Authors: Harsh Ahir, Chandu D, Rohit Kumar, Harshvardhan karthik, Assistant Prof. Sunanda
DOI Link: https://doi.org/10.22214/ijraset.2023.49211
Certificate: View Certificate
Particularly dangerous and frequently contagious include melanoma, eczema, and impetigo. When found early enough, some skin conditions are curable. The main issue with it is that only a skilled dermatologist can identify and categorise such diseases. In several cases, medical professionals appropriately categorise the illness and consequently give the pa-tient the wrong drugs. Navies Bias Classifier has been contrasted. Real-time testing findings are displayed. Since our solu-tion is mobile-based, it can be used anywhere. In order for the programme to function, the patient must supply an image of the affected area. It is processed using deep learning techniques and produces the most accurate results. In this essay, we compare two distinct real-time skin disease detection algorithms based on accuracy in this presentation.
I. INTRODUCTION
The human skin is the largest organ in the body. Its surface area is around two square yards, and its weight is between six and nine pounds. Skin serves as a barrier between the inside body and the outside world. It defends against bacterial, viral, allergic, and fungal infections and regulates body temperature. Dermatitis, hives, and other skin issues can be brought on by allergies, irritants, certain diseases, genetics, and immune system-related issues. Numerous skin conditions, including eczema, ringworm, alopecia, and acne, also have an impact . Most image processing models start with input samples that are 2-D signals and then process those data using predetermined signal processing techniques. It is a technology that is commonly utilised nowadays and has many uses in the commercial world.
II. MOTIVATION
Melanoma is the most varied skin disorder, affecting more than 125 million individuals globally, and its prevalence has been rapidly increasing over the past few decades. Nevus incidence is significant, particularly in rural areas. Skin conditions may cause difficulties in the body, including the transmission of an infection from one person to another, if they are not treated at an early stage. Investigating the contaminated area early on might help to prevent skin problems. The characteristics of skin photographs vary widely, making it difficult to develop a reliable and effective algorithm for automatically identifying skin diseases and their severity. Skin tone and colour are key factors in identifying skin diseases. Visual differences exist between skin colour and coarseness. Such photos must be processed automatically for skin analysis, which calls for a quantitative discriminator to distinguish between the illnesses.
III. RELATED WORKS
7. The Paper [7], In this model, skin illness images are assessed using the grey normalised symmetrical simultaneous occurrence stencils (GLCM) method to determine the state of the skin disease. The suggested approach is employed in a productive and cost-effective manner for the computerised evaluation of skin problems. This mechanism aids the skin in reducing the error in medical diagnosis. The initial checkup for people in distant areas without access to qualified doctors is another. In order to store the implied demand for textual skin images, the system uses relational databases. The same type of photos can also be used with this approach directly over feature vectors.
8. The Paper [8], The medical profession is a newer topic of research in artificial intelligence (AI). In this study, CBR and image processing are combined to construct a mobile-based medical support system for the diagnosis of skin diseases. This model was created to assist users in determining if they have a condition or not by helping them pre-examine their skin status. Additionally, it is important to raise awareness of skin illnesses so that we can find a remedy before they worsen and cause death or infection in other individuals. 90% accuracy is achieved in the suggested system's detection of 6 different skin disorders.15% of the symptoms are utilised for testing, 10% are used for validation, and 75% are used for testing. In comparison to unsupervised systems, which only detect diseases at a rate of 80%, our supervised system detects diseases at a rate of 90%. The following table shows the correlation between the sample disease and other associated diseases: Skin Cancer: 51%; Acne: 75%.
9. The Paper [9], The concept of "skin detection" the classification of the pixels in an image into two groups—skin and non-skin—is referred to as from an image. Numerous algorithms extract features for pixel categorization using multiple colour spaces, yet the bulk of these methods fail to correctly identify different skin tones. The color-based image retrieval (CBIR) technique is used to implement the current methodology in this work. In this method, a set of feature vectors are first created by using the CBIR method, picture tiling, and establishing the association between a pixel and its neighbours. Then, during the test stage, training is employed for skin detection. The suggested model is highly accurate in differentiating between skin types, according to experimental results, and it is not sensitive to changes in lighting or facial movement. The two steps in the suggested method are training and testing. In the testing stage, skin area was discriminated from non-skin areas after pure skin images were first trained in the training stage.
10. The Paper [10], This model, which is used to recognise skin diseases, is implemented using rule-based and forward chaining inference engine techniques. By using this approach, users are able to diagnose paediatric skin conditions online and promptly offer pertinent medical recommendations or counsel. This system is composed of the diagnosis module, login module, info module, report module, and management module. The diagnosis and management modules are the two main ones. Children's symptoms and conditions are recognised in the diagnose module based on questions the user is asked and their responses. In response to queries concerning the signs and symptoms and the state of children's skin, this approach might be an option for parents to recognise skin illnesses in kids.
V. LIMITATIONS
Eczema, impetigo, and melanoma are the only three skin conditions for which this treatment is used. Because it has only been built for Windows applications, it has not yet been created for smart phones running on Android, iOS, etc.
It is necessary to capture the image for this application without any lighting effects. It only supports English; it doesn't support common languages like Sinhala or Tamil.
Skin illness detection is a crucial step in lowering mortality rates, disease transmission, and skin disease progression. Skin disease diagnosis requires lengthy and expensive clinical procedures. In the early stages of developing an automated derma-tology screening system, image processing techniques are helpful. The identification of characteristics is crucial in the claci-fication of skin disorders. In this study, pre-trained SVM and naive bayes were used to build the detection algorithm. In conclusion, it is important to keep in mind that because Saudi Arabia has extremely hot weather and the presence of humidity, skin illnesses are more like-ly to spread there.
Copyright © 2023 Harsh Ahir, Chandu D, Rohit Kumar, Harshvardhan karthik, Assistant Prof. Sunanda. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Authors : Harsh Ahir
Paper Id : IJRASET49211
Publish Date : 2023-02-22
ISSN : 2321-9653
Publisher Name : IJRASET
DOI Link : Click Here