Visually Evoked EEG Classification and Perceived Image Regeneration using Deep Learning for Brain Fingerprinting

Project Title: Visually Evoked EEG Classification and Perceived Image Regeneration using Deep Learning for Brain Fingerprinting

Grant No.: SPR/2022/000154

Investigators: Dr. Shamama Anwar (PI), Dr. Vandana Bhattacharya (Co-PI)

Sanction Amount: 24,15,705

Duration: 3 years (25-April-2023 to 24-April-2026)

Summary: Brain fingerprinting is a scientific method for detecting hidden information stored in the brain by non-invasively measuring electroencephalographic (EEG) brain responses, or brainwaves, with sensors placed on the scalp. The technique entails displaying phrases, expressions, or images enclosing pertinent description about a crime scenario on a computer screen in succession with other, irrelevant stimuli. The brain's responses to stimuli are analysed. When the brain interprets information about particular aspects, the computer tries to analyse the brain responses that can discern distinctive feature of brainwave patterns. When a person recognises something as significant in the current context, the response is characterized by a specific brainwave pattern. In a brain fingerprinting test, words or pictures relevant to a crime scene are presented on a computer screen, in a series with other, irrelevant words or pictures.  The brainwave responses of subjects to these stimuli are measured non-invasively with a headset equipped with EEG sensors. This concept can further be enhanced by allowing the generation of these perceived images based on the EEG acquired while viewing the image. The primary objective of the project proposal is to derive some cues from brain activity recorded using an EEG recording and use them to classify, visualize and generate an image of an object a person has viewed.

Objectives:

  1. Development of EEG classification algorithms using deep learning techniques to identify the object the user was viewing while the EEG signal was being generated.
  2. Reconstruction / Regeneration of the image the user was viewing while the EEG was being captured.
  3. Development of a user-friendly software to aid in brain fingerprinting for crime scene investigations.