Summary of Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition, by Enrico Randellini and Leonardo Rigutini and Claudio Sacca’
Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition
by Enrico Randellini, Leonardo Rigutini, Claudio Sacca’
First submitted to arxiv on: 15 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel data augmentation technique to improve facial expression recognition in an automatic way. The authors propose generating synthetic images using GAN models and geometrical transformations, which significantly increases the size of available training datasets. This augmentation is then used to fine-tune pre-trained convolutional neural networks with different architectures. To evaluate the generalization ability of these models, the authors employ an extra-database protocol approach, testing on two separate databases. The results demonstrate average accuracy values of around 85% for the InceptionResNetV2 model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computers better at recognizing people’s facial expressions. Right now, there aren’t many pictures of faces to train computer models, so scientists created a new way to make more fake images by changing and combining real ones. They used special math formulas to create these fake images that look like different emotions (like happy or sad). Then, they used these fake images to teach computers to recognize facial expressions. The results show that this new method works really well, with an accuracy rate of around 85%. |
Keywords
* Artificial intelligence * Data augmentation * Gan * Generalization
