Spring框架的最新进展：2023年Spring Boot和Spring Cloud功能更新

提取人脸

• • 导入所需的库
  • 创建窗口
  • 显示原始图片
  • 显示检测到的人脸
  • 创建全局变量
  • 定义字体对象
  • 定义一个函数select_image
  • 定义了extract_faces函数
  • 设置按钮
  • 运行GUI主循环
  • 运行显示

导入所需的库

import tkinter as tk
from tkinter import filedialog
import cv2
from PIL import Image, ImageTk
from tkinter import messagebox
import subprocess

创建窗口

win = tk.Tk()
win.title("人脸提取")
win.geometry("800x650")

显示原始图片

image_label_original = tk.Label(win)
image_label_original.pack(side=tk.LEFT, padx=10, pady=80)

显示检测到的人脸

image_label_detected = tk.Label(win)
image_label_detected.pack(side=tk.LEFT, padx=10, pady=80)

创建全局变量

selected_image_path = None

定义字体对象

my_font = ("Times New Roman", 20)

定义一个函数select_image

def select_image():
    global selected_image_path
    # 打开文件选择对话框
    selected_image_path = filedialog.askopenfilename()

    # 使用OpenCV加载图片
    img = cv2.imread(selected_image_path)
    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    img_pil = Image.fromarray(img_rgb)
    img_pil = img_pil.resize((300, 300), Image.Resampling.LANCZOS)  # 调整图片大小为300x300
    img_tk = ImageTk.PhotoImage(image=img_pil)

    # 显示原始图片
    image_label_original.config(image=img_tk)
    image_label_original.image = img_tk

定义了extract_faces函数

def extract_faces():
    if selected_image_path:
        # 使用OpenCV的人脸检测
        img = cv2.imread(selected_image_path)
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
        faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)

        # 打印检测到的人脸数量
        print(f"Detected faces: {len(faces)}")

        # 如果检测到人脸，裁剪并显示
        if len(faces) > 0:
            (x, y, w, h) = faces[0]  # 获取第一个检测到的人脸
            print(f"Face coordinates: x={x}, y={y}, w={w}, h={h}")
            face_img = img[y:y+h, x:x+w]  # 裁剪人脸区域

            # 转换为PIL图像并调整大小
            face_img = cv2.cvtColor(face_img, cv2.COLOR_BGR2RGB)
            face_img = Image.fromarray(face_img)
            face_img = face_img.resize((300, 300), Image.Resampling.LANCZOS)  # 调整人脸图片大小为300x300
            face_img = ImageTk.PhotoImage(face_img)
            image_label_detected.config(image=face_img)
            image_label_detected.image = face_img
        else:
            messagebox.showinfo("信息", "没有检测到人脸")
    else:
        messagebox.showwarning("警告", "请先选择一张图片")

设置按钮

创建选择图片和识别人脸的按钮
button_select = tk.Button(win, text="选择图片", font=my_font, command=select_image, fg='black')
button_select.place(x=150, y=12)

button_extract = tk.Button(win, text="提取人脸", font=my_font, command=extract_faces, fg='black')
button_extract.place(x=450, y=12)

运行GUI主循环

win.mainloop(): 进入窗口win的主事件循环，使窗口显示并等待用户操作，直到用户关闭窗口。

win.mainloop()

运行显示

全部代码：

import tkinter as tk
from tkinter import filedialog
import cv2
from PIL import Image, ImageTk
from tkinter import messagebox
import subprocess

win = tk.Tk()
win.title("人脸提取")
win.geometry("800x650")

image_label_original = tk.Label(win)
image_label_original.pack(side=tk.LEFT, padx=10, pady=80)

image_label_detected = tk.Label(win)
image_label_detected.pack(side=tk.LEFT, padx=10, pady=80)

selected_image_path = None

my_font = ("Times New Roman", 20)

def select_image():
    global selected_image_path
    # 打开文件选择对话框
    selected_image_path = filedialog.askopenfilename()

    # 使用OpenCV加载图片
    img = cv2.imread(selected_image_path)
    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    img_pil = Image.fromarray(img_rgb)
    img_pil = img_pil.resize((300, 300), Image.Resampling.LANCZOS)  # 调整图片大小为300x300
    img_tk = ImageTk.PhotoImage(image=img_pil)

    # 显示原始图片
    image_label_original.config(image=img_tk)
    image_label_original.image = img_tk

# 人脸检测函数
def extract_faces():
    if selected_image_path:
        # 使用OpenCV的人脸检测
        img = cv2.imread(selected_image_path)
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
        faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)

        # 打印检测到的人脸数量
        print(f"Detected faces: {len(faces)}")

        # 如果检测到人脸，裁剪并显示
        if len(faces) > 0:
            (x, y, w, h) = faces[0]  # 获取第一个检测到的人脸
            print(f"Face coordinates: x={x}, y={y}, w={w}, h={h}")
            face_img = img[y:y+h, x:x+w]  # 裁剪人脸区域

            # 转换为PIL图像并调整大小
            face_img = cv2.cvtColor(face_img, cv2.COLOR_BGR2RGB)
            face_img = Image.fromarray(face_img)
            face_img = face_img.resize((300, 300), Image.Resampling.LANCZOS)  # 调整人脸图片大小为300x300
            face_img = ImageTk.PhotoImage(face_img)
            image_label_detected.config(image=face_img)
            image_label_detected.image = face_img
        else:
            messagebox.showinfo("信息", "没有检测到人脸")
    else:
        messagebox.showwarning("警告", "请先选择一张图片")

# 创建选择图片和识别人脸的按钮
button_select = tk.Button(win, text="选择图片", font=my_font, command=select_image, fg='black')
button_select.place(x=150, y=12)

button_extract = tk.Button(win, text="提取人脸", font=my_font, command=extract_faces, fg='black')
button_extract.place(x=450, y=12)

win.mainloop()