Eye centre localisation with convolutional neural network based regression

Zhang, Wenhao; Smith, Melvyn

Abstract

This paper introduces convolutional neural network regression models based on the Inception-v3 and the DenseNet architectures for accurate and real-time eye centre localisation. At a normalised error of e < 0.05, the proposed method yields an accuracy of 98.55% on the BioID dataset in a five-fold cross validation test, and 98.50% on the GI4E dataset in a cross-dataset validation test, outperforming the state-of-the-art methods. Both models, capable of running at 44 frames per second, demonstrate an excellent real-time performance. Not only is the proposed method highly accurate and efficient, it does not require invasive and expensive hardware, offering the potential for spawning applications in a wide variety of domains.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC)
• Start Date: Jul 5, 2019
• End Date: Jul 7, 2019
• Acceptance Date: Jun 14, 2019
• Online Publication Date: Feb 6, 2020
• Publication Date: Feb 6, 2020
• Deposit Date: Jul 29, 2019
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Pages: 88-92
• ISBN: 9781728123257
• DOI: https://doi.org/10.1109/ICIVC47709.2019.8980972
• Keywords: eye centre localisation; eye tracking; convolutional neural network; linear regression
• Public URL: https://uwe-repository.worktribe.com/output/1787696