Facial Image Processing for Optimized Recognition and age estimation in MATLAB

  • Unique Paper ID: 175462
  • Volume: 11
  • Issue: 11
  • PageNo: 4221-4224
  • Abstract:
  • This paper proposes a hybrid Convolutional Neural Network (CNN) model to enhance facial recognition and age estimation accuracy. Input images are preprocessed by resizing and converting to grayscale, followed by data augmentation to improve generalization. The dataset is divided into training and validation sets. The CNN architecture integrates multiple convolutional layers with batch normalization and ReLU activation, followed by pooling layers for feature extraction. Trained using Stochastic Gradient Descent with Momentum (SGDM) optimizer (learning rate: 0.001, batch size: 25, 100 epochs), the model classifies facial identities (e.g., 'Person 1,' 'Person 2') and age ranges (e.g., 20-25, 30-35). Performance is evaluated via confusion matrices and accuracy metrics. The hybrid CNN leverages deep feature extraction, achieving robust classification for biometric security and age-based authentication. Results demonstrate improved recognition accuracy, validating its efficacy for real-world applications

Copyright & License

Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{175462,
        author = {B.Manoj Kumar Raju and M. Vamsi Krishna and G.Jagadeesh and V. Mohammed Ibrahim},
        title = {Facial Image Processing for Optimized Recognition and age estimation in MATLAB},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4221-4224},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175462},
        abstract = {This paper proposes a hybrid Convolutional Neural Network (CNN) model to enhance facial recognition and age estimation accuracy. Input images are preprocessed by resizing and converting to grayscale, followed by data augmentation to improve generalization. The dataset is divided into training and validation sets. The CNN architecture integrates multiple convolutional layers with batch normalization and ReLU activation, followed by pooling layers for feature extraction. Trained using Stochastic Gradient Descent with Momentum (SGDM) optimizer (learning rate: 0.001, batch size: 25, 100 epochs), the model classifies facial identities (e.g., 'Person 1,' 'Person 2') and age ranges (e.g., 20-25, 30-35). Performance is evaluated via confusion matrices and accuracy metrics. The hybrid CNN leverages deep feature extraction, achieving robust classification for biometric security and age-based authentication. Results demonstrate improved recognition accuracy, validating its efficacy for real-world applications},
        keywords = {Face Dataset, Image Processing Techniques, Deep Learning Techniques, Convolution Neural Network, Classification, Accuracy.},
        month = {April},
        }

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 11
  • PageNo: 4221-4224

Facial Image Processing for Optimized Recognition and age estimation in MATLAB

Related Articles