Update emotion.py

emotion.py

@@ -120,4 +120,489 @@ 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])
+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>
+    """
+
+
+def _score_radio_value(score: int) -> str:
+    score = int(score)
+    score = min(5, max(1, score))
+    return SCORE_LABELS[score]
+
+
+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 _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
+
+
+# =========================
+# 引導框（臉要放哪裡）
+# =========================
+GUIDE_W_RATIO = 0.55   # 框寬佔畫面比例（可調）
+GUIDE_H_RATIO = 0.70   # 框高佔畫面比例（可調）
+GUIDE_Y_OFFSET = 0.00  # 框中心往上(-)或往下(+)位移比例（可調，例如 -0.05）
+
+def _guide_box(frame: np.ndarray) -> Tuple[int, int, int, int]:
+    """回傳引導框 (x1,y1,x2,y2)"""
+    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:
+    """判斷臉框中心是否落在引導框內"""
+    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, detected_in_box: bool) -> np.ndarray:
+    """
+    在畫面上畫引導框：未偵測到(或不在框內)=紅框；偵測到且在框內=綠框
+    """
+    if frame_rgb is None:
+        return frame_rgb
+
+    img = Image.fromarray(frame_rgb)
+    draw = ImageDraw.Draw(img)
+
+    x1, y1, x2, y2 = _guide_box(frame_rgb)
+
+    # 顏色：紅 / 綠（RGB）
+    color = (0, 200, 0) if detected_in_box else (220, 0, 0)
+
+    # 線寬（跟解析度稍微連動）
+    h, w = frame_rgb.shape[:2]
+    thickness = max(3, int(min(w, h) * 0.008))
+
+    # 畫框（加粗）
+    for t in range(thickness):
+        draw.rectangle([x1 - t, y1 - t, x2 + t, y2 + t], outline=color)
+
+    # 提示文字
+    msg = "偵測中…" if detected_in_box else "請把臉放進框內"
+    tx = x1
+    ty = max(0, y1 - int(thickness * 6))
+    draw.rectangle([tx, ty, tx + 240, ty + 32], fill=(255, 255, 255))
+    draw.text((tx + 6, ty + 6), msg, fill=(0, 0, 0))
+
+    return np.array(img)
+
+
+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]]
+) -> Tuple[Optional[Dict], 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)
+        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
+        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
+    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)
+
+    # 預設：沒偵測到（或不在引導框內）-> 紅框
+    detected_in_box = False
+
+    now = time.time()
+    if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
+        show = st.stable_emo or "unknown"
+        annotated = _draw_guide_overlay(frame_rgb, detected_in_box)
+        return (
+            gr.update(visible=True, value=annotated),
+            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
+
+    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)
+    if pick is None or bbox is None or pick.get("face") is None:
+        show = st.stable_emo or "unknown"
+        annotated = _draw_guide_overlay(frame_rgb, detected_in_box)
+        return (
+            gr.update(visible=True, value=annotated),
+            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"),
+        )
+
+    # bbox 是 small 座標，換算回 frame_rgb 座標後判斷是否在引導框內
+    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)
+    guide = _guide_box(frame_rgb)
+    detected_in_box = _bbox_center_in_box(bbox_full, guide)
+
+    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"
+        annotated = _draw_guide_overlay(frame_rgb, detected_in_box)
+        return (
+            gr.update(visible=True, value=annotated),
+            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"
+        annotated = _draw_guide_overlay(frame_rgb, detected_in_box)
+        return (
+            gr.update(visible=True, value=annotated),
+            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"),
+        )
+
+    annotated = _draw_guide_overlay(frame_rgb, detected_in_box)
+    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()),
+        st,
+        gr.update(value="重新攝影機辨識"),
+    )
+
+
+# =========================
+# 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"),                      
+    )
+
+
+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"),
+    )
+
+
+# =========================
+# Gradio UI
+# =========================
+
+if __name__ == "__main__":
+    with gr.Blocks(title="Emotion Detector", css=css) 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,
+        )
+
+        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)