Project

Age Classification Model Comparison

Tools used

Python
OpenCV
PyTorch
Scikit-learn
NumPy
SVM
CNN
HOG
SIFT
Bag of Visual Words

Evaluated three computer vision approaches for age group classification using traditional machine learning and deep learning techniques.

Project brief

Designed and conducted a comparative study of three different approaches for classifying facial images into age groups. The project implemented a Support Vector Machine (SVM) using Histogram of Oriented Gradients (HOG) features, a Bag of Visual Words (BoVW) model with SIFT feature extraction, and a Convolutional Neural Network (CNN). Each model was trained, evaluated and compared using the same dataset, analysing classification accuracy, computational performance and trade-offs between traditional computer vision techniques and modern deep learning methods.