• Ms. Harshita Patwa
• Mr. Rajneesh Pachouri
• Mr. Anurag Jain
• Ms. Sadhvi Biltharey

Skin diseases impact heaps of folk everywhere and are a big well-being question. Effective remedy for many disorders depends on an early and exact disease. This research uses MATLAB-executed deep education methods, especially the VGG16 construction, to supply a powerful resolution for the categorization of skin afflictions. Creating an intensely exact and direct model for the robotic categorization of skin environments is the main aim concerning this research. The project's dataset resides of five various groups of skin ailments: vitiligo, sharp fleas, diabetic blisters, larcenist bites, and blemishes-cystic blemishes. Because all class in the dataset has existed painstakingly preferred to indicate a difference of skin disorders, the model is flexible and outfitted to tackle a roomy range of dermatological issues. The VGG16 construction is a standard spiral interconnected system (CNN) model that is to say secondhand by way of allure wonderful feature origin capacities. Using the rash dataset, transfer knowledge is used to advance the pre-prepared VGG16 model. To guarantee the model's stability, a absolute cross-confirmation process is secondhand for preparation, confirmation, and experiment. The extraordinary categorizations veracity achieved in this place study is with allure most important talents. With an amazing veracity of 98.08%, the model positively shows allure efficiency wrongly diagnosing and categorizing skin environments. This extreme veracity rate is essential for threatening wrong diagnoses and lifting the standard of take care of victims all at once. Apart from allure special accuracy, the submitted approach specifies dermatologists and healing pros accompanying absolute-period rash categorization, rendition it a priceless reserve. A convenient connect conceived accompanying MATLAB guarantees approachability and usefulness valuable, admitting healing experts to form experienced conclusions fast and correctly. In conclusion, this project offers a all-encompassing form for classifying skin ailments utilizing deep education methods, emphasising the VGG16 construction. The model's competency to right categorize a type of skin ailments is manifested by allure 98.08% veracity rate, that can help accompanying early disease and effective situation. This study form progress towards the aim.

SVM, Vehicle Collision (AVC), labeling, neural network, Segmentation, tracking, Animal Footprint, Animal.

"Enhanced Skin Disease Diagnosis through VGG16 Architecture: Leveraging CNN for Accurate Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.k376-k383, May-2025, Available :http://www.jetir.org/papers/JETIR2505B25.pdf

"Enhanced Skin Disease Diagnosis through VGG16 Architecture: Leveraging CNN for Accurate Classification", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppk376-k383, May-2025, Available at : http://www.jetir.org/papers/JETIR2505B25.pdf