https://github.com/inokinoki/sy32-image-processing
Face detection implemented as a course project
https://github.com/inokinoki/sy32-image-processing
Last synced: 11 months ago
JSON representation
Face detection implemented as a course project
- Host: GitHub
- URL: https://github.com/inokinoki/sy32-image-processing
- Owner: Inokinoki
- Created: 2019-03-11T22:03:55.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2020-07-11T09:24:45.000Z (almost 6 years ago)
- Last Synced: 2025-04-03T20:21:56.288Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 28.2 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# SY32 Image Processing Course Project
This project contains:
- course exercises([TD](/TD))
- homework([TP](/TP))
- final project([facial-detection](/facial-detection))
which are attached to my SY32 Image Processing course.
# Facial Detection
Train a Machine Learning Model to detect faces in images, Support Vector Machine(SVM) as core algorithm, Histogram of Oriented Gradients as feature.
# How to use
1. Download the pre-trained model from project release, put it into the facial-detection folder. You can also train your own using `train.py`.
2. Install dependencies:
```
pip install sklearn sklearn-image numpy
```
3. Unzip `project_test.zip` (and `project_train.zip` if you'd like to train/optimize the model)
4. Run:
```
python test.py
```
or
```
python test.py 1
```
if you only want to test with the `0001.jpg`.
Then you'll get the face description file. There should be position and size info.
And if you choose to detect a single image, the faces in it will be cropped into several files.