Update emotion.py

emotion.py

@@ -1,14 +1,12 @@
 import time
+import cv2  # 新增：用於繪圖
 from dataclasses import dataclass, field
 from typing import Optional, Dict, Tuple, List
-
 import gradio as gr
 import numpy as np
 from PIL import Image
-
 from deepface import DeepFace
 
-
 # =========================
 # 參數（可微調）
 # =========================
@@ -18,14 +16,12 @@ EMA_ALPHA = 0.45
 CONF_TH = 40.0
 SWITCH_CONFIRM_SEC = 2.5
 IOU_TH = 0.25
-ZOOM_FACTOR = 1.5
-
-DETECTOR_BACKEND = "mtcnn"     # 想快一點可改 "opencv"
+ZOOM_FACTOR = 1.3  # 微調縮放倍率
+DETECTOR_BACKEND = "mtcnn"     
 ALIGN_FACE = True
 
-
 # =========================
-# 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 +34,6 @@ 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 +45,6 @@ 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）",
@@ -62,116 +54,65 @@ SCORE_LABELS = {
 }
 SCORE_CHOICES = [SCORE_LABELS[i] for i in [1, 2, 3, 4, 5]]
 
-
 # =========================
 # 狀態
 # =========================
 @dataclass
 class AppState:
-    mode: str = "攝影機辨識" 
-
+    mode: str = "攝影機辨識"
     running: bool = True
     finished: bool = False
     last_analyze_t: float = 0.0
-
-    # tracking
     track_bbox: Optional[Tuple[int, int, int, int]] = None
-
-    # smoothing
     ema_scores: Optional[np.ndarray] = None
     emo_keys: List[str] = field(default_factory=list)
-
-    # stable/candidate
     stable_emo: str = "unknown"
     candidate_emo: Optional[str] = None
     candidate_since: Optional[float] = None
-
-    # final
     final_emo: Optional[str] = None
     final_conf: Optional[float] = None
-
-    final_score: int = 3  
-
+    final_score: int = 3
 
 # =========================
-# UI HTML (強制黑色文字)
+# 輔助函式
 # =========================
 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。"
-    )
-
+    return _hint_html("請先按「Click to access webcam」開啟攝影機；接著，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。")
-
+    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。可按「重新攝影機辨識」再試一次。")
-
+    return _hint_html("已停止辨識。")
 
 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;margin-bottom:8px;">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:
-    score = int(score)
-    score = min(5, max(1, score))
-    return SCORE_LABELS[score]
-
+    return SCORE_LABELS[min(5, max(1, int(score)))]
 
 def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
-    if frame is None:
-        return None
+    if frame is None: return None
     h, w = frame.shape[:2]
-    if w <= target_w:
-        return frame
+    if w <= target_w: return frame
     scale = target_w / w
     new_h = max(1, int(h * scale))
     img = Image.fromarray(frame)
@@ -179,351 +120,168 @@ 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
-        
+    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
-
+    new_w, new_h = int(w / zoom), int(h / zoom)
+    start_x, start_y = (w - new_w) // 2, (h - new_h) // 2
+    return frame[start_y : start_y + new_h, start_x : start_x + new_w]
 
 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)
+    ax2, ay2, bx2, by2 = ax+aw, ay+ah, bx+bw, by+bh
+    ix1, iy1, ix2, iy2 = max(ax, bx), max(ay, by), 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]]
-) -> Tuple[Optional[Dict], Optional[Tuple[int, int, int, int]]]:
-    if not faces:
-        return None, None
+    if inter <= 0: return 0.0
+    return inter / (aw * ah + bw * bh - inter)
 
+def _pick_face_by_tracking(faces: List[Dict], prev_bbox: Optional[Tuple[int, int, int, int]]):
+    if not faces: 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)
+        fa = f.get("facial_area", {})
+        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 and f.get("face") is not None:
             cand.append((f, (x, y, w, h), w * h))
-
-    if not cand:
-        return None, None
-
-    if prev_bbox is not None:
-        best = None
-        best_i = 0.0
+    if not cand: return None, None
+    if prev_bbox:
+        best, best_i = None, 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]
-
+            if i > best_i: best_i, best = i, (f, bb)
+        if best and best_i >= IOU_TH: return best
     cand.sort(key=lambda x: x[2], reverse=True)
     return cand[0][0], cand[0][1]
 
+def _draw_guide_box(frame: np.ndarray, is_detected: bool):
+    """ 在影像上繪製導引框（紅框/綠框） """
+    h, w = frame.shape[:2]
+    # 建立一個佔畫面中間 50% 的框
+    bw, bh = int(w * 0.5), int(h * 0.6)
+    x1, y1 = (w - bw) // 2, (h - bh) // 2
+    x2, y2 = x1 + bw, y1 + bh
+    
+    # 顏色 (RGB): 綠色表示偵測中，紅色表示未對準
+    color = (0, 255, 0) if is_detected else (255, 0, 0)
+    label = "Scanning..." if is_detected else "Please align your face"
+    
+    # 繪製矩形與文字
+    cv2.rectangle(frame, (x1, y1), (x2, y2), color, 3)
+    cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, color, 2)
+    return frame
 
 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.running, st.finished, st.last_analyze_t = True, False, 0.0
+    st.track_bbox, st.ema_scores, st.emo_keys = None, None, []
+    st.stable_emo, st.candidate_emo, st.candidate_since = "unknown", None, None
+    st.final_emo, st.final_conf, st.final_score = None, None, 3
     return st
 
-
 # =========================
 # Camera streaming
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
-    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_html),
-            gr.update(value=mood_val),
-            gr.update(value=hint_html),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
     if frame_rgb is None:
-        return (
-            gr.update(visible=True),
-            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)
+        return (None, gr.update(), gr.update(), gr.update(), st, gr.update())
 
-    now = time.time()
-    if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
-        show = st.stable_emo or "unknown"
-        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(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    st.last_analyze_t = now
+    if st.finished or (not st.running):
+        # 結束時顯示結果，隱藏攝像頭
+        result_html = _result_card_html(st.final_emo, st.final_conf) if st.final_emo else _hint_html("已停止")
+        mood_val = _score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3)) if st.final_emo else _score_radio_value(3)
+        return (None, gr.update(value=result_html), gr.update(value=mood_val), gr.update(value=_camera_hint_done()), st, gr.update(value="重新攝影機辨識"))
 
+    # 1. 數位變焦
+    frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
+    
+    # 2. 為了畫框，進行快速人臉檢查
     small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
-
-    faces = DeepFace.extract_faces(
-        img_path=small,
-        detector_backend=DETECTOR_BACKEND,
-        enforce_detection=False,
-        align=ALIGN_FACE,
-    )
+    faces = DeepFace.extract_faces(img_path=small, detector_backend="opencv", enforce_detection=False, align=False)
     pick, bbox = _pick_face_by_tracking(faces, st.track_bbox)
-    if pick is None or bbox is None or pick.get("face") is None:
-        show = st.stable_emo or "unknown"
-        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(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    st.track_bbox = bbox
-    face = pick["face"]
-    if face.dtype != np.uint8:
-        face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
-
-    result = DeepFace.analyze(
-        img_path=face,
-        actions=["emotion"],
-        enforce_detection=False,
-    )
-    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"
-        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(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
-    top_conf = float(emo_dict[top_key])
-
-    if top_conf < CONF_TH:
-        show = st.stable_emo or "unknown"
-        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(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
-
-    # 延遲確認
-    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),
-            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"),
-        )
+    is_detected = pick is not None and pick.get("face") is not None
+    
+    # 3. 繪製導引框
+    frame_with_box = _draw_guide_box(frame_rgb.copy(), is_detected)
+    now = time.time()
 
+    # 4. 核心辨識邏輯 (每隔一段時間分析)
+    if is_detected and (now - st.last_analyze_t >= ANALYZE_EVERY_SEC):
+        st.last_analyze_t = now
+        st.track_bbox = bbox
+        
+        face = pick["face"]
+        if face.dtype != np.uint8:
+            face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
+            
+        result = DeepFace.analyze(img_path=face, actions=["emotion"], enforce_detection=False)
+        if isinstance(result, list): result = result[0]
+        emo_dict = result.get("emotion", {})
+        
+        if emo_dict:
+            top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
+            top_conf = float(emo_dict[top_key])
+            
+            # EMA 平滑
+            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, st.emo_keys = vec, keys
+            else:
+                st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
+            
+            stable_key = st.emo_keys[int(np.argmax(st.ema_scores))]
+            st.stable_emo = stable_key
+            
+            # 延遲確認邏輯
+            if st.candidate_emo != stable_key:
+                st.candidate_emo, st.candidate_since = stable_key, now
+            
+            if st.candidate_since and (now - st.candidate_since >= SWITCH_CONFIRM_SEC):
+                st.final_emo, st.final_conf, st.running, st.finished = stable_key, top_conf, False, True
+                return (frame_with_box, 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"))
+
+    # 持續回傳帶有導引框的影像
+    show_emo = st.stable_emo or "unknown"
     return (
-        gr.update(visible=True),
-        gr.update(value=_result_card_html(stable_key, top_conf)),
-        gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))),
+        frame_with_box,
+        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()),
         st,
-        gr.update(value="重新攝影機辨識"),
+        gr.update()
     )
 
-
-# =========================
-# Mode / Buttons
-# =========================
-
 def on_restart(st: AppState):
     st = _reset_state_for_camera(st)
-    return (
-        gr.update(visible=True),                               
-        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(visible=True), gr.update(value=_hint_html("等待影像…")), 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"))
 
 def on_stop(st: AppState):
-    st.running = False
-    st.finished = True
-    if st.final_emo is None:
-        return (
-            gr.update(visible=False),
-            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),
-        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(value=_hint_html("已停止")), gr.update(value=_score_radio_value(3)), gr.update(value=_camera_hint_stopped()), st, gr.update(value="重新攝影機辨識"))
 
 # =========================
 # Gradio UI
 # =========================
-
 if __name__ == "__main__":
-    with gr.Blocks(title="Emotion Detector", css=css) as demo:
+    with gr.Blocks(title="Emotion Detector") as demo:
         st = gr.State(AppState())
-
         gr.Markdown("## 情緒辨識")
-        
+                
         hint = gr.HTML(_camera_hint_before_start())
-
-        cam = gr.Image(
-            sources=["webcam"],
-            streaming=True,
-            type="numpy",
-            label="攝影機",
-            visible=True,
-        )
-
+        cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機", 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）"))
-
+        result = gr.HTML(_hint_html("等待影像…"))
+        
         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",
-        )
-
+        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])
+        btn_stop.click(fn=on_stop, inputs=[st], outputs=[cam, result, mood, hint, st, btn_restart])
+        
     demo.launch(server_name="0.0.0.0", server_port=7860, share=False)