---
datasets:
- detection-datasets/fashionpedia
language:
- en
pipeline_tag: object-detection
tags:
- YOLOS
- Object detection
- KYC
- Face detection
base_model:
- hustvl/yolos-small
library_name: transformers
---

# YOLO-Face-4-KYC

A fine-tuned YOLO model for detecting facial features and personal headwear, including glasses, hats, and masks — optimized for identity verification and KYC (Know Your Customer) applications. This model is built upon the YOLOS architecture and trained on a filtered and relabeled subset of the [Fashionpedia dataset](https://huggingface.co/datasets/detection-datasets/fashionpedia), focusing exclusively on categories relevant to liveness verification and facial compliance checks. For more details of the implementation, check out the source code [here](https://github.com/Genereux-akotenou/Yolo-Face-4-Kyc)

## Supported Categories

The model detects the following classes:

```python
CATEGORIES = [
  'face',
  'glasses',
  'hat',
  'mask',
  'headband',
  'head covering'
]
```
<img src="https://raw.githubusercontent.com/genereux-akotenou/Yolo-Face-4-Kyc/master/docs-utils/img1.png" style="width: 15em;"/>