https://github.com/cliangyu/eye_see_you
A face recognition security system
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.1%) to scientific vocabulary
Repository
A face recognition security system
Basic Info
- Host: GitHub
- Owner: cliangyu
- License: mit
- Language: Python
- Default Branch: main
- Size: 8.79 KB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
eyeseeyou
A face recognition security system
Video demo
Inspiration
Make MLDA@EEE more AI-savvy! We had dreamed of a computer vision for door access control for a long time. Now it's time to implement it!
What it does
We built a hardware system that could detect (and classify) multiple faces in one frame.
This model can detect multiple person in the same frame
Door will only open with the right person detected High accuracy with 90 % True Positive and less than 2 % False Positive Can easily tune the model for security or convenience How we built it We proposed a hardware system based on Raspberry Pi running on Python to detect (and classify) faces. The Raspberry Pi board was connected to a motor that presses door switch to release access. A LED light band is connected to the board, to indicate the validity of the detected faces.
Challenges we ran into
The computing capacity of a single Raspberry Pi is quite limited, which doesn't support high refresh rate detection. We resolved this issue by restricting the resolution to free the computing power.
Accomplishments that we're proud of
This real-time detection model runs on Raspberry Pi High accuracy with 90 % True Positive and less than 2 % False Positive Secure model that can be iterated to finetune further What's next for Eye See You We plan to finetune the model to make it fit for more scenarios of various light ambience.
Built With
python raspberry-pi
Run it on your raspberry-pi board
You need a raspberry-pi board, with a high-res webcam, a motor, and a LED light band to implement the system. Copy open.py to your raspberry-pi board, and run 'sudo python3 open.py'
Learn more at our Devpost page! (https://devpost.com/software/eye-see-you-28nb1x)
Owner
- Name: Liangyu Chen
- Login: cliangyu
- Kind: user
- Location: Singapore
- Company: Nanyang Technological University
- Website: cliangyu.com
- Twitter: cliangyu_
- Repositories: 1
- Profile: https://github.com/cliangyu
GitHub Events
Total
Last Year
Issues and Pull Requests
Last synced: over 1 year ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0