Copyright © 2025 Authors retain the copyright of this article. This article 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.

@article{154884,
        author = {Soumya Upadhyaya and Janani Swaminathan and Sudeep Kumar and Mukund Patel and Yash Choudhary},
        title = {A Method of Skin Disease Detection Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {8},
        number = {12},
        pages = {674-681},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=154884},
        abstract = {Skin diseases may be caused by fungal infection, bacteria, allergy, or viruses, etc. Theadvancement of lasers and Photonics based medical technology has made it possible todiagnose the skin diseases much more quickly and accurately, but the cost of suchdiagnosis is limited while it costs high. This can be solved with the application of automated methods that will help in early diagnosis especially with the set of imageswithvarietyofdiagnosis.
This work contributes in the research skin disease detection with the objective toIdentify unique skin problems using image input with high accuracy, which will beusefulforplaceswithlessclinicalexpertise. Ourproposedapproachissimpleandfast.Our model presents a completely automated system of dermatological diseaserecognitionthroughlesionimages. The approach works on the resize of the image to extract features using pretrained model (VGG 16). The VGG16 model was tested on the dataset to classify 6 types of skin cancer such as akiec, vasc, df, mel, bkl, bcc, nv. The pre-trained model of VGG16 has given a novel result of 94% accuracy compared to the other CNN or DNN models used in the different researches which provides the accuracy of 75 to 90% Using VGG16 which is unique property of having a smaller number of hyper-parameters, which focus on having convolution layers of 3 x 3 filter with a stride 1 and always uses the maxpool layer of 2 x 2 filter of stride 2 that helps the model to be more compact.
},
        keywords = {},
        month = {},
        }