Skip to content

SDeyGitHubber/Sports_Person_Classifier

Repository files navigation

Sports_Person_Classifier

In this project, we shall be applying image processing techniques to process a dataset, created by using an extension, called Fatkun. Then, we use image processiing techniques, using libraries, such as OpenCV and pywt(Python Wavelet Transform). We have used algorithms for face and eye detection to aid face recognition, from Haar Cascades, and finally used the best algorithm after testing multiple algorithms, for classification.

Toola and Techniques used:

  • Programming Language: Python
  • IDE Jupyter Notebook
  • Data Analysis: Pandas, Numpy, Seaborn, Matplotlib
  • Webscraping: Fatkun
  • Web App and API: Flask
  • Frontend: HTML, Javascript, and CSS
  • Algorithms and Models: sklearn,haarcascades

Features

  • Used Fatkun extension for scraping images from the web
  • Used multiple models for testing- Support Vector Classifier, Random Forest Classifier, and Logistic Regression; performed Hyperparameter tuning on each and finally dumped the best model
  • The final model achieved an accuracy of 86.84%( logistic regression)
  • Developed a frontend, having a responsive webpage and a feature of uploading an image for classification

A glimpse of the webpage

Sports.Person.Classifier.-.Personal.-.Microsoft.Edge.2023-07-09.18-54-02.mp4

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages