What is it about?
A new feature descriptor is designed to extract salient features from human facial expression. The RADAP feature descriptor is able to capture highly robust muscle movements from facial regions. The proposed work is evaluated on 9 different challenging facial expression datasets.
Featured Image
Why is it important?
Our findings show the effectiveness of hand-crafted features in extracting minute variations in different facial expressions. It also holds its own when compared to state-of-the-art deep learning techniques.
Perspectives
Writing and improving this article was a very illuminating experience in terms of how to present a research work. Also multiple reviews by expert reviewers made this article in its final form. We did experiments on 9 different datasets along with results for deep learning techniques as well. We hope, this paper will serve as a benchmark literature comparison for future articles on Facial Expression Recognition.
Murari Mandal
Read the Original
This page is a summary of: RADAP: Regional Adaptive Affinitive Patterns with Logical Operators for Facial Expression Recognition, IET Image Processing, February 2019, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-ipr.2018.5683.
You can read the full text:
Contributors
The following have contributed to this page
