自动化技术-图像识别

import cv2
import numpy as np
import pyautogui

# 获取屏幕截图
screenshot = pyautogui.screenshot()
screenshot = np.array(screenshot)
screenshot = cv2.cvtColor(screenshot, cv2.COLOR_RGB2BGR)

# 转换为灰度图像
gray = cv2.cvtColor(screenshot, cv2.COLOR_BGR2GRAY)

# 计算灰度图像的平均值
average_color = np.mean(gray)

# 设置白屏的阈值
threshold = 200  # 这里可以根据实际情况调整

# 判断屏幕是否为白屏
if average_color > threshold:
    print("屏幕为白屏")
else:
    print("屏幕不是白屏")

import cv2

# 加载两张图片
image1 = cv2.imread('image1.jpg')
image2 = cv2.imread('image2.jpg')

# 将图片转换为灰度图像
gray_image1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)
gray_image2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)

# 计算两张灰度图像的结构相似度指数（SSIM）
sift = cv2.SIFT_create()
keypoints_1, descriptors_1 = sift.detectAndCompute(gray_image1, None)
keypoints_2, descriptors_2 = sift.detectAndCompute(gray_image2, None)

bf = cv2.BFMatcher()
matches = bf.knnMatch(descriptors_1, descriptors_2, k=2)

good_matches = []
for m, n in matches:
    if m.distance < 0.75 * n.distance:
        good_matches.append([m])

similarity = len(good_matches) / len(keypoints_1) * 100
print("图片相似度: {:.2f}%".format(similarity))