Storyboard

https://www.dlology.com/blog/easy-landmark-image-recognition-with-tensorflow-hub-delf-module/

>Modelo

ID:(1787, 0)

Descripción

>Top

El Google-Landmarks Dataset tiene un gran numero de imágenes de localidades en torno al mundo.

Que se puede accesar via: google-landmarks-dataset

ID:(13823, 0)

Descripción

>Top

Setear librerías para trabajar con DELF:

from absl import logging

import matplotlib.pyplot as plt
import numpy as np
from PIL import Image, ImageOps
from scipy.spatial import cKDTree
from skimage.feature import plot_matches
from skimage.measure import ransac
from skimage.transform import AffineTransform
from six import BytesIO

import tensorflow as tf

import tensorflow_hub as hub
from six.moves.urllib.request import urlopen

ID:(13814, 0)

Descripción

>Top

Setear librerías para trabajar con DELF:

#@title Choose images
images = 'Bridge of Sighs' #@param ['Bridge of Sighs', 'Golden Gate', 'Acropolis', 'Eiffel tower']
if images == 'Bridge of Sighs':
  # from: https://commons.wikimedia.org/wiki/File:Bridge_of_Sighs,_Oxford.jpg
  # by: N.H. Fischer
  IMAGE_1_URL = 'https://upload.wikimedia.org/wikipedia/commons/2/28/Bridge_of_Sighs%2C_Oxford.jpg'
  # from https://commons.wikimedia.org/wiki/File:The_Bridge_of_Sighs_and_Sheldonian_Theatre,_Oxford.jpg
  # by: Matthew Hoser
  IMAGE_2_URL = 'https://upload.wikimedia.org/wikipedia/commons/c/c3/The_Bridge_of_Sighs_and_Sheldonian_Theatre%2C_Oxford.jpg'
elif images == 'Golden Gate':
  IMAGE_1_URL = 'https://upload.wikimedia.org/wikipedia/commons/1/1e/Golden_gate2.jpg'
  IMAGE_2_URL = 'https://upload.wikimedia.org/wikipedia/commons/3/3e/GoldenGateBridge.jpg'
elif images == 'Acropolis':
  IMAGE_1_URL = 'https://upload.wikimedia.org/wikipedia/commons/c/ce/2006_01_21_Ath%C3%A8nes_Parth%C3%A9non.JPG'
  IMAGE_2_URL = 'https://upload.wikimedia.org/wikipedia/commons/5/5c/ACROPOLIS_1969_-_panoramio_-_jean_melis.jpg'
else:
  IMAGE_1_URL = 'https://upload.wikimedia.org/wikipedia/commons/d/d8/Eiffel_Tower%2C_November_15%2C_2011.jpg'
  IMAGE_2_URL = 'https://upload.wikimedia.org/wikipedia/commons/a/a8/Eiffel_Tower_from_immediately_beside_it%2C_Paris_May_2008.jpg'

ID:(13815, 0)

Descripción

>Top

Función para bajar y guardar imágenes:

def download_and_resize(name, url, new_width=256, new_height=256):
  path = tf.keras.utils.get_file(url.split('/')[-1], url)
  image = Image.open(path)
  image = ImageOps.fit(image, (new_width, new_height), Image.ANTIALIAS)
  return image

ID:(13816, 0)

Descripción

>Top

Bajar imágenes:

image1 = download_and_resize('image_1.jpg', IMAGE_1_URL)
image2 = download_and_resize('image_2.jpg', IMAGE_2_URL)

plt.subplot(1,2,1)
plt.imshow(image1)
plt.subplot(1,2,2)
plt.imshow(image2)

ID:(13817, 0)

Descripción

>Top

Bajar imágenes:

delf = hub.load('https://tfhub.dev/google/delf/1').signatures['default']

ID:(13818, 0)

Descripción

>Top

Definición de función de consulta a DELF:

def run_delf(image):
  np_image = np.array(image)
  float_image = tf.image.convert_image_dtype(np_image, tf.float32)

  return delf(
      image=float_image,
      score_threshold=tf.constant(100.0),
      image_scales=tf.constant([0.25, 0.3536, 0.5, 0.7071, 1.0, 1.4142, 2.0]),
      max_feature_num=tf.constant(1000))

ID:(13819, 0)

Descripción

>Top

Correr DELF:

result1 = run_delf(image1)
result2 = run_delf(image2)

ID:(13820, 0)

Descripción

>Top

Correr DELF:

#@title TensorFlow is not needed for this post-processing and visualization
def match_images(image1, image2, result1, result2):
  distance_threshold = 0.8

  # Read features.
  num_features_1 = result1['locations'].shape[0]
  print('Loaded image 1s %d features' % num_features_1)
  
  num_features_2 = result2['locations'].shape[0]
  print('Loaded image 2s %d features' % num_features_2)

  # Find nearest-neighbor matches using a KD tree.
  d1_tree = cKDTree(result1['descriptors'])
  _, indices = d1_tree.query(
      result2['descriptors'],
      distance_upper_bound=distance_threshold)

  # Select feature locations for putative matches.
  locations_2_to_use = np.array([
      result2['locations'][i,]
      for i in range(num_features_2)
      if indices[i] != num_features_1
  ])
  locations_1_to_use = np.array([
      result1['locations'][indices[i],]
      for i in range(num_features_2)
      if indices[i] != num_features_1
  ])

  # Perform geometric verification using RANSAC.
  _, inliers = ransac(
      (locations_1_to_use, locations_2_to_use),
      AffineTransform,
      min_samples=3,
      residual_threshold=20,
      max_trials=1000)

  print('Found %d inliers' % sum(inliers))

  # Visualize correspondences.
  _, ax = plt.subplots()
  inlier_idxs = np.nonzero(inliers)[0]
  plot_matches(
      ax,
      image1,
      image2,
      locations_1_to_use,
      locations_2_to_use,
      np.column_stack((inlier_idxs, inlier_idxs)),
      matches_color='b')
  ax.axis('off')
  ax.set_title('DELF correspondences')

ID:(13821, 0)

Descripción

>Top

Mostrar conexiones entre características:

match_images(image1, image2, result1, result2)

ID:(13822, 0)

Descripción

>Top

Cargar estructura para consulta:

tf.reset_default_graph()
tf.logging.set_verbosity(tf.logging.FATAL)

m = hub.Module('https://tfhub.dev/google/delf/1')

# The module operates on a single image at a time, so define a placeholder to
# feed an arbitrary image in.
image_placeholder = tf.placeholder(
    tf.float32, shape=(None, None, 3), name='input_image')

module_inputs = {
    'image': image_placeholder,
    'score_threshold': 100.0,
    'image_scales': [0.25, 0.3536, 0.5, 0.7071, 1.0, 1.4142, 2.0],
    'max_feature_num': 1000,
}

module_outputs = m(module_inputs, as_dict=True)

image_tf = image_input_fn(db_images)

ID:(13824, 0)

Descripción

>Top

Importar imágenes para analizar:

with tf.train.MonitoredSession() as sess:
    results_dict = {}  # Stores the locations and their descriptors for each image
    for image_path in db_images:
        image = sess.run(image_tf)
        print('Extracting locations and descriptors from %s' % image_path)
        results_dict[image_path] = sess.run(
            [module_outputs['locations'], module_outputs['descriptors']],
            feed_dict={image_placeholder: image})

locations_agg = np.concatenate([results_dict[img][0] for img in db_images])
descriptors_agg = np.concatenate([results_dict[img][1] for img in db_images])
accumulated_indexes_boundaries = list(accumulate([results_dict[img][0].shape[0] for img in db_images]))

d_tree = cKDTree(descriptors_agg) # build the KD tree

ID:(13825, 0)

Descripción

>Top

Clasificación de lugar:

# Array to keep track of all candidates in database.
inliers_counts = []
# Read the resized query image for plotting.
img_1 = mpimg.imread(resized_image)
for index in unique_image_indexes:
    locations_2_use_query, locations_2_use_db = get_locations_2_use(index, indices, accumulated_indexes_boundaries)
    # Perform geometric verification using RANSAC.
    _, inliers = ransac(
        (locations_2_use_db, locations_2_use_query), # source and destination coordinates
        AffineTransform,
        min_samples=3,
        residual_threshold=20,
        max_trials=1000)
    # If no inlier is found for a database candidate image, we continue on to the next one.
    if inliers is None or len(inliers) == 0:
        continue
    # the number of inliers as the score for retrieved images.
    inliers_counts.append({'index': index, 'inliers': sum(inliers)})
    print('Found inliers for image {} -> {}'.format(index, sum(inliers)))
    # Visualize correspondences.
    _, ax = plt.subplots()
    img_2 = mpimg.imread(db_images[index])
    inlier_idxs = np.nonzero(inliers)[0]
    plot_matches(
        ax,
        img_1,
        img_2,
        locations_2_use_db,
        locations_2_use_query,
        np.column_stack((inlier_idxs, inlier_idxs)),
        matches_color='b')
    ax.axis('off')
    ax.set_title('DELF correspondences')
    plt.show()

ID:(13827, 0)