AI influencers image classification 📷

Overview

This project focuses on developing a face recognition model using Convolutional Neural Network (CNN) and Machine Learning (ML) approaches. Additionally, it aims to compare the performance of Logistic Regression and CNN for image classification tasks.

Key Components

• Developed a CNN model achieving an impressive Accuracy Score of 0.9844.
• Scraped images of 6 AI influencers from Google Images and utilized OpenCV Cascade Classifiers for face detection.
• Implemented Data Augmentation techniques to enhance the robustness of the CNN model.
• Explored a Machine Learning (ML) approach
  • Applied feature extraction using Wavelet transform.
  • Employed K Fold Cross Validation for model selection
  • Trained a Logistic Regression model with an accuracy score of 0.9255.
• Explored Deep Learning (DL) approach:
  • Utilized TensorFlow for data preprocessing and model building.
  • Created and deployed a Web Application for model comparison.

  You can also check out the Jupyter notebook for more details

Results

• CNN Model:
  • Accuracy Score: 0.9844
• Logistic Regression Model:
  • Accuracy Score: 0.9255