Project V : Malaria Detection

Aim of the Project

To build a Web App using Deep Convolutional Neural Networks to predict whether a given cell image is either Parasitized (Infected with Malaria) or Uninfected

Life Cycle of the Project

  1. Collected the dataset from Kaggle which contained 27,558 images in total for both the classes
  2. Used Data Augmentation to generate extra data from the existing dataset
  3. Built a High Performance Custom DL Model using Convolutional Neural Networks, providing an Accuracy of 92.23 % on the Validation Dataset
  4. Saved the DL model with an h5 extension
  5. Built a Web App using Python at the Backend with Flask API and HTML, CSS & JS serving at the Frontend
  6. The Web App allows the User to upload an image, makes predictions on this image using the saved DL model and sends a Prediction text indicating whether a given cell image is either Parasitized (Infected with Malaria) or Uninfected

Results from the Project

  • If the cell image belongs to Parasitized class
  • If the cell image belongs to Uninfected class

Technologies Used

| Python | Tensorflow | Keras | CNN |

| Flask | Matplotlib | Numpy |

Performance of the Model

  • Training Accuracy = 93.20 %

  • Validation Accuracy = 92.23 %

  • Training Loss = 20.518 %

  • Validation Loss = 21.28 %

Check out the Project Demo

GitHub Repository