Computer Vision PS4 Solution

Description

Setup

Note that we will be using a new conda environment for this project!

1. Install Miniconda. It doesn’t matter whether you use Python 2 or 3 because we will create our own environment that uses 3 anyways.

2. Open the terminal

1. 1. On Windows: open the installed Conda prompt to run the command.

1. 2. On MacOS: open a terminal window to run the command

1. 3. On Linux: open a terminal window to run the command

3. Navigate to the folder where you have the project

• 1. 1. (6 points) Demonstrate the output of the function applied to the image im1.jpg to detect circles of radii 75, 90, 100 and 143 by setting useGradient to True and False. In each case, display the images with the detected circle(s), labeling the figure with the circumference and center. Include the outputs for each case in your report.

• 1. 2. (4 points) Experiment with the threshold values to determine circle parameters from the accu-mulator array. In your report include images of the selected circles along with the corresponding Hough Space for low ( 0.4), mid-range ( 0.7) and high ( 0.95) thresholds. Explain how your results vary with increasing thresholds and why that may be the case. You can set useGradient to either True or False.

• 3. (10 points) Circle detection on real images. Demonstrate the output of the function applied to the real image biliards.jpg. Check if your implementation is capable of identifying the balls by varying the radii in the range 17-20. You might have to modulate the threshold parameter for this part –

Code: The score for each part is provided below. Please refer to the submission results on Gradescope for a detailed breakdown.

Part 1: Color Quantization		25
Part 2: Circle Detection		40
Extra Credit		10
Total		65 (+10)

Submission Instructions and Deliverables

Code zip: The following code deliverables will be uploaded as a zip file on Gradescope.

Deliverables

1. proj4_code/quantization_student.py

1. 1. quantizeRGB()

1. 2. quantizeHSV()

1. 3. computeQuantizationError()

2. proj3_code/detect_circles_student.py

1. 1. detectCircles()

3. proj4_code/proj4.ipynb

Do not create this zip manually! You are supposed to use the command python zip_submission.py –gt_username <username> for this.

Report: The final thing to upload is the PDF export of the report on gradescope.

To summarize, the deliverables are as follow:

• Submit the code as zip on Gradescope at PS4 – Code

• Submit the report as PDF on Gradescope at PS4 – Report. Please refer to the pptx template where we have detailed the points associated with each question.

There is no submission to be done on Canvas. Good luck!

This iteration of the assignment is developed by Prithvijit Chattopadhyay and Judy Hoffman. This assignment was originally developed by James Hays, Samarth Brahmbhatt, and John Lambert, and updated by Judy Hoffman, Mitch Donley, and Vijay Upadhya.

5