ANALYZE_EVERY_SEC = 1.4    # 越大越順（Space 建議 1.2~2.0）
+DOWNSAMPLE_W = 480         # 越小越順（360/480）
 EMA_ALPHA = 0.45
 CONF_TH = 40.0
-SWITCH_CONFIRM_SEC = 2.5
+SWITCH_CONFIRM_SEC = 2.2   # 穩定多久才定案（秒）
 IOU_TH = 0.25
-ZOOM_FACTOR = 1.5
+ZOOM_FACTOR = 1.25         # 太大會失真且更慢，Space 建議 <= 1.25
 
-DETECTOR_BACKEND = "mtcnn"     # 想快一點可改 "opencv"
+# ✅ 快很多：opencv（比 mtcnn 順非常多）
+DETECTOR_BACKEND = "opencv"
 ALIGN_FACE = True
 
+# ✅ 防誤判（太小的人臉當作沒臉）
+MIN_FACE_AREA_RATIO = 0.04  # 4%（可調 0.03~0.06）
+
 
 # =========================
-# 情緒中文 + 分數映射（7 -> 5）
+# 情緒中文 + 分數映射
 # =========================
 EMO_ZH = {
     "angry": "生氣",
@@ -38,7 +46,6 @@ EMO_ZH = {
     "unknown": "未知",
 }
 
-# 你要的：把 7 種情緒塞進 5 分心情分數
 EMO_TO_SCORE = {
     "angry": 1,
     "disgust": 1,
@@ -50,9 +57,6 @@ EMO_TO_SCORE = {
     "unknown": 3,
 }
 
-def get_emotion_score(emo: str) -> int:
-    return EMO_TO_SCORE.get(emo, 3)
-
 SCORE_LABELS = {
     1: "1（心情差）",
     2: "2（不太好）",
@@ -62,14 +66,17 @@ SCORE_LABELS = {
 }
 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:
-    mode: str = "攝影機辨識" 
-
     running: bool = True
     finished: bool = False
     last_analyze_t: float = 0.0
@@ -89,80 +96,55 @@ class AppState:
     # final
     final_emo: Optional[str] = None
     final_conf: Optional[float] = None
+    final_score: int = 3
 
-    final_score: int = 3  
+    # face status for overlay
+    face_ok: bool = False
+    last_face_t: float = 0.0
+    face_in_box: bool = False
 
 
 # =========================
-# UI HTML (強制黑色文字)
+# UI HTML
 # =========================
 def _hint_html(msg: str) -> str:
-    # 加入 color:#000000 強制黑色
     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「重新攝影機辨識」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。")
 
-
 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("）")
 
-    # ✅ 強制設定 color: #000000
     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="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>
     """
 
 
-def _score_radio_value(score: int) -> str:
-    score = int(score)
-    score = min(5, max(1, score))
-    return SCORE_LABELS[score]
-
-
+# =========================
+# 影像工具
+# =========================
 def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
     if frame is None:
         return None
@@ -176,28 +158,67 @@ def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
     return np.array(img)
 
 def _zoom_center(frame: np.ndarray, zoom: float) -> np.ndarray:
-    """
-    裁切畫面中心以模擬數位變焦。
-    zoom: 放大倍率 (例如 1.5)
-    """
     if frame is None or zoom <= 1.0:
         return frame
-        
     h, w = frame.shape[:2]
-    
-    # 計算新的寬高
     new_w = int(w / zoom)
     new_h = int(h / zoom)
-    
-    # 計算起始點 (讓裁切框置中)
     start_x = (w - new_w) // 2
     start_y = (h - new_h) // 2
-    
-    # 進行裁切
-    cropped = frame[start_y : start_y + new_h, start_x : start_x + new_w]
-    return cropped
+    return frame[start_y:start_y + new_h, start_x:start_x + new_w]
 
 
+# =========================
+# 引導框（固定位置）
+# =========================
+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]:
+    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)
+
+    # 提示文字底條
+    tx = x1
+    ty = max(0, y1 - int(thickness * 7))
+    draw.rectangle([tx, ty, min(w - 1, tx + 420), 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
@@ -213,11 +234,10 @@ def _iou(a: Tuple[int, int, int, int], b: Tuple[int, int, int, int]) -> float:
     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]]
-) -> Tuple[Optional[Dict], Optional[Tuple[int, int, int, int]]]:
+):
     if not faces:
         return None, None
 
@@ -262,102 +282,194 @@ def _reset_state_for_camera(st: AppState) -> AppState:
     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
+
+
 # =========================
-# Camera streaming
+# Camera streaming (含紅/綠框)
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
+    # 已結束/停止
     if st.finished or (not st.running):
         cam_visible = False
-
         if st.final_emo:
-            result_html = _result_card_html(st.final_emo, st.final_conf)
-            mood_val = _score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))
-            hint_html = _camera_hint_done()
-        else:
-            result_html = _hint_html("尚未完成辨識。")
-            mood_val = _score_radio_value(3)
-            hint_html = _camera_hint_stopped()
-
+            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=result_html),
-            gr.update(value=mood_val),
-            gr.update(value=hint_html),
+            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"),
         )
 
+    # 尚未開始串流
     if frame_rgb is None:
         return (
-            gr.update(visible=True),
+            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"),
         )
-    
-    frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
 
+    # zoom（提升臉部比例）
+    frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
     now = time.time()
+
+    # ✅ 先畫一張「即時框」：用最近一次人臉狀態（避免每幀都做重運算）
+    recent_face = st.face_ok and (now - st.last_face_t) < 1.2
+    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)
+
+    # 沒到分析時間 → 直接回傳快速版本（順）
     if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
-        show = st.stable_emo or "unknown"
+        # 沒臉時不要顯示任何情緒卡（避免誤導）
+        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),
-            gr.update(value=_result_card_html(show, st.final_conf)),
-            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
+            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"),
         )
 
+    # 到分析時間 → 做一次偵測/分析
     st.last_analyze_t = now
-
     small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
 
-    # ✅ 這裡固定 enforce_detection=False（避免沒臉就丟例外，造成卡頓/誤判）
-    faces = DeepFace.extract_faces(
-        img_path=small,
-        detector_backend=DETECTOR_BACKEND,
-        enforce_detection=False,
-        align=ALIGN_FACE,
-    )
+    # ✅ enforce_detection=False：沒有臉不丟例外（更順）
+    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：紅框 + 不跑情緒
     if pick is None or bbox is None or pick.get("face") is None:
-        show = st.stable_emo or "unknown"
+        st.track_bbox = None
+        st.face_ok = False
+        st.face_in_box = False
+        st.last_face_t = now
+
+        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"),
+        )
+
+    # 把 bbox 從 small 映射回原 frame
+    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：當作沒臉（紅框）
+    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
+        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),
-            gr.update(value=_result_card_html(show, st.final_conf)),
-            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
+            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"),
         )
 
+    # 檢查臉是否在引導框內：不在就紅框，不跑情緒
+    guide = _guide_box_xyxy(frame_rgb)
+    in_box = _bbox_center_in_box(bbox_full, guide)
+
     st.track_bbox = bbox
+    st.last_face_t = now
+    st.face_ok = True
+    st.face_in_box = in_box
+
+    if not in_box:
+        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"),
+        )
+
+    # ✅ 有臉且在框內：綠框，開始情緒分析
     face = pick["face"]
     if face.dtype != np.uint8:
         face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
 
-    # ✅ 這裡也固定 enforce_detection=False（避免偶發抓不到臉時丟例外）
-    result = DeepFace.analyze(
-        img_path=face,
-        actions=["emotion"],
-        enforce_detection=False,
-    )
+    try:
+        result = DeepFace.analyze(
+            img_path=face,
+            actions=["emotion"],
+            enforce_detection=False,   # ✅ 避免偶發例外造成卡頓
+        )
+    except Exception:
+        annotated = _draw_guide_overlay(frame_rgb, green=True, msg="已偵測到人臉，辨識中…（分析暫時失敗）")
+        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:
-        show = st.stable_emo or "unknown"
+        annotated = _draw_guide_overlay(frame_rgb, green=True, msg="已偵測到人臉，辨識中…")
         return (
-            gr.update(visible=True),
-            gr.update(value=_result_card_html(show, st.final_conf)),
-            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
+            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"),
@@ -367,16 +479,17 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
     top_conf = float(emo_dict[top_key])
 
     if top_conf < CONF_TH:
-        show = st.stable_emo or "unknown"
+        annotated = _draw_guide_overlay(frame_rgb, green=True, msg="已偵測到人臉，辨識中…（信心偏低）")
         return (
-            gr.update(visible=True),
-            gr.update(value=_result_card_html(show, st.final_conf)),
-            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
+            gr.update(visible=True, value=annotated),
+            gr.update(value=_hint_html("已偵測到人臉，辨識中…（信心值偏低，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"),
         )
 
+    # smoothing
     keys = list(emo_dict.keys())
     vec = np.array([float(emo_dict[k]) for k in keys], dtype=np.float32)
 
@@ -390,7 +503,7 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
     stable_key = st.emo_keys[stable_idx]
     st.stable_emo = stable_key
 
-    # 延遲確認
+    # 延遲確認（避免跳來跳去）
     if st.candidate_emo != stable_key:
         st.candidate_emo = stable_key
         st.candidate_since = now
@@ -403,6 +516,8 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
         and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC
     )
 
+    annotated = _draw_guide_overlay(frame_rgb, green=True, msg="已偵測到人臉，開始辨識情緒中…")
+
     if confirmed and st.final_emo is None:
         st.final_emo = stable_key
         st.final_conf = top_conf
@@ -412,7 +527,7 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
         st.finished = True
 
         return (
-            gr.update(visible=False),
+            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()),
@@ -421,7 +536,7 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
         )
 
     return (
-        gr.update(visible=True),
+        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()),
@@ -431,26 +546,26 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
 
 
 # =========================
-# Mode / Buttons
+# Buttons
 # =========================
 def on_restart(st: AppState):
     st = _reset_state_for_camera(st)
+    # ✅ 清掉上一張，避免殘影
     return (
-        gr.update(visible=True),                               
-        gr.update(value=_hint_html("等待影像…（尚未開���串流）")),  
-        gr.update(value=_score_radio_value(3)),                
-        gr.update(value=_camera_hint_before_start()),          
+        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(value="重新攝影機辨識"),
     )
 
-
 def on_stop(st: AppState):
     st.running = False
     st.finished = True
     if st.final_emo is None:
         return (
-            gr.update(visible=False),
+            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()),
@@ -459,7 +574,7 @@ def on_stop(st: AppState):
         )
 
     return (
-        gr.update(visible=False),
+        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()),
@@ -475,15 +590,16 @@ if __name__ == "__main__":
     with gr.Blocks(title="Emotion Detector", css=css) as demo:
         st = gr.State(AppState())
 
-        gr.Markdown("## 情緒辨識")
-        
+        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",
+            label="攝影機畫面",
             visible=True,
         )