https://github.com/prashant0598/face-recognition
Face Recognition Project made in Machine Learning using KNN algorithm and open cv for python
https://github.com/prashant0598/face-recognition
face-detection knn-classification machine-learning
Last synced: 12 months ago
JSON representation
Face Recognition Project made in Machine Learning using KNN algorithm and open cv for python
- Host: GitHub
- URL: https://github.com/prashant0598/face-recognition
- Owner: prashant0598
- Created: 2017-09-03T05:48:41.000Z (almost 9 years ago)
- Default Branch: master
- Last Pushed: 2019-03-15T04:19:34.000Z (about 7 years ago)
- Last Synced: 2025-04-14T02:33:50.165Z (about 1 year ago)
- Topics: face-detection, knn-classification, machine-learning
- Language: Jupyter Notebook
- Size: 271 KB
- Stars: 21
- Watchers: 2
- Forks: 20
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Contributing: Contributing.md
Awesome Lists containing this project
README
[](http://hits.dwyl.io/{prashant0598}/{https://github.com/prashant0598/Face-Recognition})
[](https://github.com/ellerbrock/open-source-badges/)
# Face-Recognition :boy: :movie_camera:
Face Recognition using KNN algorithm and open cv for python.This is a implementation of knn classifier.
## Breakdown of the code for knn classifier
1. Importing libraries
2. Create some data for classification
3. Write the kNN workflow
4. Finally, run knn on the data and observe results
## Dependencies
Python 2.7 and OpenCv
## How it works! :wink:
* Run record_faces.py on the command line.The script will open a camera window.Stand in front of the camera until recording of the face is completed.
* The default file where the features are stored is face_01.npy. You can change the file name if you want to store information of many persons.It stores data in a numpy matrix.
* Open the face_recognition.py file and edit your name in the dictionary value corresponding to the number in which your face was stored i.e. for face_01,add your name to '0' value in the names dictionary.
* Run the face_recognition.py file!
## Accuracy :tada:
* 98.4 (using knn) because of small dataset.
* Taking distance from webcam and quality of light into consideration it would give 90+ accuracy.
## License
[MIT](https://prashant0598.mit-license.org)