opencv关键点检测

python 使用opencv进行图片关键点检测

功能：

        在一张图片中裁剪出一块小图

        使用cv2中  cv2.SIFT_create()   SIFT检测器检测关键点

        匹配原图和小图的关键点

import cv2
import numpy as np
# 读取图像
img1 = cv2.imread(r'E:\234947.jpg', cv2.IMREAD_GRAYSCALE)
img2 = cv2.imread(r'E:\234.jpg', cv2.IMREAD_GRAYSCALE)

# 初始化SIFT检测器
sift = cv2.SIFT_create()
# 检测关键点和计算描述符
keypoints1, descriptors1 = sift.detectAndCompute(img1, None)
keypoints2, descriptors2 = sift.detectAndCompute(img2, None)
# 使用BFMatcher进行匹配
bf = cv2.BFMatcher(cv2.NORM_L2, crossCheck=False)
matches = bf.knnMatch(descriptors1, descriptors2, k=2)

# 应用比值测试
good_matches = []
for m, n in matches:
    if m.distance < 0.75 * n.distance:
        good_matches.append(m)
# 使用RANSAC进行几何验证
if len(good_matches) > 4:
    src_pts = np.float32([keypoints1[m.queryIdx].pt for m in good_matches]).reshape(-1, 1, 2)
    dst_pts = np.float32([keypoints2[m.trainIdx].pt for m in good_matches]).reshape(-1, 1, 2)

    matrix, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
    matches_mask = mask.ravel().tolist()
else:
    matches_mask = None
# 绘制匹配结果

draw_params = dict(matchColor=(0, 255, 0),
                   singlePointColor=None,
                   matchesMask=matches_mask,
                   flags=2)
img1_color = cv2.cvtColor(img1, cv2.COLOR_GRAY2BGR)
img2_color = cv2.cvtColor(img2, cv2.COLOR_GRAY2BGR)
print("----------------",keypoints1,matches_mask)
img3 = cv2.drawMatches(img1_color, keypoints1, img2_color, keypoints2, good_matches, None, **draw_params)

# 显示匹配结果
cv2.imshow('Matches', img3)
cv2.waitKey(0)
cv2.destroyAllWindows()

结果展示：