DEEP LEARNING-BASED NAIL DISEASE CLASSIFICATION USING MOBILENET-V3-CAPSULE ARCHITECTURE

The project titled "Deep Learning-Based Nail Disease Classification Using MobileNetV3-Capsule Architecture" presents an intelligent system for identifying nail diseases through image analysis.Nails often reflect underlying health conditions, and early diagnosis of nail disorders like onychomycosis and psoriasis can aid timely treatment.This work proposes a hybrid deep learning model that combines MobileNetV3 for efficient feature extraction and a Capsule Network for robust classification.A curated dataset of nail images, categorized into healthy, onychomycosis, and psoriasis classes, was used.Images were pre-processed using standard techniques such as resizing, normalization, and augmentation to ensure consistency and improve generalization.MobileNetV3, known for its lightweight design and speed, was utilized to extract meaningful features from the images.The features were passed to the Capsule Network, which captured spatial relationships more effectively than traditional CNNs.The proposed model achieved an impressive classification accuracy of 99.4%, demonstrating high precision in distinguishing between nail conditions.This accuracy highlights the effectiveness of the integrated architecture, particularly for medical imagebased diagnosis.The system is designed to be efficient and scalable making it suitable for deployment on mobile or low-resource devices, especially in remote healthcare settings.This project underscores the potential of combining lightweight deep learning models with advanced classifiers to create accessible, non-invasive diagnostic tools that support early disease detection and improve healthcare outcomes.Invasive-diagnostic tools that support early disease detection and improve healthcare outcomes.