Home / All Innovations / Innovation Details

Skin Disease Identification Using image Analysis

Description: Skin diseases are the most prevalent diseases globally. Even though the diseases being common, diagnosis of disease is extremely difficult and requires laborious skills and enormous experience in the field of medicine. So our aim was to provide a better alternative to medical professionals in order to integrate their medicinal practice with booming technology used currently, which not only provides a path but also accuracy of disease prediction and helpful in improvising diagnosis and curing methods. In this project, we provide an approach to detect five kinds of most commonly occurring diseases. Computer vision, Machine learning and Deep Learning are dual stages which we used to identify diseases accurately. Our objective of the project is to detect the type of skin disease easily with accuracy and recommend the best.

Image Analytics has been increasingly becoming popular and is being employed in various domains. It can simplify various tasks involving human effort like weeding, disease identification, identification of plant growth stage etc. The scope of our project is that it can be used for skin disease identification and this algorithm can be given to a website where anyone can upload an image to know the disease type. It can make the task even simpler, easy to use and also it is not expensive as a diagnosis test to implement it. This system has a scope to become more and more efficient with large amount of image data. Convolutional neural networks is more accurate and datasets can be trained more quickly. It is a type of network in which it contains all convolutional layers, it performs good in terms of large data and real time applications. Skin disease identification method is proposed, which is based on CNN using gradient descent algorithm. Besides some scalable applications are proposed, for example, we explore how the system is identifying the diseases based on deep learning. This showed significant improvement in accuracy of skin disease detection. Datasets and KERAS are used Features of Proposed System The approach works on color images and grey scale images. The system successfully detects five different types of diseases and results are helpful for healthcare department to diagnose the disease.Image analysis makes this very simple and easy to identify the skin disease by analyzing it using deep learning concepts and predict the precise output sucessfully. The proposed system is highly beneficial in rural areas where access to dermatologists is limited. e. It can be used to help people from all over the world and can be used in doing some productive work. The tools used are free to use and are available for the user, hence, the system can be deployed free of cost.

Organisation: Sreenidhi Institute of Science and Technology,India

Innovator(s): Rokkam Krishna Vamsi,Akkenapally Sharanya, Akshaya Narayana, Mahima Chowdary Maddineni, Chaturya Katragadda, Dr K Vijayalakshmi

Category: Healthcare/Fitness

Country: India

Silver Award