https://github.com/mrpranavr/building_defect_detection_app

An application that detects defects in buildings live using a image classification deep learning model
https://github.com/mrpranavr/building_defect_detection_app

flask-application opencv-python tensorflow

Last synced: 5 months ago
JSON representation

An application that detects defects in buildings live using a image classification deep learning model

• Host: GitHub
• URL: https://github.com/mrpranavr/building_defect_detection_app
• Owner: mrpranavr
• Created: 2022-02-02T09:38:38.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2022-02-02T10:25:15.000Z (over 4 years ago)
• Last Synced: 2025-06-01T10:27:26.031Z (about 1 year ago)
• Topics: flask-application, opencv-python, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 32.1 MB
• Stars: 3
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          

  
Building Defect Detector





  This is a application that makes use of image classification in order to detect building defects through a live camera. Transfer

  learning is used for the deep learning model.

  

   

  


  


      



  

## About the project

  This project in its core is a image classification model that can detect defects in a building. These defects are Roof defect, cracks defect and flakes on surfaces. In order for users to use the model easily, I have incorporated the model into a application with a GUI that once excecuted, runs on the local network of the device. 

  

  It has an option to open the webcam of the user's device. This in turn opens a new window showing the live camera feedback. The predictions can also be seen live on that same window. In other words, the user can see live prediction of the shown defects on the video screen itself.

  

  

  ## Needed python packages

  

  - Tensorflow (latest version 2.7)

  - Flask

  - OpenCV 

  - Numpy

  - Matplotlib