[Feat] Malaria Cells Classification using CNN and Transfer Learning

[IkkiOcean]

Malaria Cells Classification using CNN and Transfer Learning

Is your feature request related to a problem? Please describe.
Malaria is a life-threatening disease caused by parasites that are transmitted through the bites of infected female Anopheles mosquitoes. Early and accurate detection of malaria is crucial for effective treatment. Classifying malaria-infected cells using machine learning can help automate and improve the accuracy of diagnosis. The challenge is to develop a model that can accurately classify healthy and infected cells.

Describe the solution you'd like
I propose building a classification model using CNN and Transfer Learning (VGG16). The CNN model will be trained from scratch, while VGG16 will be fine-tuned to leverage pre-trained weights on large image datasets. Both models will be compared to determine which offers better accuracy for malaria cell classification. The dataset will consist of microscopic images of red blood cells, labeled as infected or healthy.

Describe alternatives you've considered
An alternative solution is using other pre-trained models such as ResNet or Inception, but VGG16 is chosen for its balance between performance and computational efficiency in medical image classification tasks. Further optimization and hyperparameter tuning could be considered to improve accuracy.

Approach to be followed (optional)

1. Exploratory Data Analysis (EDA) to visualize and understand the dataset.
2. Model Building:
   • CNN architecture to be built from scratch.
   • VGG16 fine-tuning for Transfer Learning.
3. Training & Evaluation:
   • Train both models, tune hyperparameters, and compare the performance using metrics such as accuracy, precision, recall, and F1 score.
4. Visualization & Conclusion:
   • Visualize model performance and results through graphs and tables.

Additional context
The dataset can be sourced from public repositories such as Kaggle’s "Malaria Cell Images Dataset." Visual examples of the dataset, model architecture, and accuracy graphs will be provided in the README file.

[github-actions[bot]]

Thanks for creating the issue in ML-Nexus!🎉 Before you start working on your PR, please make sure to:

• ⭐ Star the repository if you haven't already.
• Pull the latest changes to avoid any merge conflicts.
• Attach before & after screenshots in your PR for clarity.
  • Include the issue number in your PR description for better tracking. Don't forget to follow @UppuluriKalyani – Project Admin – for more updates! Tag @Neilblaze,@SaiNivedh26 for assigning the issue to you. Happy open-source contributing!☺️