spark-extract-sift-features.py

gistfile1.txt

from __future__ import print_function
import sys
import os

import cv2
import numpy as np



def extract_sift_features_opencv(imgfile_imgbytes):
    imgfilename, imgbytes = imgfile_imgbytes
    nparr = np.fromstring(buffer(imgbytes), np.uint8)
    img = cv2.imdecode(nparr, 1)

    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    sift = cv2.xfeatures2d.SIFT_create()

    kp, descriptors = sift.detectAndCompute(gray, None)

#    with open("/tmp/test-sam", 'w') as f:
#        f.write("%s : %s" % (imgfilename, descriptors), file=f)

    return (imgfilename, descriptors)


if __name__ == "__main__":
    from pyspark import SparkContext
    sc = SparkContext(appName="feature_extractor")

    seqFilePath = sys.argv[1]
    images = sc.sequenceFile(seqFilePath)

    images_sift = images.map(extract_sift_features_opencv)

    test = images_sift.collectAsMap()
    print(test.keys())

    print("done")