added Chess piece classifcation using machine learning

[RajKhanke]

Resolves issue #958

This project involves developing a machine learning application to classify chess pieces from images using a Convolutional Neural Network (CNN). The process begins with collecting and preprocessing a dataset of chess piece images, including various classes such as bishop, king, knight, pawn, queen, and rook. The images are resized, normalized, and split into training and validation sets to train the CNN model. The model's performance is evaluated based on accuracy, precision, recall, and F1 score.

For real-time predictions, a Streamlit application is created. Users can upload images of chess pieces, which are then processed and classified by the trained model. The application displays the prediction result in a styled success box with bold white text, and also provides additional information about the identified chess piece. The project integrates image preprocessing, model inference, and user interaction, showcasing how machine learning models can be deployed in web applications for practical use cases.

CNN model is trained over batch size = 128 ,with 100 epochs input image size =(128,128,3) achieved average validation accuracy of 97.11 %

Dataset :

https://www.kaggle.com/datasets/akshayramakrishnan28/cataract-classification-dataset/data

#Demo :

webapp.mp4

[github-actions]

Thank you for submitting your pull request! 🙌 We'll review it as soon as possible. If there are any specific instructions or feedback regarding your PR, we'll provide them here. Thanks again for your contribution! 😊

[RajKhanke]

@Niketkumardheeryan @invigorzz313 please merge this pr along with level and label of gssoc'24. it will resolve issue no 958

[RajKhanke]

@Niketkumardheeryan @invigorzz313 please take alook towards my other pr of student performance prediction as well