如何手动设置关键点并提取特征

Question

我正在使用 ORB 来检测一组图像上的关键点，如下例所示：

我想要做的是：我想在图像的特定坐标处手动设置 22 个点，并将从这些点中提取的特征存储到特征向量中。例如：

之后，将这些特征分别存储到第 22 维向量中。

我目前用来加载我的图像并设置关键点的代码是这样的：

import matplotlib.pyplot as plt
import numpy as np
import os
import pandas as pd
from sklearn.utils import Bunch
from skimage.io import imread
import skimage
import cv2

DATADIR = "C:/Dataset"
CATEGORIES = ["class 1", "class 2", "class 3", "class 4", "class 5"]


def load_image_files(fullpath):
    descr = "A image classification dataset"
    for category in CATEGORIES:
        path = os.path.join(DATADIR, category)
        for person in os.listdir(path):
            personfolder = os.path.join(path, person)
            for imgname in os.listdir(personfolder):
                class_num = CATEGORIES.index(category)
                fullpath = os.path.join(personfolder, imgname)
                imageList = skimage.io.imread(fullpath)
                orb = cv2.ORB_create(22)
                kp, des = orb.detectAndCompute(imageList, None)'''
                orb = cv2.ORB_create()
                key_points = [cv2.KeyPoint(64, 9, 1), cv2.KeyPoint(107, 6, 10), cv2.KeyPoint(171, 10, 10)]
                kp, des = orb.compute(imageList, key_points)
                drawnImages = cv2.drawKeypoints(imageList, kp, None, flags= cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
                cv2.imshow("Image", drawnImages)
                cv2.waitKey(0)

    return Bunch(target_names=CATEGORIES,
                     images=images,
                     DESCR=descr)

这些是我希望从中提取特征的坐标

p1 = 60, 10
p2 = 110, 10
p3 = 170, 10
p4 = 25, 60
p5 = 60, 40
p6 = 110, 35
p7 = 170, 35
p8 = 190, 60
p9 = 30, 95
p10 = 60, 80
p11 = 100, 105
p12 = 120, 105
p13 = 160, 180
p14 = 185, 95
p15 = 25, 160
p16 = 55, 160
p17 = 155, 160
p18 = 185, 160
p19 = 65, 200
p20 = 83, 186
p21 = 128, 186
p22 = 157, 197

Answer 1

使用 orb API 中的计算方法。一些标准将是

kp = orb.detect(img,None)
kp, des = orb.compute(img, kp)

但对于您的情况，关键点来自用户输入，因此请使用类似

input_kp = # comes from user
kp, des = orb.compute(img, input_kp)

确保输入关键点与计算方法所期望的格式相匹配。您可以像这样从 x、y 值创建关键点。

key_points = [cv2.KeyPoint(x1, y1, 1), cv2.KeyPoint(x2, y2, 1) ...]