Skip to content

domenVres/IBB-Ear-Based-Identification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

IBB-Ear-Based-Identification

This is a code for ear based user identification assignment, which was a part of Image based biometry course at Faculty of Computer and Information Science, University of Ljubljana.

The assignment was implemented on AWE dataset [1] with perfectly cropped ear and also briefly tested on dataset that was obtained during the ear segmentation assignment [3]. I tested Pixel 2 pixel method, Local Binary Patterns (LBP) and two CNNs: ResNet50 and AlexNet. The starting point for my CNNs was [2]. I also used different image preprocessing techniques.

I obtained the following accuracies:

The rank curves on perfectly detected ears without preprocessing (except the required one for CNNs) are:

References

[1] http://ears.fri.uni-lj.si/datasets.html#awe-full

[2] https://pytorch.org/tutorials/beginner/finetuning_torchvision_models_tutorial.html

[3] https://github.com/domenVres/IBB-Ear-Segmentation

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published