Derma-Speziale: An Image-Based Automated System for Skin Disease Identification Using Convolutional Neural Networks
Author(s):
Neethu C Sekhar, Rosmin Augustine , Johny Xavier Fernandez , Midhlaj Ahammed T K, Serene Anna Giji
Keywords:
Deep Learning, prediction modelling, CNN, Tensorflow
Abstract
Skin disease is perhaps the most well-known kind of human illness, which may happen to everybody regardless of any demographic characteristics and skin diseases are becoming one of the most common health issues in all countries worldwide. Multiple tests should be carried out to determine the skin diseases faced by patients. This takes a while, depending on the prediction of the diagnosis. As a result, a framework is required that can analyse skin diseases without any of these requirements and provide superior results in seconds. An automated image-based system based on convolutional neural networks (CNN) for skin disease recognition is proposed in this paper. Training dataset is required for various skin diseases.. The dataset includes all forms of skin diseases, however we focused on nine main types of skin diseases, with each class including between 150 and 300 samples. Users can enter images and system processes, use CNN algorithm to extract features, and use softmax classifier to diagnose diseases. The proposed CNN model is compared with a recurrent neural networks(RNN) model to ensure CNN model is more accurate in classification and prediction of the input images.
Article Details
Unique Paper ID: 154162

Publication Volume & Issue: Volume 8, Issue 7

Page(s): 1 - 6
Article Preview & Download


Share This Article

Conference Alert

NCSST-2021

AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2021

SWEC- Management

LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT

Last Date: 7th November 2021

Go To Issue



Call For Paper

Volume 8 Issue 4

Last Date 25 September 2021

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies