A Hybrid Deep Learning System for Automatic Detection of Scalp Diseases and Hair Fall Stage Classification

March 2026

V. Jaganraja, Daiva Dinesh Kumar Chowdary, Mahendra Vakkalagadda, S. Vinoth Kumar, Sankar Ganesh Karuppasamy, Rayappan Lotus

scalp diseases hair fall VGG16 ResNet50 DenseNet121 EfficientNet-B0 U-Net MobileNetV3 Intersection over Union IoU CNN convolutional neural networks deep learning machine learning neural networks

TLDR The system effectively detects scalp diseases and classifies hair fall stages with high precision.

The study presents a hybrid deep learning system designed to detect scalp diseases and classify hair fall stages. It utilizes an ensemble of VGG16, ResNet50, DenseNet121, and EfficientNet-B0 for detecting 10 scalp and hair disorders, and combines U-Net with EfficientNet-B0 and MobileNetV3 for recognizing 7 levels of hair fall. The system's segmentation performance is evaluated using the Intersection over Union (IoU) benchmark, demonstrating higher precision and robustness compared to single CNNs. This approach offers a reliable and efficient method for comprehensive scalp and hair assessments.

View this study on ieeexplore.ieee.org →

Discuss this study in the Community →

Research cited in this study

2 / 2 results

research Deep Learning Approaches for Hair Disease Classification: A Comparative Analysis of MobileNetV2 and VGG19 Architectures

1 citations , November 2024

VGG19 is more accurate, but MobileNetV2 is faster and uses fewer resources.

research Enhanced Hair Disease Classification Using Deep Learning

March 2024

The model accurately classifies hair conditions with 97% accuracy.