Skip to content

We used a dataset of facial images with ages and trained a deep learning model to predict a person’s age from their face. The model’s accuracy was checked by comparing its predictions to the actual ages.

Notifications You must be signed in to change notification settings

dark-devil9/age-detection-cnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

.....

🧠 Age Detection Using Deep Learning

This project predicts a person’s age based on their facial image using a Convolutional Neural Network (CNN). It includes training the model on the UTKFace dataset and deploying it in a real-time webcam-based application.

📌 Features

  • Predicts age from facial images using CNN
  • Trained on the UTKFace dataset (20K+ images)
  • Real-time age detection via webcam using OpenCV
  • Age range classification for clearer output (e.g., "10–20", "28–45")

🖼 Dataset

  • Name: UTKFace Dataset
  • Size: ~20,000 facial images
  • Labels: Age (0–116), Gender, Ethnicity (only Age used here)
  • Format: age_gender_ethnicity_date.jpg (age is extracted from the filename)

🧪 Model Architecture

The model is a CNN built with TensorFlow/Keras:

About

We used a dataset of facial images with ages and trained a deep learning model to predict a person’s age from their face. The model’s accuracy was checked by comparing its predictions to the actual ages.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published