Question

在我的项目中，我将为服务器提供图像，并且服务器必须在数据集中搜索相似的图像。

我正在使用基于orb和Flann的Matcher在查询图像和数据集中的每个图像之间找到匹配项。这是我的searcher.py文件，根据匹配项，该文件仍然缺少一些代码：

# import the necessary packages
from orbdescriptor import orbdescriptor
from orb_pickle import orb_pickle
import argparse
import glob
import cv2
import pickle
import numpy as np

class Searcher:
    def __init__(self, indexPath):
        # store our index path
        self.indexPath = indexPath

    def search(self, kp, desc, limit = 10):
        # initialize our dictionary of results
        results = {}
        FLANN_INDEX_LSH = 0
        MIN_MATCH_COUNT = 10
        orbpickle = orb_pickle()
        index_params = dict(algorithm = FLANN_INDEX_LSH, table_number = 12, key_size = 20, multi_probe_level = 2) 
        search_params = dict(checks=50)   # or pass empty dictionary
        flann = cv2.FlannBasedMatcher(index_params,search_params)
        # open the index file for reading
        keypoints_database = pickle.load( open( "keypoints_database.p", "rb" ) )
        for keypoint_item in keypoints_database:
            kp1, desc1, image_path = orbpickle.unpickle_keypoints(keypoint_item)
            if (len(desc1) > 0):
                desc = np.float32(desc)
                desc1 = np.float32(desc1)
                matches = flann.knnMatch(desc,desc1,k=2)

问题是，根据上面代码中搜索到的匹配项，我还能怎么做才能在数据集中找到相似的图像？任何帮助将不胜感激...

Python：使用Orb查找相似的图像

0 个答案: