High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Skinova- AI Based Skin Disease Detection System

Author(s):

Karuna Jadhav , D Y Patil Polytechnic Ambi, Pune; Kalyani Naigaonkar, D Y Patil Polytechnic Ambi, Pune; Shatakshi Darandale, D Y Patil Polytechnic Ambi, Pune; Arya Jagtap, D Y Patil Polytechnic Ambi, Pune

Keywords:

Skin Disease Detection, Artificial Intelligence, Machine Learning, Deep Learning, Convolutional Neural Network (CNN), Image Classification, Dermatology, Medical Image Analysis, Automated Diagnosis, Healthcare System

Abstract

Skin diseases are among the most common health problems affecting people worldwide, and early detection plays a crucial role in effective treatment. However, accurate identification of skin conditions often requires expert dermatological analysis, which may not always be easily accessible. To address this issue, this project presents Skinova, an AI-based skin disease detection system that assists users in identifying possible skin conditions using image analysis. Skinova utilizes machine learning and deep learning techniques to analyze uploaded images of skin lesions and classify them into different disease categories. The system is trained on a dataset of skin disease images to recognize patterns and features associated with various conditions. By leveraging convolutional neural networks (CNN), the model improves accuracy in classification and reduces the dependency on manual diagnosis. The proposed system provides a user-friendly interface where users can upload images and receive quick predictions along with basic information about the detected condition. This helps in early awareness and encourages users to consult medical professionals for further treatment. Overall, Skinova aims to bridge the gap between patients and dermatological diagnosis by providing a fast, accessible, and intelligent preliminary screening tool for skin disease detection.

Other Details

Paper ID: IJSRDV14I20059
Published in: Volume : 14, Issue : 2
Publication Date: 01/05/2026
Page(s): 52-55

Article Preview

Download Article