About this document

Deep Learning for Psoriasis Detection by Sakshi Srivastava is a document available to read on EtoBox.

This document proposes a deep learning framework to detect psoriasis disease from skin images. It compares popular deep learning models (VGG-16, VGG-19, Inception v3) as feature extractors paired with classifiers (Random Forest, SVM, KNN, etc.). The best performing model uses VGG-19 for feature extraction and logistic regression for classification, achieving an AUC of 0.990 and classification accuracy of 94.2% on a dataset of 312 skin images.

Author

Sakshi Srivastava

Language

EN