Skip to content

Detection of scratch defects on metal nuts using random forest classifier

License

Notifications You must be signed in to change notification settings

shubh-tiwari/random-forest-scratch-segmentation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Scratch segmentation using random forest classifier

This repo contains the scripts to detect scratch defects on metal nut using random forest classifer

Process flow chart

Predicted sample

Training random forest classifier

  • Data acquisition
  • Feature extraction using some of the imporatant filters and edge detection methods available in image processing
  • Creating dataframe of these features and splitting training and validation dataset
  • Training the random forest classifier
  • Evaluating the accuracy score on validation dataset

The model gives the accuracy score of 95.39% on validation dataset

Acknowledgment for the metal nut image dataset

Paul Bergmann, Michael Fauser, David Sattlegger and Carsten Steger, the authors of the MVTec-AD paper

About

Detection of scratch defects on metal nuts using random forest classifier

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages