计算两个白色背景、不同角度、不同位置的符号之间的相似度

import cv2

# 读取图像
img1 = cv2.imread('symbol1.png', 0)
img2 = cv2.imread('symbol2.png', 0)

# 使用ORB特征检测器
orb = cv2.ORB_create()

# 检测关键点和描述符
kp1, des1 = orb.detectAndCompute(img1, None)
kp2, des2 = orb.detectAndCompute(img2, None)

# 创建BFMatcher对象
bf = cv2.BFMatcher(cv2.NORM_HAMMING, crossCheck=True)

# 匹配描述符
matches = bf.match(des1, des2)

# 根据匹配结果排序
matches = sorted(matches, key=lambda x: x.distance)

# 绘制匹配结果
img_matches = cv2.drawMatches(img1, kp1, img2, kp2, matches[:10], None, flags=cv2.DrawMatchesFlags_NOT_DRAW_SINGLE_POINTS)

cv2.imshow('Matches', img_matches)
cv2.waitKey(0)
cv2.destroyAllWindows()

import cv2

# 读取图像
img1 = cv2.imread('symbol1.png')
img2 = cv2.imread('symbol2.png')

# 直方图均衡化
img1_eq = cv2.equalizeHist(cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY))
img2_eq = cv2.equalizeHist(cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY))

# 计算相似度（例如使用SSIM）
from skimage.metrics import structural_similarity as ssim

similarity = ssim(img1_eq, img2_eq)
print(f'Similarity: {similarity}')