Scholarlink

<p>This study explores how differences in colors presented separately to each eye (binocular color differences) can be identified through EEG signals, a method of recording electrical activity from the brain. Four distinct levels of green-red color differences, defined in the CIELAB color space with constant luminance and chroma, are investigated in this study. Analysis of Event-Related Potentials (ERPs) revealed a significant decrease in the amplitude of the P300 component as binocular color differences increased, suggesting a measurable brain response to these differences. Four classification models—Support Vector Machines (SVM), EEGNet, Temporal Convolutional Neural Network (T-CNN), and a hybrid CNN-LSTM model were employed to decode EEG data. The highest accuracy reached was 81.93% for binary classification tasks (the largest color differences) and 54.47% for a more nuanced four-class categorization, significantly exceeding random chance. This research offers the first evidence that binocular color differences can be objectively decoded through EEG signals, providing insights into the neural mechanisms of visual perception and forming a basis for developing color-based brain-computer interfaces (BCIs).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decoding binocular color differences via EEG signals: linking ERP dynamics to chromatic disparity in CIELAB space

  • 期刊论文

  • 发表日期：

    2025年9月10日

查看全文
  • Famiao Mou,
  • Zhineng Lv,
  • Xuesong Jin,
  • Jijun Pan,
  • Lijun Yun,
  • Zaiqing Chen

摘要

This study explores how differences in colors presented separately to each eye (binocular color differences) can be identified through EEG signals, a method of recording electrical activity from the brain. Four distinct levels of green-red color differences, defined in the CIELAB color space with constant luminance and chroma, are investigated in this study. Analysis of Event-Related Potentials (ERPs) revealed a significant decrease in the amplitude of the P300 component as binocular color differences increased, suggesting a measurable brain response to these differences. Four classification models—Support Vector Machines (SVM), EEGNet, Temporal Convolutional Neural Network (T-CNN), and a hybrid CNN-LSTM model were employed to decode EEG data. The highest accuracy reached was 81.93% for binary classification tasks (the largest color differences) and 54.47% for a more nuanced four-class categorization, significantly exceeding random chance. This research offers the first evidence that binocular color differences can be objectively decoded through EEG signals, providing insights into the neural mechanisms of visual perception and forming a basis for developing color-based brain-computer interfaces (BCIs).