Skip to content

Face Recognition with SVM classifier using PCA, ICA, NMF, LDA reduced face vectors

Notifications You must be signed in to change notification settings

tulsyanp/tcd-ai-group-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Face Recognition

Face Recognition with SVM classifier using PCA, ICA, NMF, LDA reduced face vectors

Repository Structure

  • The folders PCA, ICA, NMF, LDA and DATASET consists of all the images and classification report for ech algorithm respectively.
  • The files pca.py | ica.py | nmf.py | lda.py consists of algorithm implementation for each algorithm respectively.
  • The document Report.docx present in the root of the source code contains all the textual document of the project.
  • The document todo-mom.docx present in the root of the source code contains all the todos of each individual and minutes of meeting of the group.
  • The requirements.txt file contains the project dependencies.

Dependencies

  • Python3
  • Run pip install -r requirements.txt to install required Python libraries

Steps to run each algorithm individually

  • Clone the repository
  • Run pip install -r requirements.txt to install required Python libraries
  • For PCA, run the command python pca.py
  • For ICA, run the command python ica.py
  • For NMF, run the command python nmf.py
  • For LDA, run the command python lda.py

Experimental Result

Dataset used

PCA (Principal Component Analysis)

Eigenfaces Prediction Classification Report
Eigenface generated Prediction Classification report

LDA (Linear Discriminant Analysis)

FisherFaces Prediction Classification Report
Fisherface generated Prediction Classification report

ICA (Independent Component Analysis)

Eigenfaces Prediction Classification Report
Eigenface generated Prediction Classification report

NMF (Non-negative Matrix Factorization)

Eigenfaces Prediction Classification Report
Eigenface generated Prediction Classification report

Comparison of above algorithms (Accuracy and Training time)

Comparion_report

Group Members

  1. Prateek Tulsyan - 19303677
  2. Mrinal Jhamb - 19301913
  3. Shubham Dhupar - 19304374
  4. Rushikesh Joshi - 19300976