The project aims to develop a robust skin lesion classification system capable of accurately identifying and classifying lesions into seven different diseases. Leveraging the power of both semantic segmentation and image classification, we propose an ensembling approach that combines the U-Net architecture for precise lesion segmentation with the VGG network for disease classification. The U-Net model will be utilized to perform pixel-level segmentation of skin lesions, providing detailed information about lesion boundaries. Subsequently, the segmented regions will be fed into VGG and Res-Net for classification in an ensemble can further enhance the model's performance for disease classification, enabling the model to make predictions based on both localized features and overall lesion characteristics.
-
Notifications
You must be signed in to change notification settings - Fork 1
ChandraKarthik07/Advancing-Dermatology-with-Deep-Learning-An-ensemble-Model-for-Skin-Lesion-Classification
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published