Morphological Convolutional Neural Network for Efficient Facial Expression Recognition
Robert, Sarifuddin Madenda, Suryadi Harmanto, Michel Paindavoine, Dina Indarti · 2026
Read Morphological Convolutional Neural Network for Efficient Facial Expression Recognition by Robert, Sarifuddin Madenda, Suryadi Harmanto, Michel Paindavoine, Dina Indarti (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13117524.txt.
Description
Robert and co-authors add shape-based features to a neural network that reads facial expressions. Their 2026 paper argues that standard networks lean on surface appearance, which shifts with lighting and face type. Shape structure, drawn from the outline of features, could add a steadier signal alongside it.
The team built a data set from five public collections plus a new Indonesian one: three thousand six hundred eighty-four images from three hundred twenty-six people across seven expressions. Tests used subject-independent splits so no person appeared in both training and scoring. Their best model reached about eighty-nine percent accuracy, level with strong baselines. It also ran with lower delay and far less graphics memory. The authors present the design as a lean option for real-time use.
Catalog record
| CREATOR | Robert, Sarifuddin Madenda, Suryadi Harmanto, Michel Paindavoine, Dina Indarti |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |