Image interpretation by python

Department of Electrical Engineering and Computer Science

CIS/EEC 693

Computer Vision

Summer 2021

Project 4

(Due date: 06/09/2020)

The objective of this project is to implement the image registration technique. Given two images

image1 and image2, the aim is to register image2 with respect to image1. The registration

problem has to be solved by matching SIFT features extracted from the images.

Inputs: Given images, image1 and image2.

Output: image2 transformed with respect to image1 such that the difference between two

images is minimum.

Tasks to be accomplished:

1. Extract SIFT features from images using a function from OpenCV library or any other library.

2. Match features using naive nearest neighbor approach (function to be implemented) and the

second version of nearest neighbor approach - cv2.BFMatcher().

3. Compute the transformation matrix (affine transformation).

4. Transform image2 such that it aligns with image1.

5. Compute registration error for both feature matching methods.

Analysis question:

Which feature matching algorithm works better and why?

Notes:

• The project should be implemented in Python.

• Only one single file should be submitted through Blackboard for evaluation, which includes:

✓ The project report that includes the methodology, equations used, implementation results and discussion, conclusion, appropriate technical references, etc.

✓ The program codes along with the dataset used for testing and validation.

• Late submissions will not be accepted. • Email submissions will not be accepted.