Goal: Learn how to implement image alignment

• • Align two images by feature matching, find their homography, and warp the transformed image into an aligned image.

Readings and sample codes

• • Image Alignment (Feature Based) using OpenCV (C++/Python)

Program and test images

• • Prepare two images for one object. One image is aligned image, another one is a transformed image that can be scaled, rotated, translated and perspectively transformed.

  • To find the homography between the two images, you need to perform keypoint feature matching.

    • Use at least two keypoint methods.

    • Use at least two feature matching methods.

Web Report

• • Create a web page with descriptions, explanation and pictures for your programs. 

  • Requirements of the report page:

    • For each program code, you have to write 4 parts: (1) goal of this code, (2) theory and principle of the code, (3) code segment explanation, and (4) result comparison or analysis.

    • Use your image to run your programs. 

    • Compare and discuss the result images, and explain why the change of methods can produce different results.

    • Conclude with your best results.

  • Submit your web address by Microsoft Teams.