Giter Club home page Giter Club logo

face-recognition-low-res's Introduction

Low-resolution Face Recognition & Identification using Super-Resolution

readme-pic.png

  • A face recognition & identification program intended to detect & identify faces from pictures that are of size 30x30 pixels using EDSR image super-resolution.

  • Achieved accuracy of at least 90% on samples across 30 distinct faces.

  • All faces have been taken from the LFW3D face samples, real-life faces are used as well

    • Take note that some personal info (especially the real-life faces) have been redacted from the samples & documentation.

Technologies Used

  • Python
  • OpenCV
  • EDSR (Enhanced Deep Residual Networks) image super-resolution
  • Bicubic & nearest neighbor scaling

Installation

  • Download the repository and unzip it
  • Install Anaconda Python IDE
  • Install relevant libraries
  • Select the version to run (for KNN model, use the knn-version; for SVM model, use the svm-version)
  • Open the relevant .ipynb notebook in the folder in sequence

Credits

  • LFW3D for the faces supplied
  • Mr. Geitgey for his high-resolution face recognition & identification trained model.

face-recognition-low-res's People

Contributors

lshun avatar

Stargazers

avatar

Watchers

avatar avatar

face-recognition-low-res's Issues

Any suggestions for improving the speed and accuracy of facial recognition?

I'm using svm version and ai as the detection mode here. The accuracy here is a bit off as sometimes even completely different people are falsely recognized as someone else. Also it's taking a bit too long for recognizing each image.
Summary

Total pictures 48
Faces identified correctly: 25
Faces identified wrongly: 13
Faces not identified: 10
Absolute Accuracy (correct / [correct + incorrect + not detected]) * 100%:
52.0 %
Detection Accuracy [(correct + incorrect) / total] * 100%:
79.17 %
END, time taken: 6795.78 seconds
Avg. secs. per picture: 141.58 seconds

Process finished with exit code 0

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.