Skin Disease Detection using Efficient Net B0 Convolutional Neural Network

Skin Disease Detection using Efficient Net B0 Convolutional Neural Network

1. Piyush Ranjan, 1JB21CS106, adm21cse5170@sjbit.edu.in

2. Ritika Kumari, 1JB21CS120, adm21cse5177@sjbit.edu.in

3. Mansi Kumari, 1JB21CS084, adm21cse5136@sjbit.edu.in

4. Loknath S Shetty, 1JB21CS080, adm21cse5128@sjbit.edu.in

5. Chaitra D, dchaitra@sjbit.edu.in

1,2,3,4 Student, Department of Computer Science and Engineering, SJB Institute of Technology,560060

5 Assistant Professor, Department of Computer Science and Engineering, SJB Institute of Technology,560060

Keywords:
Skin disease, Convolutional Neural Network, EfficientNet, Improved YOLOv3.

Abstract

Skin diseases are a common ailment affecting millions of people worldwide.The surface of the skin has many different features that are affected by the environment, dust, smoke, harmful materials and other such factors. These effects occur as per the type of skin- Oily skin or Dry skin. Early detection and treatment of these diseases are crucial in improving patient outcomes. In recent years, machine learning techniques, particularly convolutional neural networks (CNN), have shown promise in the automated detection of skin diseases.

In this paper, after analyzing such harmful effects, and try to classify the type of skin disease, so as to provide further treatment. A better Convolutional Neural Network- EfficientNet B0 is used to predict the type of skin disease based on image samples of skin diseases provided. The proposed system consists of three main stages: preprocessing, training, and testing. In the preprocessing stage, the images were re-sized, normalized, and augmented to enhance the quality of the images. In the training stage, the EfficientNet B0 CNN architecture was used to train the system on the skin disease images. The system's performance was evaluated using a test dataset, which included images that were not used in the training process. This gives an improved efficiency over other existing models.