Programming Homework Help

Database: The Celebrities in Frontal-Profile in the Wild (CFPW) dataset contains images of 500 subjects (with 10 frontal images and 4 profile images for each subject). 5000 frontal images were pre-processed using D-lib to crop and align the faces. 37 images had a failure to detect case. All profile images were excluded from this assignment. The final gallery had the following distribution:

You should assume the system is symmetric. For this assignment, you may use the programming language/tool of your choice (R, Python, Matlab, etc) in the analysis of the data. Please indicate which tool/language is being used, and include a text file of code with your submission.

Files needed for this assignment (see Module 2):

• genuines.txt
• impostors.txt
• labels_cleaned.txt
• sim-matrix.txt

Answer the following Question:

1. Plot the genuine and imposter match score distributions.
2. What is the d-prime value for this system?
3. Plot error rates (FMR and FNMR) relative to the threshold and indicate the point (i.e. threshold) where the EER occurs. What is the EER of the system?
4. Using the scores provided in the similarity matrix, summarize the rank-t identification rate for different values of t using the Cumulative Match Characteristic (CMC) curve. (When evaluating each of the 500 subjects as a candidate, use the highest Im_id for that sub_id as the probe; and only the lowest Im_id as a candidate match from the gallery.)
   • What is the rank-1 identification rate?
   • What is the rank-5 identification rate?