Download the dataset from the link below, and place the following files in the root:
1- eyeGlasses-faces.mat
2- non-eyeglasses-faces.mat
Each mat file contains 1294 (227x227 pixels) images picked randomly from SoF and FERET datasets. We have used 1294 images for training and 389 images for testing. That is for each class.
To start:
-Run demo.m.
For more information, read report.pdf.
Dataset (cropped images from FEET and Sof datasets):
https://www.dropbox.com/s/ho3ev5e8a4khr0h/dataset.zip?dl=0
SoF dataset:
https://sites.google.com/view/sof-dataset
FERET dataset:
http://www.itl.nist.gov/iad/humanid/feret/feret_master.html

To test using new test images, please edit 'load_data' file accordingly.

Citation:
-----------

If you use this code, please cite the following paper:
Mahmoud Afifi and Mostafa Korashy. "Eyeglasses shop: Eyeglasses replacement system using frontal face image." Proc. 4th Int'l Conf. Mathematics and Information Science (ICMIS). 2015.

BibTeX
----------
@inproceedings{afifi2015eyeglasses,
title={Eyeglasses shop: Eyeglasses replacement system using frontal face image},
author={Afifi, Mahmoud and Korashy, Mostafa},
booktitle={Proc. 4th Int'l Conf. Mathematics and Information Science (ICMIS)},
year={2015}
}

If you use the training dataset in your work, please cite:

1- Mahmoud Afifi, Abdelrahman Abdelhamed. AFIF4: Deep Gender Classification based on AdaBoost-based Fusion of Isolated. Facial Features and Foggy Faces. Journal of Visual Communication and Image representation, 62, 77-86, 2019.
2- P. J. Phillips, P. J. Rauss, and S. Z. Der, ” FERET (Face Recognition Technology) Recognition Algorithm Development and Test Results”, October 1996. Army Research Lab technical report 995.