Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# 🧠 FaceGNN v1.1
|
| 6 |
+
|
| 7 |
+
FaceGNN is a graph-based facial recognition system that combines deep learning feature extraction with Graph Neural Networks (GNNs) for robust identity classification. It supports embedding generation via FaceGNN and offers a reliable system.
|
| 8 |
+
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
## 📊 Project Overview
|
| 12 |
+
|
| 13 |
+
This study proposes a novel approach for face recognition by leveraging Graph Neural Networks (GNNs) to classify face embeddings extracted from face images. The methodology comprises three main phases:
|
| 14 |
+
- (1) dataset preparation and embedding generation.
|
| 15 |
+
- (2) graph construction using k-Nearest Neighbors (k-NN).
|
| 16 |
+
- (3) training and evaluation of a GNN-based classifier.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
|
| 20 |
+
## 🖼️ Model Architecture
|