Skin disease detection using Convolutional Neural Networks
Skin diseases are more common than other diseases. Skin diseases may be caused by fungal infection, bacteria, allergy, or viruses, etc. A skin disease may change texture or color of the skin. In general, skin diseases are chronic, infectious and sometimes may develop into skin cancer.Therefore, skin
Project Title
Skin disease detection using Convolutional Neural Networks
Project Area of Specialization
Project Summary
Skin diseases are more common than other diseases. Skin diseases may be caused by fungal infection, bacteria, allergy, or viruses, etc. A skin disease may change texture or color of the skin. In general, skin diseases are chronic, infectious and sometimes may develop into skin cancer.Therefore, skin diseases must be diagnosed early to reduce their development and spread. The diagnosis and treatment of a skin disease takes longer time and causes financial and physical cost to the patient. In general, most of the common people do not know the type and stage of a skin disease. Some of the skin diseases show symptoms several months later, causing the disease to develop and grow further. This is due to the lack of medical knowledge in the public. Sometimes, a dermatologist (skin specialist doctor) may also find it difficult to diagnose the skin disease and may require expensive laboratory tests to correctly identify the type and stage of the skin disease. The advancement of lasers and photonics based medical technology has made it possible to diagnose the skin diseases much more quickly and accurately. But the cost of such diagnosis is still limited and very expensive. Therefore, we propose an image processing-based approach to diagnose the skin diseases. This method takes the digital image of disease effect skin area then use image analysis to identify the type of disease. Our proposed approach is simple, fast and does not require expensive equipment's other than a camera and a computer.
Project Objectives
We are developing an system that will diagnose skin diseases by using image processing-based approach. This method takes the digital image of disease effect skin area where user can capture image or uplaod existing image to our system and then on the basis of trained data sample image will be preprocessed and features will be extracted from it and on the basis of specific features we will identify if the skin is effected by any disease or not.
Project Implementation Method
We will be implementing convolutional neural networks approach for the prediction of skin diseases. It takes following steps:
1) Preprocessing: Achieving high performance of skin disease detection system requires overcoming some major difficulties. Such as creating a database and unifying image dimensions. e.g image resizing etc.
2) Feature Extraction: At the beginning, Convolutional Neural Network (CNN) is a set of stacked layers involving both nonlinear and linear processes. These layers are learned in a joint manner. The main building blocks of any CNN model are: convolutional layer, pooling layer, nonlinear Rectified Linear Units (ReLU) layer connected to a regular multilayer neural network called fully connected layer, and a loss layer at the backend. CNN has known for its significant performance in applications as the visual tasks and natural language processing.
Example : AlexNet consists of five convolutional layers; where a nonlinear ReLU layer is stacked after each convolutional layer. AlexNet was trained using more than 1.2 million images belonging to 1000 classes .We proposed feature extraction from a pretrained convolutional neural network. Because it is the easiest and robust approach to use the power of pretrained deep learning networks.
3) Classification: Classification is a computer vision method. After extracting features, the role of classification is to classy the image via Support Vector Machine (SVM). A SVM can train classifier using extracted features from the training set.
Benefits of the Project
Key Benefits of the projects are:
1) Fast solution it saves time.
2) Patient can detect disease from his phone or computer that saves his/her travelling cost.
3) Early detection of some serious diseases e.g. skin cancer will be very beneficial in saving life and treatment at early stage.
Technical Details of Final Deliverable
We will be developing system as a web application developed in react js as front-end and using AI techniques we will implement convolutional neural network using Python .
Final Deliverable of the Project
Core Industry
Other Industries
Core Technology
Other Technologies
Sustainable Development Goals
Required Resources
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Dataset Gathering | Miscellaneous | 1 | 5000 | 5000 |
| Total in (Rs) | 5000 |
If you need this project, please contact me on contact@adikhanofficial.com
Design and fabrication of solar thermal energy storage system
Historically man has been dependent of fossil fuels, i.e. coal and petroleum derivatives t...
Enhanced safety of Motorbikes through IoT based Smart Helmet
The number of bikes produced in Pakistan is continuously growing; in the financial year 20...
Design and Development of Automated Pharmacy
There is only one company Willach Pharmacy Solutions, which makes the automated pharmacy r...
Neurorehabilitation (Mental Stress) using Machine Learning& Multim...
we hypothesize that multimedia content has superior mental stress-reduction capabilities....
