Coder Social home page Coder Social logo

thomasodum / color-blob-based-cosfire Goto Github PK

View Code? Open in Web Editor NEW

This project forked from barisgecer/color-blob-based-cosfire

0.0 2.0 0.0 37.43 MB

Color-blob-based COSFIRE filters for object recognition by Baris Gecer, George Azzopardi, Nicolai Petkov

License: GNU Lesser General Public License v3.0

MATLAB 15.62% Shell 0.71% HTML 13.76% Makefile 0.72% Java 18.67% M4 11.67% C 13.20% Python 7.76% C++ 17.89%

color-blob-based-cosfire's Introduction

Color-blob-based-COSFIRE

Color-blob-based COSFIRE filters for object recognition by Baris Gecer, George Azzopardi, Nicolai Petkov This is the code required to run the Color-blob-based COSFIRE filters, the codes are described casually here and more formally in this paper:

B. Gecer, G. Azzopardi, and N. Petkov, “Color-blob-based COSFIRE filters for Object Recognition” Image and Vision Computing, vol. 57, pp. 165-174, 2017.

If you find this paper or code useful, we encourage you to cite the paper. BibTeX:

@article{gecer2016color,
  title={Color-blob-based COSFIRE filters for object recognition},
  author={Gecer, Baris and Azzopardi, George and Petkov, Nicolai},
  journal={Image and Vision Computing},
  year={2016},
  publisher={Elsevier}
}

=============================================================================

Below we have short explanations of the scripts:

/demos

Contain two simple examples to show how can you use the code
	- Toy example of faces
	- Marylin image

/CCOSFIRE

Contains the core functions of our approach

/ts

Contains the codes for the experiments on the GTSRB data set (traffic signs)
/wrapper
	The actual codes
	- to do a small experiment run Application.m
/compile
	Files needed to run the code on cluster
/exps
	Experiment results (i.e. see overall.txt or confusionMatrix)

/bf

Contains the codes for the experiments on the butterfly data set
/wrapper
	The actual codes
	- to do a small experiment run Application.m
/compile
	Files needed to run the code on cluster
/exps
	Experiment results (i.e. see overall.txt or confusionMatrix)

/org

Contains the codes and experiments of the original COSFIRE paper:
G. Azzopardi and N. Petkov, “Trainable COSFIRE filters for keypoint detection and pattern recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35 (2), pp. 490-503, 2013.

/libsvm-3.17

contains libsvm codes directly adapted from: https://www.csie.ntu.edu.tw/~cjlin/libsvm/
Please cite their work if you use it: https://www.csie.ntu.edu.tw/~cjlin/libsvm/faq.html#f203

color-blob-based-cosfire's People

Contributors

barisgecer avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.