使用谷歌Vision API做人脸检测时如何在Python中通过GUI展示图像

完整可运行修改代码 #

import tkinter as tk
from PIL import Image, ImageTk
from tkinter.filedialog import askopenfile
import io
import os
from google.cloud import vision

root = tk.Tk()
root.title("人脸情绪识别")
canvas = tk.Canvas(root, width=600, height=300)
canvas.grid(columnspan=3, rowspan=3)

os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = r'crack-producer-313920-5e16fbab8c24.json'

client = vision.ImageAnnotatorClient()
file_name = os.path.abspath('picture.jpg')

with io.open(file_name, 'rb') as image_file:
    content = image_file.read()
    
image = vision.Image(content=content)
response = client.face_detection(image=image)
faces = response.face_annotations

likelihood_name = ('UNKNOWN', 'VERY_UNLIKELY', 'UNLIKELY', 'POSSIBLE',
                'LIKELY', 'VERY_LIKELY')
print('Faces:')

for face in faces:
    print('anger: {}'.format(likelihood_name[face.anger_likelihood]))
    print('joy: {}'.format(likelihood_name[face.joy_likelihood]))
    print('surprise: {}'.format(likelihood_name[face.surprise_likelihood]))

    vertices = (['({},{})'.format(vertex.x, vertex.y)
                for vertex in face.bounding_poly.vertices])

    print('face bounds: {}'.format(','.join(vertices)))

if response.error.message:
    raise Exception(
        '{}\nFor more info on error messages, check: '
        'https://cloud.google.com/apis/design/errors'.format(
            response.error.message))

# ------------------- 新增GUI图片渲染逻辑 -------------------
# 加载原始图片
pil_img_raw = Image.open(file_name)
orig_w, orig_h = pil_img_raw.size
# 缩放图片适配画布尺寸，保持原始比例
pil_img = pil_img_raw.copy()
pil_img.thumbnail((600, 300))
new_w, new_h = pil_img.size
# 计算坐标缩放比例
x_ratio = new_w / orig_w
y_ratio = new_h / orig_h

# 转换为Tkinter支持的图片格式
tk_img = ImageTk.PhotoImage(pil_img)
# 绑定到canvas属性，避免图片被Python垃圾回收导致不显示
canvas.tk_img = tk_img
# 绘制图片到画布左上角
canvas.create_image(0, 0, anchor=tk.NW, image=tk_img)

# 可选：绘制人脸框和情绪结果到GUI
for idx, face in enumerate(faces):
    v = face.bounding_poly.vertices
    # 转换原始坐标为适配缩放后图片的坐标
    x1, y1 = int(v[0].x * x_ratio), int(v[0].y * y_ratio)
    x2, y2 = int(v[2].x * x_ratio), int(v[2].y * y_ratio)
    # 画红色人脸边框
    canvas.create_rectangle(x1, y1, x2, y2, outline='red', width=2)
    # 拼接情绪文本
    emotion_info = f"#{idx+1} 喜:{likelihood_name[face.joy_likelihood]} 怒:{likelihood_name[face.anger_likelihood]} 惊:{likelihood_name[face.surprise_likelihood]}"
    # 文本绘制在人脸框上方
    canvas.create_text(x1, y1-8, anchor=tk.SW, text=emotion_info, fill='red', font=('黑体',9))

root.mainloop()

关键改动说明 #

• grid() 是Tkinter的布局方法，仅负责控制组件在父容器中的位置，本身不需要绑定额外变量，之前无法显示是因为没有把图片内容渲染到已布局好的Canvas组件上
• 必须将ImageTk.PhotoImage生成的图片对象绑定到一个长期存在的变量/实例属性上，否则会被Python垃圾回收机制清理，导致界面看不到图片
• 新增的坐标缩放逻辑适配了图片缩放后的尺寸，保证人脸框位置和实际人脸位置对齐
• 可选的人脸框和情绪文本绘制逻辑可以直接在GUI上展示识别结果，无需再查看终端输出

内容的提问来源于stack exchange，提问作者Filzo