2

我正在尝试构建一个 CBIR 系统，最近使用 OpenCV 函数在 Python 中编写了一个程序，该程序让我可以查询本地图像数据库并返回结果（按照本教程进行操作）。我现在需要将它与另一个网络抓取模块（使用 Scrapy）链接起来，其中我输出了 ~1000 个在线图像链接。这些图像分散在整个网络中，应该输入到第一个 OpenCV 模块。是否可以在不下载的情况下对这个在线图像集进行计算？

这些是我为 OpenCV 模块所遵循的步骤

1) 定义基于区域的彩色图像描述符

2）从数据集中提取特征（索引）（作为命令行参数传递的数据集）

# import the necessary packages
import sys
sys.path.append('/usr/local/lib/python2.7/site-packages')
from colordescriptor import ColorDescriptor
import argparse
import glob
import cv2

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d", "--dataset", required = True,
  help = "Path to the directory that contains the images to be indexed")
ap.add_argument("-i", "--index", required = True,
  help = "Path to where the computed index will be stored")
args = vars(ap.parse_args())

# initialize the color descriptor
cd = ColorDescriptor((8, 12, 3))
# open the output index file for writing
output = open(args["index"], "w")

# use glob to grab the image paths and loop over them
for imagePath in glob.glob(args["dataset"] + "/*.jpg"):
    # extract the image ID (i.e. the unique filename) from the image
    # path and load the image itself
    imageID = imagePath[imagePath.rfind("/") + 1:]
    image = cv2.imread(imagePath)

    # describe the image
    features = cd.describe(image)

    # write the features to file
    features = [str(f) for f in features]
    output.write("%s,%s\n" % (imageID, ",".join(features)))

# close the index file
output.close()

3) 定义相似度度量

# import the necessary packages
import numpy as np
import sys
sys.path.append('/usr/local/lib/python2.7/site-packages')
import csv

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

    def search(self, queryFeatures, limit = 5):
        # initialize our dictionary of results
        results = {}

        # open the index file for reading
        with open(self.indexPath) as f:
            # initialize the CSV reader
            reader = csv.reader(f)

            # loop over the rows in the index
            for row in reader:
                # parse out the image ID and features, then compute the
                # chi-squared distance between the features in our index
                # and our query features
                features = [float(x) for x in row[1:]]
                d = self.chi2_distance(features, queryFeatures)

                # now that we have the distance between the two feature
                # vectors, we can udpate the results dictionary -- the
                # key is the current image ID in the index and the
                # value is the distance we just computed, representing
                # how 'similar' the image in the index is to our query
                results[row[0]] = d

            # close the reader
            f.close()

        # sort our results, so that the smaller distances (i.e. the
        # more relevant images are at the front of the list)
        results = sorted([(v, k) for (k, v) in results.items()])

        # return our (limited) results
        return results[:limit]

    def chi2_distance(self, histA, histB, eps = 1e-10):
        # compute the chi-squared distance
        d = 0.5 * np.sum([((a - b) ** 2) / (a + b + eps)
            for (a, b) in zip(histA, histB)])

        # return the chi-squared distance
        return d

`

4) 执行实际搜索

# import the necessary packages
from colordescriptor import ColorDescriptor
from searcher import Searcher
import sys
sys.path.append('/usr/local/lib/python2.7/site-packages')
import argparse
import cv2

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--index", required = True,
    help = "Path to where the computed index will be stored")
ap.add_argument("-q", "--query", required = True,
    help = "Path to the query image")
ap.add_argument("-r", "--result-path", required = True,
    help = "Path to the result path")
args = vars(ap.parse_args())

# initialize the image descriptor
cd = ColorDescriptor((8, 12, 3))

# load the query image and describe it
query = cv2.imread(args["query"])
features = cd.describe(query)

# perform the search
searcher = Searcher(args["index"])
results = searcher.search(features)

# display the query
cv2.imshow("Query", query)

# loop over the results
for (score, resultID) in results:
    # load the result image and display it
    result = cv2.imread(args["result_path"] + "/" + resultID)
    cv2.imshow("Result", result)
    cv2.waitKey(0)

最后的命令行命令是：

python search.py --index index.csv --query query.png --result-path dataset

其中 index.csv 是第 2 步之后在图像数据库上生成的文件。query.png 是我的查询图像，数据集是包含约 100 张图像的文件夹。

那么是否可以修改索引以使我不需要本地数据集并且可以直接从 URL 列表中进行查询和索引？

4

0 回答 0