These days, the demand for online lectures is increasing. For better visual experience, along with the video of the lecture, soft copy of the slides is also being embedded into the video. But most of the universities are manually matching slides from the video to the soft copy which is a laborious task. So the problem statement is to automate this slide matching process

Given a set of noisy slide images extracted from the video and a set of slides from the original ppt. You need to build a mapping for each of the sampled noisy slides with the corresponding original slide.

Refer to the attached report pdf for more details.