Object Segmentation in Images using EEG Signals

TL;DR

This paper presents a novel method using EEG signals and brain-computer interfaces to assist in object segmentation within images, combining brain activity analysis with image processing algorithms.

Contribution

It introduces a new approach that leverages EEG responses to image regions to improve object boundary detection in images.

Findings

EEG-based responses can indicate object regions in images.

The method effectively combines EEG signals with GrabCut for segmentation.

Brain signals provide useful information for image analysis tasks.

Abstract

This paper explores the potential of brain-computer interfaces in segmenting objects from images. Our approach is centered around designing an effective method for displaying the image parts to the users such that they generate measurable brain reactions. When an image region, specifically a block of pixels, is displayed we estimate the probability of the block containing the object of interest using a score based on EEG activity. After several such blocks are displayed, the resulting probability map is binarized and combined with the GrabCut algorithm to segment the image into object and background regions. This study shows that BCI and simple EEG analysis are useful in locating object boundaries in images.