A clean and concise Python implementation of SIFT (Scale-Invariant Feature Transform)
This is an implementation of SIFT (David G. Lowe's scale-invariant feature transform) done entirely in Python with the help of NumPy. This implementation is based on OpenCV's implementation and returns OpenCV
KeyPointobjects and descriptors, and so can be used as a drop-in replacement for OpenCV SIFT. This repository is intended to help computer vision enthusiasts learn about the details behind SIFT.
PythonSIFT has been reimplemented (and greatly improved!) in Python 3. You can find the original Python 2 version in the
legacybranch. However, I strongly recommend you use
master(the new Python 3 implementation). It's much better.
Python 3
NumPy
OpenCV-Python
Last tested successfully using
Python 3.8.5,
Numpy 1.19.4and
OpenCV-Python 4.3.0.
import cv2 import pysiftimage = cv2.imread('your_image.png', 0) keypoints, descriptors = pysift.computeKeypointsAndDescriptors(image)
It's as simple as that. Just like OpenCV.
The returned
keypointsare a list of OpenCV
KeyPointobjects, and the corresponding
descriptorsare a list of
128element NumPy vectors. They can be used just like the objects returned by OpenCV-Python's SIFT
detectAndComputemember function. Note that this code is not optimized for speed, but rather designed for clarity and ease of understanding, so it will take a few minutes to run on most images.
You can find a step-by-step, detailed explanation of the code in this repo in my two-part tutorial:
Implementing SIFT in Python: A Complete Guide (Part 1)
Implementing SIFT in Python: A Complete Guide (Part 2)
I'll walk you through each function, printing and plotting things along the way to develop a solid understanding of SIFT and its implementation details.
I've adapted OpenCV's SIFT template matching demo to use PythonSIFT instead. The OpenCV images used in the demo are included in this repo for your convenience.
python python template_matching_demo.py
Anyone is welcome to report and/or fix any bugs. I will resolve any opened issues as soon as possible.
Any questions about the implementation, no matter how simple, are welcome. I will patiently explain my code to you.
"Distinctive Image Features from Scale-Invariant Keypoints", David G. Lowe
Definitely worth a read!
SIFT was patented, but it has expired. This repo is primarily meant for educational purposes, but feel free to use my code any way you want, commercial or otherwise. All I ask is that you cite or share this repo.
You can find the original (now expired) patent here (Inventor: David G. Lowe. Assignee: University of British Columbia.).