An EEG-Based Image Annotation System

Parekh, V., Subramanian, R., Roy, D. and Jawahar, C. V. (2018) An EEG-Based Image Annotation System. In: 6th National Conference on Computer Vision, Pattern Recognition, Image Processing, and Graphics, Mandi, India, 16-19 Dec 2017, pp. 303-313. (doi:10.1007/978-981-13-0020-2_27)

162412.pdf - Accepted Version



The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20–200 ms, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training.

Item Type:Conference Proceedings
Glasgow Author(s) Enlighten ID:Subramanian, Dr Ramanathan
Authors: Parekh, V., Subramanian, R., Roy, D., and Jawahar, C. V.
College/School:College of Science and Engineering > School of Computing Science
Copyright Holders:Copyright © 2018 Springer Nature Singapore Pte Ltd
First Published:First published in Computer Vision, Pattern Recognition, Image Processing, and Graphics, Communications in Computer and Information Science book series (CCIS, volume 841):303-313
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher

University Staff: Request a correction | Enlighten Editors: Update this record