We will create this vocabulary by randomly selecting tens or hundreds of thousands of local features from our training set and clustering them with k-means. The number of k-means clusters represents the size of our vocabulary and features. For example, you could begin by clustering a large number of SIFT descriptors into k=50 clusters. This divides the 128-dimensional continuous SIFT feature space into 50 regions. As long as we keep the centroids of our original clusters, we can figure out which region any new SIFT feature belongs to. Our visual word vocabulary is made up of centroids. Work with Historgrams. We will densely sample many SIFT descriptors for each image. Rather than storing hundreds of SIFT descriptors, we simply count the number of SIFT descriptors that fall into each cluster in our visual word vocabulary. This is accomplished by locating the nearest neighbor k-means centroid for each SIFT feature. Thus, if we have a visual vocabulary of 50 words and detect 200 distinct SIFT features in an image, our bag of SIFT representation will be a histogram of 50 dimensions, with each bin counting how many times a SIFT descriptor was assigned to that cluster. The sum of all bin-counts is 200. The histogram should be normalized so that the magnitude of the bag of features does not change dramatically with image size. Instead of using SIFT to detect invariant keypoints, which takes time, you should densely sample keypoints in a grid with a specific step size (sampling density) and scale. Because the bag of SIFT representation has many design decisions and free parameters (number of clusters, sampling density, sampling scales, SIFT parameters, etc.), accuracy may vary.   Use KMeans in Sklearn to do clustering and find the nearest cluster centroid for each SIFT feature; Use cv2.xfeatures2d.SIFT_create() to create a SIFT object; Use cv2.Keypoint() to generate key points; Use sift.compute() to compute SIFT descriptors given densely sampled keypoints. Be mindful of RAM usage. Try to make the code more memory efficient, otherwise it could easily exceed RAM limits in Colab, at which point your session will crash. If your RAM is going to run out of space, use gc.collect() for the garbage collector to collect unused objects in memory to free some space. Store data or features as NumPy arrays instead of lists. Computation on NumPy arrays is much more efficient than lists. CODE from sklearn import neighbors np.random.seed(56) ##########--WRITE YOUR CODE HERE--########## # The following steps are just for your reference # You can write in your own way # # # densely sample keypoints # def sample_kp(shape, stride, size): # return kp # # # extract vocabulary of SIFT features # def extract_vocabulary(raw_data, key_point): # return vocabulary # # # extract Bag of SIFT Representation of images # def extract_feat(raw_data, vocabulary, key_point): # return feat # # # sample dense keypoints # skp = sample_kp((train_data[0].shape[0],train_data[0].shape[1]),(64,64), 8) # vocabulary = extract_vocabulary(train_data, skp) # train_feat = extract_feat(train_data, vocabulary, skp) # test_feat = extract_feat(test_data, vocabulary, skp) train_feat = test_feat = ##########-------END OF CODE-------########## # this block should generate # train_feat and test_feat corresponding to train_data and test_data

Database System Concepts
7th Edition
ISBN:9780078022159
Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan
Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan
Chapter1: Introduction
Section: Chapter Questions
Problem 1PE
icon
Related questions
icon
Concept explainers
Question

We will create this vocabulary by randomly selecting tens or hundreds of thousands of local features from our training set and clustering them with k-means. The number of k-means clusters represents the size of our vocabulary and features. For example, you could begin by clustering a large number of SIFT descriptors into k=50 clusters. This divides the 128-dimensional continuous SIFT feature space into 50 regions. As long as we keep the centroids of our original clusters, we can figure out which region any new SIFT feature belongs to. Our visual word vocabulary is made up of centroids.

Work with Historgrams. We will densely sample many SIFT descriptors for each image. Rather than storing hundreds of SIFT descriptors, we simply count the number of SIFT descriptors that fall into each cluster in our visual word vocabulary. This is accomplished by locating the nearest neighbor k-means centroid for each SIFT feature. Thus, if we have a visual vocabulary of 50 words and detect 200 distinct SIFT features in an image, our bag of SIFT representation will be a histogram of 50 dimensions, with each bin counting how many times a SIFT descriptor was assigned to that cluster. The sum of all bin-counts is 200. The histogram should be normalized so that the magnitude of the bag of features does not change dramatically with image size.

Instead of using SIFT to detect invariant keypoints, which takes time, you should densely sample keypoints in a grid with a specific step size (sampling density) and scale.
Because the bag of SIFT representation has many design decisions and free parameters (number of clusters, sampling density, sampling scales, SIFT parameters, etc.), accuracy may vary.

 

  • Use KMeans in Sklearn to do clustering and find the nearest cluster centroid for each SIFT feature;

  • Use cv2.xfeatures2d.SIFT_create() to create a SIFT object;

  • Use cv2.Keypoint() to generate key points;

  • Use sift.compute() to compute SIFT descriptors given densely sampled keypoints.

  • Be mindful of RAM usage. Try to make the code more memory efficient, otherwise it could easily exceed RAM limits in Colab, at which point your session will crash.

  • If your RAM is going to run out of space, use gc.collect() for the garbage collector to collect unused objects in memory to free some space.

  • Store data or features as NumPy arrays instead of lists. Computation on NumPy arrays is much more efficient than lists.

CODE

from sklearn import neighbors

np.random.seed(56)

##########--WRITE YOUR CODE HERE--##########
# The following steps are just for your reference
# You can write in your own way
#
# # densely sample keypoints
# def sample_kp(shape, stride, size):
# return kp
#
# # extract vocabulary of SIFT features
# def extract_vocabulary(raw_data, key_point):
# return vocabulary
#
# # extract Bag of SIFT Representation of images
# def extract_feat(raw_data, vocabulary, key_point):
# return feat
#
# # sample dense keypoints
# skp = sample_kp((train_data[0].shape[0],train_data[0].shape[1]),(64,64), 8)
# vocabulary = extract_vocabulary(train_data, skp)
# train_feat = extract_feat(train_data, vocabulary, skp)
# test_feat = extract_feat(test_data, vocabulary, skp)

train_feat =
test_feat =

##########-------END OF CODE-------##########
# this block should generate
# train_feat and test_feat corresponding to train_data and test_data
Expert Solution
trending now

Trending now

This is a popular solution!

steps

Step by step

Solved in 2 steps

Blurred answer
Knowledge Booster
Heuristic System
Learn more about
Need a deep-dive on the concept behind this application? Look no further. Learn more about this topic, computer-science and related others by exploring similar questions and additional content below.
Similar questions
Recommended textbooks for you
Database System Concepts
Database System Concepts
Computer Science
ISBN:
9780078022159
Author:
Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan
Publisher:
McGraw-Hill Education
Starting Out with Python (4th Edition)
Starting Out with Python (4th Edition)
Computer Science
ISBN:
9780134444321
Author:
Tony Gaddis
Publisher:
PEARSON
Digital Fundamentals (11th Edition)
Digital Fundamentals (11th Edition)
Computer Science
ISBN:
9780132737968
Author:
Thomas L. Floyd
Publisher:
PEARSON
C How to Program (8th Edition)
C How to Program (8th Edition)
Computer Science
ISBN:
9780133976892
Author:
Paul J. Deitel, Harvey Deitel
Publisher:
PEARSON
Database Systems: Design, Implementation, & Manag…
Database Systems: Design, Implementation, & Manag…
Computer Science
ISBN:
9781337627900
Author:
Carlos Coronel, Steven Morris
Publisher:
Cengage Learning
Programmable Logic Controllers
Programmable Logic Controllers
Computer Science
ISBN:
9780073373843
Author:
Frank D. Petruzella
Publisher:
McGraw-Hill Education