Discomfort analysis of liminal space images

Ayana Sonoda; Kazuya Ueki

doi:10.1117/12.3018211

2 May 2024 Discomfort analysis of liminal space images

Ayana Sonoda, Kazuya Ueki

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 131640R (2024) https://doi.org/10.1117/12.3018211
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

Images of liminal spaces became viral on the Internet around May 2019 as images that made people feel uncomfortable. In this study, we first collected images of liminal spaces and trained a model to recognize whether a space was a liminal space using a convolutional neural network. The change in the numerical values of the trained model when various images were input into the model was used to investigate the factors that cause discomfort in the liminal space. The input images were preprocessed by adding people or objects and reducing the brightness. The results showed that the presence or absence of people and objects was closely related to discomfort in the liminal space.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ayana Sonoda and Kazuya Ueki "Discomfort analysis of liminal space images", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 131640R (2 May 2024); https://doi.org/10.1117/12.3018211

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available