OpenCV-Python: SURT Demo one

# -*-coding:utf-8-*-
#author: lyp time: 2018/8/3
import cv2
import numpy as np

img = cv2.imread(‘lyp.jpg‘)
grayImg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

surf = cv2.xfeatures2d.SURF_create(300, upright=True)
kp, des = surf.detectAndCompute(grayImg, None)

img2 = cv2.drawKeypoints(img, kp, None, (0, 255, 0), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv2.imshow(‘SURF Image‘, img2)

cv2.waitKey()
cv2.destroyAllWindows()

0.函数讲解

retval=cv2.xfeatures2d.SURF_create([, hessianThreshold[, nOctaves[, nOctaveLayers[, extended[, upright]]]]])

hessianThreshold: H矩阵阀值，默认值是100， 大于该阀值的关键点将会被显示出来，推荐范围为300-500
extended: 是否扩展SURF描述维度，默认值是False，扩展时将计算128维度的扩展描述，否则默认计算64维度的描述（速度快）
upright:是否计算SURF描述的方向，默认值是False, 不计算则运行较快

keypoints=cv2.Feature2D.detect(image[, mask]) 关键点
keypoints, descriptors=cv2.Feature2D.compute(image, keypoints[, descriptors]) 特征描述向量

1.参考来自
小林的CV视觉工坊

OpenCV-Python: SURT Demo one

原文：https://www.cnblogs.com/gfgwxw/p/9416038.html