Skip to content

A hybrid shape-from-shading algorithm based on linearization

License

Notifications You must be signed in to change notification settings

muhammedkotan/hybridSFS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Kotan & Oz Hybrid Shape From Shading

A hybrid shape-from-shading algorithm based on linearization

Citation and Contact

Citation and Contact!

Citation

This study includes only a part of the thesis: Development of a linearization based hybrid method using image tones for the surface inspection of metallic parts, Sakarya University,Computer and Information Sciences,2020. If you find our work useful, please cite :

1- @article{kotan2021linearization, title={A linearization-based hybrid approach for 3D reconstruction of objects in a single image}, author={Kotan, Muhammed and {"O}z, Cemil and Kahraman, Abdulgani}, journal={International Journal of Applied Mathematics and Computer Science}, volume={31}, number={3}, year={2021} }

2- @article{kotan2017surface, title={Surface inspection system for industrial components based on shape from shading minimization approach}, author={Kotan, Muhammed and {"O}z, Cemil}, journal={Optical Engineering}, volume={56}, number={12}, pages={123105}, year={2017}, publisher={International Society for Optics and Photonics} }

About Images

About Images

Images

Image 1 is a classic "tent" image. It can be obtained by the formula below.

Z(x,y)=min{-2|x|+2α,-|y|+α}

tent

Resulting Depth map tent_res_

Image 2 is a cat image from the dataset : From Shading to Local Shape see: http://vision.seas.harvard.edu/qsfs/

CatIm

Resulting Depth Map CatIm_res_

Image 3 is a defect image from the dataset : NEU surface defect database see: http://faculty.neu.edu.cn/yunhyan/NEU_surface_defect_database.html

inclusion_1

Resulting Depth map inclusion_1_res_

About

A hybrid shape-from-shading algorithm based on linearization

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages