Deep learning-based multi-object association retrieval

Dong Cui; Zhihui Wang; Caixia Wang; Daoerji Fan; Huijuan Wu

doi:10.1117/12.2637763

13 May 2022 Deep learning-based multi-object association retrieval

Dong Cui, Zhihui Wang, Caixia Wang, Daoerji Fan, Huijuan Wu

Proceedings Volume 12248, Second International Conference on Sensors and Information Technology (ICSI 2022); 1224817 (2022) https://doi.org/10.1117/12.2637763
Event: 2nd International Conference on Sensors and Information Technology (ICSI 2022), 2022, Nanjing, China

Abstract

Advances in computer technology and artificial intelligence have led to a surge in the volume and complexity of multimedia data, and content-based image retrieval systems (CBIR) have become widely popular to extract useful information from this data. Traditional CBIR systems are implemented by inter-image features and cannot perform associative image retrieval. Therefore, in this paper, we propose a new method for associative image retrieval by mimicking the human brain mechanism. By using an improved deep residual network to extract different kinds of image features, and using a loss function to maximize the feature distance loss between non-associative image groups and minimize the loss between associative image groups, and finally using the trained model to achieve multi-objective associative retrieval.

Citation Download Citation

Dong Cui, Zhihui Wang, Caixia Wang, Daoerji Fan, and Huijuan Wu "Deep learning-based multi-object association retrieval", Proc. SPIE 12248, Second International Conference on Sensors and Information Technology (ICSI 2022), 1224817 (13 May 2022); https://doi.org/10.1117/12.2637763

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