Update emotion.py

emotion.py

@@ -1,175 +1,123 @@
 import time
-import cv2
 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 PIL import Image, ImageDraw
+
 from deepface import DeepFace
 
+
 # =========================
-# 參數（效能優化版）
+# 參數（可微調）
 # =========================
 ANALYZE_EVERY_SEC = 0.8
 DOWNSAMPLE_W = 720
 EMA_ALPHA = 0.45
 CONF_TH = 40.0
 SWITCH_CONFIRM_SEC = 2.5
-ZOOM_FACTOR = 1.3
+IOU_TH = 0.25
+ZOOM_FACTOR = 1.5
+
+DETECTOR_BACKEND = "mtcnn"     # 想快一點可改 "opencv"
+ALIGN_FACE = True
+
 
 # =========================
-# 狀態與映射
+# 情緒中文 + 分數映射（7 -> 5）
 # =========================
-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}
-SCORE_LABELS = {i: f"{i}（{desc}）" for i, desc in zip(range(1,6), ["心情差","不太好","普通","不錯","超棒"])}
-SCORE_CHOICES = [SCORE_LABELS[i] for i in range(1,6)]
+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",
+}
+
+# 你要的：把 7 種情緒塞進 5 分心情分數
+EMO_TO_SCORE = {
+    "angry": 1,
+    "disgust": 1,
+    "fear": 1,
+    "sad": 2,
+    "neutral": 3,
+    "surprise": 4,
+    "happy": 5,
+    "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）",
+    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]]
+
 
+# =========================
+# 狀態
+# =========================
 @dataclass
 class AppState:
+    mode: str = "攝影機辨識" 
+
     running: bool = True
     finished: bool = False
     last_analyze_t: float = 0.0
-    last_check_t: float = 0.0
-    is_aligned: bool = False
+
+    # 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  
+
+
 # =========================
-# UI 介面
+# UI HTML (強制黑色文字)
 # =========================
 def _hint_html(msg: str) -> str:
-    return f'<div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#000000;text-align:center;">{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 = f"{conf:.1f}%" if conf else "--%"
+    # 加入 color:#000000 強制黑色
     return f"""
-    <div style="border-radius:16px;padding:30px;border:2px solid #4CAF50;background:#FFFFFF;color:#000000;text-align:center;box-shadow: 0 4px 10px rgba(0,0,0,0.1);">
-      <div style="font-size:18px;margin-bottom:10px;color:#666;">✨ 辨識完成 ✨</div>
-      <div style="font-size:56px;font-weight:800;color:#2E7D32;margin-bottom:15px;">{zh}</div>
-      <div style="font-size:20px;margin-bottom:10px;">心情分數：<strong>{score}</strong></div>
-      <div style="font-size:16px;color:#888;">系統信心值：{conf_txt}</div>
+    <div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#000000;">
+      {msg}
     </div>
     """
 
-def _draw_ui_overlay(frame: np.ndarray, is_aligned: bool):
-    canvas = frame.copy()
-    h, w = canvas.shape[:2]
-    bw, bh = int(w * 0.45), int(h * 0.55)
-    x1, y1 = (w - bw) // 2, (h - bh) // 2
-    x2, y2 = x1 + bw, y1 + bh
-    color = (0, 255, 0) if is_aligned else (255, 0, 0)
-    text = "SCANNING..." if is_aligned else "PLACE FACE HERE"
-    cv2.rectangle(canvas, (x1, y1), (x2, y2), color, 2)
-    l = 40
-    cv2.line(canvas, (x1, y1), (x1+l, y1), color, 5); cv2.line(canvas, (x1, y1), (x1, y1+l), color, 5)
-    cv2.line(canvas, (x2, y2), (x2-l, y2), color, 5); cv2.line(canvas, (x2, y2), (x2, y2-l), color, 5)
-    cv2.putText(canvas, text, (x1, y1 - 15), cv2.FONT_HERSHEY_SIMPLEX, 0.8, color, 2)
-    return canvas
 
-# =========================
-# 核心串流邏輯
-# =========================
-def on_stream(frame_rgb: np.ndarray, st: AppState):
-    if frame_rgb is None or st.finished or not st.running:
-        # 當 finished 為 True 時，這裡會被觸發，返回關閉攝影機的指令
-        return (gr.update(visible=False), gr.update(), gr.update(), gr.update(), st)
-
-    now = time.time()
-    # 數位變焦
-    h, w = frame_rgb.shape[:2]
-    nw, nh = int(w / ZOOM_FACTOR), int(h / ZOOM_FACTOR)
-    sx, sy = (w - nw) // 2, (h - nh) // 2
-    frame_rgb = frame_rgb[sy:sy+nh, sx:sx+nw]
-
-    # 每 0.3 秒檢查一次臉部位置
-    if now - st.last_check_t > 0.3:
-        st.last_check_t = now
-        try:
-            small = np.array(Image.fromarray(frame_rgb).resize((200, 200)))
-            faces = DeepFace.extract_faces(img_path=small, detector_backend="opencv", enforce_detection=False)
-            if faces and faces[0]['face'] is not None:
-                fa = faces[0]['facial_area']
-                fx, fy = fa['x'] * (frame_rgb.shape[1]/200), fa['y'] * (frame_rgb.shape[0]/200)
-                fw, fh = fa['w'] * (frame_rgb.shape[1]/200), fa['h'] * (frame_rgb.shape[0]/200)
-                gx1, gy1 = (frame_rgb.shape[1] - int(frame_rgb.shape[1]*0.45))//2, (frame_rgb.shape[0] - int(frame_rgb.shape[0]*0.55))//2
-                gx2, gy2 = gx1 + int(frame_rgb.shape[1]*0.45), gy1 + int(frame_rgb.shape[0]*0.55)
-                st.is_aligned = (gx1 < fx + fw/2 < gx2) and (gy1 < fy + fh/2 < gy2)
-            else:
-                st.is_aligned = False
-        except:
-            st.is_aligned = False
-
-    frame_with_ui = _draw_ui_overlay(frame_rgb, st.is_aligned)
-
-    # 分析邏輯
-    if st.is_aligned and (now - st.last_analyze_t >= ANALYZE_EVERY_SEC):
-        st.last_analyze_t = now
-        try:
-            res = DeepFace.analyze(img_path=frame_rgb, actions=["emotion"], enforce_detection=False, detector_backend="opencv")
-            emo_dict = res[0].get("emotion") if isinstance(res, list) else res.get("emotion")
-            if emo_dict:
-                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
-                else: st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
-                
-                stable_key = st.emo_keys[np.argmax(st.ema_scores)]
-                st.stable_emo = stable_key
-                
-                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):
-                    # 【關鍵點】辨識成功，設定 finished 並關閉攝像頭
-                    st.final_emo, st.final_conf, st.running, st.finished = stable_key, float(emo_dict[stable_key]), False, True
-                    return (
-                        gr.update(visible=False), # 隱藏攝像頭
-                        _result_card_html(stable_key, st.final_conf), # 跳出大卡片
-                        SCORE_LABELS[EMO_TO_SCORE.get(stable_key, 3)], # 更新分數按鈕
-                        _hint_html("辨識完成！"), # 更新提示文字
-                        st
-                    )
-        except:
-            pass
-
-    return (frame_with_ui, gr.update(value=_result_card_html(st.stable_emo, None)), gr.update(), gr.update(), st)
+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。"
+    )
 
-# =========================
-# 按鈕動作
-# =========================
-def on_restart(st: AppState):
-    st.running, st.finished, st.ema_scores, st.stable_emo = True, False, None, "unknown"
-    return (gr.update(visible=True), _hint_html("請將臉部對準方框"), SCORE_LABELS[3], st)
 
-# =========================
-# UI 配置
-# =========================
-with gr.Blocks(title="Emotion Detector") as demo:
-    state = gr.State(AppState())
-    gr.Markdown("## 情緒辨識系統")
-    
-    hint = gr.HTML(_hint_html("請點擊下方錄製按鈕開始辨識"))
-    
-    with gr.Column(elem_id="main-container"):
-        cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機預覽")
-        result_area = gr.HTML(_hint_html("辨識結果將在此顯示"))
-    
-    with gr.Row():
-        btn_restart = gr.Button("重新辨識 / 開啟攝影機", variant="primary")
-        btn_stop = gr.Button("停止", variant="secondary")
-        
-    mood = gr.Radio(choices=SCORE_CHOICES, value=SCORE_LABELS[3], label="判定心情", interactive=False)
-
-    cam.stream(on_stream, [cam, state], [cam, result_area, mood, hint, state], show_progress="minimal")
-    btn_restart.click(on_restart, [state], [cam, hint, mood, state])
-    btn_stop.click(lambda st: (gr.update(visible=False), _hint_html("已停止"), st), [state], [cam, hint, state])
-
-if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+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])