dasec / glasses-detection

Methods for automatic detection of glasses in near-infrared iris images

glasses-detection

This repository contains code for automatic detection of glasses in near-infrared images implemented by Florian Struck.

License

This work is licensed under license provided by Hochschule Darmstadt (h_da-License).

Attribution

Any publications using the code must cite and reference the conference paper [1].

Contents

This repository contains 3 different approaches for glasses detection:

• explicit-glasses-identifier - an explicit approach for glasses detection based on edges and reflections
• dl-glasses-identifier - uses deep neuronal network to identify glasses
• statistic-glasses-identifier - uses the BSIF filter and statistical metrics of an image to identify glasses

Instructions

The repository contains 3 independent projects. Each project has its own structure and dependencies and can therefore be built independently of the other projects. They can be built by running the "make" command in their respective project folders. Afterwards, the executable can be found in PROJECT/build/.

Models

The models used in the paper are available here: (Models)

Dependencies

explicit-glasses-identifier:

• BOOST library (Version >= 1.52)
• OpenCV (Version 2.4)
• glog (Version 0.3.5)

dl-glasses-identifier:

• BOOST library (Version >= 1.52)
• OpenCV (Version 2.4)
• glog (Version 0.3.5)
• Caffe (See http://caffe.berkeleyvision.org/installation.html)

statistic-glasses-identifier:

• BOOST library (Version >= 1.52)
• OpenCV (Version 2.4)
• glog (Version 0.3.5)
• matio (Version 1.5)

Contact

Code author: Florian Struck ([email protected])

References

• [1] Pawel Drozdowski, Florian Struck, Christian Rathgeb, Christoph Busch: "Detection of Glasses in Near-infrared Ocular Images", in Proc. of the 11th IAPR International Conference on Biometrics (ICB 2018), Queensland, Australia, February 2018.

© Hochschule Darmstadt

glasses-detection's Issues

how to use?(dl-glasses-identifier)

Hi, How to run dl-glassess-identifier ?

Is it convenient to provide a model of deep learning?

Instructions or proper make file to install the app/libraries

I've been trying to install the dependencies for this and its really disorganized to be able to do so. Especially the opencv libraries. I believe many will really appreciate a proper set of instructions or file to install the dependencies.