Project 3: Detecting Harris Corners and Matching Images
CS 342: Computer Vision

Brief

• Due: 14-March-2020 at 11:59 PM
• Project materials: proj3.zip.
• Turn In: through Google Classroom
• Required files: submission.zip

Overview

The goal of this project is to write two methods: first one for finding harris corners then for creating key points (with gradient) from these corners. You must provide two similar (but not same) photos taken by you for this project.

Setup

1. Run the notebook using:
   jupyter notebook ./code/proj3.ipynb
2. Generate the submission once you've finished the project using:
   python zip_submission.py

Forbidden functions cv2.cornerHarris() (you can use this for testing, but not in your final code)
Ask me if you have any question.
YOU MUST NOT USE ANY CODE FOUND ONLINE. You will get a zero (0) for the project if we find any violation to academic integrity policy, and there won't be any exception. A second violation will cause a failing Grade.
Editing Code: You need to implement two methods. You can also work on improving the effiency of the third method, for extra credit. You may use a simple text editor like Sublime Text, an IDE like PyCharm, or even just editing the code in browser from the iPython notebook home page. Google "Python editor" to find a litany of additional suggestions.

Writeup

For this project, and all other projects, you must do a project report. In the report you will describe your algorithm and any decisions you made to write your algorithm a particular way. If you are using the 'preprocess' method, explain, what are the parameters you are usign and why. In the case of this project, show the results of your running the algorithm on the given images and it's output. NOTE: You must add the resultant images to the document. Also, discuss anything additional that you did. Feel free to add any other information you feel is relevant. You must include all the images produced by the Jupyter Notebook. A good writeup doesn't just show results, it tries to draw some conclusions from your experiments.

Rubric

• +60 pts: Working implementation of Harris Corner Detection
• +40 pts: Working implementation of Key Points generation.
• -5*n pts: Lose 5 points for every time you do not follow the instructions for the turn in format

Turning in

This is very important as you will lose points if you do not follow instructions. Every time after the first that you do not follow instructions, you will lose 5 points. The folder you hand in must contain the following:

• code/ - directory containing all your code for this assignment
• results/ - directory containing your results (generated by the notebook) and your REPORT. The report should be submitted in PDF format.
• data/ - directory containing images you have taken.

Do not use absolute paths in your code (e.g. /user/abc/classes/CompVision/proj1). Your code will break if you use absolute paths and you will lose points because of it. Simply use relative paths as the starter code already does. Do not turn in the /data/ folder unless you have added new data. Hand in your project as a zip file through Google Classroom. You can create this zip file using
python zip_submission.py.