Skip to content

OmerGeysoglu/Structural-Damage-Level-Classification

Repository files navigation

Structural Damage Detection Application

This application is developed to assist insurance companies by classifying structural damages into "undamaged", "minor damage", "moderate damage", and "heavy damage" categories, aiding in the determination of compensation payouts. The model analyzes damages in photos, classifies them, and provides this crucial information to insurers. This project was presented at the Neova Sigorta Ideathon.

Models can be accessed from the links below. https://drive.google.com/drive/folders/1jGdS3Lr1RPtvTTDocmP7LMrZckOQdgz7?usp=sharing

Model Performance

Our model has achieved the following performance metrics during the training and validation process:

Training and Validation Accuracy

Training and Validation Accuracy

Training and Validation Loss

Training and Validation Loss

Installation

To clone the project to your local machine:

git clone https://github.com/OmerGeysoglu/Structural-Damage-Level-Classification

cd Structural-Damage-Level-Classification

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published