---
language: en
tags:
  - image-classification
  - face-mask-detection
  - mobilenetv2
  - tensorflow
  - computer-vision
  - safety
license: mit
---

# Face Mask Detection — MobileNetV2

An AI model that classifies whether a person is:
- ✅ **Wearing a mask correctly**
- ❌ **Not wearing a mask**
- ⚠️ **Wearing a mask improperly**

## Model Details
- **Architecture**: MobileNetV2 + custom classification head
- **Input**: 224×224 RGB image (face crop)
- **Classes**: `with_mask`, `without_mask`, `mask_worn_incorrectly`
- **Framework**: TensorFlow/Keras

## Usage
```python
import tensorflow as tf
import numpy as np
from PIL import Image

model = tf.keras.models.load_model("face_mask_model.h5")
img   = Image.open("face.jpg").resize((224, 224))
arr   = np.expand_dims(np.array(img), 0) / 255.0
pred  = model.predict(arr)
print(["with_mask","without_mask","mask_worn_incorrectly"][pred.argmax()])
```

## Live Demo
Try the interactive demo on [Spaces](None/face-mask-detection-demo).