Reconstructing Visual Stimulus Images from EEG Signals Based on Deep Visual Representation Model

TL;DR

The results show that the DVRM have good performance in the task of learning deep visual representation from EEG signals and generating reconstructed images that are realistic and highly resemble the original images.

Abstract

Reconstructing visual stimulus images is a significant task in neural decoding, and up to now, most studies consider the functional magnetic resonance imaging (fMRI) as the signal source. However, the fMRI-based image reconstruction methods are difficult to widely applied because of the complexity and high cost of the acquisition equipments. Considering the advantages of low cost and easy portability of the electroencephalogram (EEG) acquisition equipments, we propose a novel image reconstruction method based on EEG signals in this paper. Firstly, to satisfy the high recognizability of visual stimulus images in fast switching manner, we build a visual stimuli image dataset, and obtain the EEG dataset by a corresponding EEG signals collection experiment. Secondly, the deep visual representation model(DVRM) consisting of a primary encoder and a subordinate decoder is proposed to reconstruct visual stimuli. The encoder is designed based on the residual-in-residual dense blocks to learn the distribution characteristics between EEG signals and visual stimulus images, while the decoder is designed based on the deep neural network to reconstruct the visual stimulus image from the learned deep visual representation. The DVRM can fit the deep and multiview visual features of human natural state and make the reconstructed images more precise. Finally, we evaluate the DVRM in the quality of the generated images on our EEG dataset. The results show that the DVRM have good performance in the task of learning deep visual representation from EEG signals and generating reconstructed images that are realistic and highly resemble the original images.

Figures (7)

• Figure 1: The visual stimulus images (62 types of characters, and 50 fonts of each character).
• Figure 2: The experiment diagram of EEG signals acquisition.
• Figure 3: The experimental paradigm: (a) The experimental paradigm about images of numbers; (b) The experimental paradigm about images of letters.
• Figure 4: The framework of DVRM. (a) Training process: $X$ and $Y$ are input to the encoder to obtain $Z$, which is used to reconstruct $X$ through the decoder. (b) Test process: $Y^{*}$ is encoded to $Z^{*}$ by the pretrained encoder. For $Z^{*}$, the pretrained decoder can reconstruct $X^{pred}$.
• Figure 5: The confusion matrixes of our RRDB-based encoder.

Theorems & Definitions (1)

• Remark 1