Classifying Eyewear on GAN-Generated Faces Using Convolutional Neural Networks

In today's world of computer vision, Convolutional Neural Networks (CNNs) play a crucial role in analyzing and processing image data. This study explores how CNNs work alongside image data, specifically focusing on classifying eyewear on GAN-generated faces. By harnessing CNNs' ability to extract hierarchical features from images and the capability of Generative Adversarial Networks (GANs) to create realistic synthetic data, this research highlights advancements in image classification tasks. The study evaluates the performance of various machine learning algorithms in classifying eyewear on GAN-generated faces. Results show that Ridge regression, Lasso regression, and Support Vector Machines perform well on tabular data, with Ridge regression achieving the highest accuracy. Shifting to image data, CNNs outshine feedforward neural networks (FFNN), especially those with multiple convolutional layers. This underscores the importance of leveraging CNN architectures for accurate image classification tasks, with potential applications in e-commerce and virtual try-on systems.

Authors

Institutions

Publication Details

Journal
STARS (University of Central Florida)
Published
2026-11-20
Primary Topic
Advanced Neural Network Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Classifying Eyewear on GAN-Generated Faces Using Convolutional Neural Networks

Poorna Sandamini Senaratne, Shahd Alnofaie
STARS (University of Central Florida)
Advanced Neural Network Applications
article

Classifying Eyewear on GAN-Generated Faces Using Convolutional Neural Networks

Poorna Sandamini Senaratne, Shahd Alnofaie
article en

Abstract

In today's world of computer vision, Convolutional Neural Networks (CNNs) play a crucial role in analyzing and processing image data. This study explores how CNNs work alongside image data, specifically focusing on classifying eyewear on GAN-generated faces. By harnessing CNNs' ability to extract hierarchical features from images and the capability of Generative Adversarial Networks (GANs) to create realistic synthetic data, this research highlights advancements in image classification tasks. The study evaluates the performance of various machine learning algorithms in classifying eyewear on GAN-generated faces. Results show that Ridge regression, Lasso regression, and Support Vector Machines perform well on tabular data, with Ridge regression achieving the highest accuracy. Shifting to image data, CNNs outshine feedforward neural networks (FFNN), especially those with multiple convolutional layers. This underscores the importance of leveraging CNN architectures for accurate image classification tasks, with potential applications in e-commerce and virtual try-on systems.

STARS (University of Central Florida)
University of Central Florida (US)
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon