https://github.com/abhayvashokan/live-face-recognition
Live training and recognition of faces using convolutional neural network.
https://github.com/abhayvashokan/live-face-recognition
cnn face-recognition opencv
Last synced: 2 months ago
JSON representation
Live training and recognition of faces using convolutional neural network.
- Host: GitHub
- URL: https://github.com/abhayvashokan/live-face-recognition
- Owner: AbhayVAshokan
- Created: 2019-08-17T10:57:48.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2022-12-08T07:51:45.000Z (over 3 years ago)
- Last Synced: 2025-07-29T20:29:47.498Z (11 months ago)
- Topics: cnn, face-recognition, opencv
- Language: Python
- Homepage:
- Size: 148 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Live-Face-Recognition
> Live training and recognition of faces using convolutional neural network.
`tkinter` library is used for creating the user interface for the project.
During image generation, the head region of the new user is cropped using Haarcascade classifier. A Gaussian blur filter is applied and it is resized to 64x64. Finally the image is normalized bu dividing it with 255.
A custom CNN model is created with 2 convolution, 2 max-pooling and 3 dense layers due to limitations from the computational point of view for the training process. This model is used for face recognition during test.
#### Setup
```
pip install -r requirements.txt
```