Summary of Surveying Facial Recognition Models For Diverse Indian Demographics: a Comparative Analysis on Lfw and Custom Dataset, by Pranav Pant et al.
Surveying Facial Recognition Models for Diverse Indian Demographics: A Comparative Analysis on LFW and Custom Dataset
by Pranav Pant, Niharika Dadu, Harsh V. Singh, Anshul Thakur
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 A recent paper explores the effectiveness of facial recognition technology across various ethnic backgrounds, focusing on specific Indian demographics. The study uses two datasets: LFW and JFAD, a newly developed dataset comprising images of students from IIT Jodhpur. The authors evaluate traditional and deep learning-based models, including Eigenfaces, SIFT, CNNs, Gabor filters, Laplacian transforms, and segmentation techniques. The results show that these models struggle to adapt to Indian ethnic variability, highlighting the need for modifications to improve accuracy and inclusivity in real-world applications. The JFAD dataset serves as a valuable resource for further research, emphasizing the importance of developing facial recognition systems that perform equitably across diverse populations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new study looks at how well facial recognition technology works for people from different ethnic backgrounds, specifically focusing on India. Researchers used two big collections of pictures: one they’ve been using before (LFW) and a new one they made themselves (JFAD). This new dataset has photos of students from IIT Jodhpur, which helps test how well the technology works for Indian people. The study shows that these facial recognition systems aren’t very good at recognizing faces that are different from what they’re used to seeing. This highlights a problem: we need better ways to recognize faces that work equally well for everyone, no matter where they’re from. |
Keywords
* Artificial intelligence * Deep learning
