EEG2IMAGE: Image Reconstruction from EEG Brain Signals

TL;DR

This paper introduces a novel framework that uses EEG signals and contrastive learning with a conditional GAN to reconstruct images of objects and characters, even with small datasets, advancing BCI technology.

Contribution

It presents a new method combining contrastive learning and a modified GAN to synthesize images from EEG signals using limited data, improving BCI image reconstruction.

Findings

Effective image synthesis from EEG signals demonstrated

Outperforms existing methods on small EEG datasets

Produces 128x128 images with limited training data

Abstract

Reconstructing images using brain signals of imagined visuals may provide an augmented vision to the disabled, leading to the advancement of Brain-Computer Interface (BCI) technology. The recent progress in deep learning has boosted the study area of synthesizing images from brain signals using Generative Adversarial Networks (GAN). In this work, we have proposed a framework for synthesizing the images from the brain activity recorded by an electroencephalogram (EEG) using small-size EEG datasets. This brain activity is recorded from the subject's head scalp using EEG when they ask to visualize certain classes of Objects and English characters. We use a contrastive learning method in the proposed framework to extract features from EEG signals and synthesize the images from extracted features using conditional GAN. We modify the loss function to train the GAN, which enables it to synthesize 128x128 images using a small number of images. Further, we conduct ablation studies and experiments to show the effectiveness of our proposed framework over other state-of-the-art methods using the small EEG dataset.