Python Image Processing Cookbook

Finding similarity between an image and a set of images with SIFT

You will use SIFT keypoints/descriptors to compute the similarity between two images (using opencv-python). Here are the steps that you will need to follow:

1. First, read the query image. Also, read all of the images from the search directory to find the best possible matches:

query = cv2.imread("images/query.jpg")                                                                  matched_images = defaultdict(list)                                                                  for image_file in glob.glob('images/search/*.jpg'):                                                   search_image = cv2.imread(image_file)                                                       

The query image is shown here:

2. Extract the SIFT keypoints and descriptors for the query image and all of the search images using the following ...