# BossSensor

**Repository Path**: xyz-dev-max/BossSensor

## Basic Information

- **Project Name**: BossSensor
- **Description**: Hide screen when boss is approaching.
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-10-11
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# BossSensor
Hide your screen when your boss is approaching.

## Demo
The boss stands up. He is approaching.

![standup](https://github.com/Hironsan/BossSensor/blob/master/resource_for_readme/standup.jpg)

When he is approaching, the program fetches face images and classifies the image.
 
![approaching](https://github.com/Hironsan/BossSensor/blob/master/resource_for_readme/approach.jpg)

If the image is classified as the Boss, it will monitor changes.

![editor](https://github.com/Hironsan/BossSensor/blob/master/resource_for_readme/editor.jpg)

## Requirements

* WebCamera
* Python3.5
* OSX
* Anaconda
* Lots of images of your boss and other person image

Put images into [data/boss](https://github.com/Hironsan/BossSensor/tree/master/data/boss) and [data/other](https://github.com/Hironsan/BossSensor/tree/master/data/other).

## Usage
First, Train boss image.

```
$ python boss_train.py
```


Second, start BossSensor. 

```
$ python camera_reader.py
```

## Install
Install OpenCV, PyQt4, Anaconda.

```
conda create -n venv python=3.5
source activate venv
conda install -c https://conda.anaconda.org/menpo opencv3
conda install -c conda-forge tensorflow
pip install -r requirements.txt
```

Change Keras backend from Theano to TensorFlow. 

## Licence

[MIT](https://github.com/Hironsan/BossSensor/blob/master/LICENSE)

## Author

[Hironsan](https://github.com/Hironsan)