基于 DeepFace 与 OpenCV 的实时情绪分析器实现

性能监控（FPS 计算）

为了不让 FPS 跳动太剧烈，我们用了滑动平均算法。先算出瞬时帧率，再结合历史值更新当前 FPS。

current_time = time.time()
delta_time = current_time - prev_time
prev_time = current_time

if delta_time > 0:
    instant_fps = 1.0 / delta_time
    fps = alpha * fps + (1 - alpha) * instant_fps

情绪分析与标注

调用 DeepFace.analyze() 对当前帧进行分析。注意设置 enforce_detection=False，这样即使没检测到人脸也不会报错，程序更健壮。拿到结果后，遍历每个人脸区域，提取坐标和主导情绪，用 OpenCV 画矩形框和文字。

try:
    result = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
    for face in result:
        x, y, w, h = face['region']['x'], face['region']['y'], face['region']['w'], face['region']['h']
        emotion = face['dominant_emotion']
        confidence = face['emotion'][emotion]
        
        # 画人脸框
        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
        # 标情绪和置信度
        text = f'{emotion} ({confidence:.2f}%)'
        cv2.putText(frame, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
except Exception as e:
    print("无法检测到人脸:", e)

显示与退出

最后把 FPS 也画上去，显示整个画面。监听键盘输入，按 q 键退出，记得释放资源。

cv2.putText(frame, f'FPS: {fps:.2f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 255), 2)
cv2.imshow("Emotion Detection", frame)

if cv2.waitKey(1) & 0xFF == ord('q'):
    break

cap.release()
cv2.destroyAllWindows()

完整代码

把上面片段整合起来，就是完整的脚本：

import cv2
import time
import numpy as np
from deepface import DeepFace

# 打开摄像头
cap = cv2.VideoCapture(0)

# FPS 计算参数
prev_time = time.time()
fps = 0
alpha = 0.9  # 滑动平均权重，数值越大，FPS 越平稳

while True:
    ret, frame = cap.read()
    if not ret:
        break

    # 计算 FPS
    current_time = time.time()
    delta_time = current_time - prev_time
    prev_time = current_time
    if delta_time > 0:
        instant_fps = 1.0 / delta_time
        fps = alpha * fps + (1 - alpha) * instant_fps

    # 计算滑动平均 FPS
    try:
        # 进行表情识别
        result = DeepFace.analyze(frame, actions=['emotion'], enforce_detection=False)
        for face in result:
            x, y, w, h = face['region']['x'], face['region']['y'], face['region']['w'], face['region']['h']
            emotion = face['dominant_emotion']
            confidence = face['emotion'][emotion]  # 获取表情的置信度
            
            # 绘制人脸矩形框
            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)
            
            # 在人脸上方显示情绪信息
            text = f'{emotion} ({confidence:.2f}%)'
            cv2.putText(frame, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
    except Exception as e:
        print("无法检测到人脸:", e)

    # 显示 FPS（平滑更新）
    cv2.putText(frame, f'FPS: {fps:.2f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 255), 2)

    # 显示图像
    cv2.imshow("Emotion Detection", frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

效果展示

程序运行后，可以实时看到不同情绪的识别结果：

总结

这个项目核心在于结合了 OpenCV 的视频处理能力与 DeepFace 的深度学习模型。通过简单的几行代码，就能实现从摄像头采集、情绪分析到结果可视化的全流程。这不仅展示了如何利用现有 AI 库快速构建实用应用，也为后续开发更复杂的情感交互系统提供了基础框架。