Micro-expression recognition is an essential task in facial expression analysis that provides insight into human emotional states. However, traditional micro-expression recognition techniques require significant computational resources and time-consuming training processes, making them unsuitable for real-time and lightweight applications. To address this issue, this paper proposes a novel lightweight micro-expression recognition approach using composite databases. The proposed method leverages a combination of multiple public micro-expression databases to improve recognition performance while reducing computational costs. Our experimental results demonstrate the effectiveness of the proposed approach on the CASME II, CASME, SMIC, and SAMM micro-expression databases.
Micro-expression recognition, Lightweight, Composite databases, CASME II, CASME, SMIC, SAMM.
IRE Journals:
Malik Jawarneh
"Recognizing Micro-Expressions on Composite Databases with a Lightweight Approach" Iconic Research And Engineering Journals Volume 6 Issue 10 2023 Page 627-635
IEEE:
Malik Jawarneh
"Recognizing Micro-Expressions on Composite Databases with a Lightweight Approach" Iconic Research And Engineering Journals, 6(10)