ACORB – An ACO and ORB based Hybrid Image Feature Detector

Feature detection is most crucial stage in image identification in computer vision, which helps computer recognizing the image. This work is part of a research for the Indian currency recognition for blind people. Each country has its own currencies with unique features, colors, denominations and international value. As we move towards first quarter of 21st Century, world is facing various issues like terror-funding, smuggling and that has lead to the printing of fake currencies. Due to this, many a times a person would never be able to know that the currency which one is holding is genuine or fake. This can only be decided if one knows all the features of the currency. However, for a common man, it is not possible to remember the features of the currency; especially for blind person it is not at all possible. Though the denomination can easily be recognized for a currency but it becomes difficult to identify a counterfeit currency from the real one. This paper proposes an ACO based novel concept for feature detection using ORB feature detector, named ACORB. It has been tested thoroughly to check its effectiveness and the concept seems promising based on its results. The main motive of this work is to design and develop an algorithm for Indian currency recognition in the regional languages to help the visually challenged people to recognize the currency denomination and to check if the currency is fake or genuine.

[1]  Minfang Peng,et al.  The design and implementation of an embedded paper currency characteristic data acquisition system , 2008, 2008 International Conference on Information and Automation.

[2]  Hamid Hassanpour,et al.  Feature extraction for paper currency recognition , 2007, 2007 9th International Symposium on Signal Processing and Its Applications.

[3]  Bo Jiang,et al.  Research on paper currency recognition by neural networks , 2003, Proceedings of the 2003 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.03EX693).

[4]  Xu Liu,et al.  A camera phone based currency reader for the visually impaired , 2008, Assets '08.

[5]  Fumiaki Takeda,et al.  Recognition system of US dollars using a neural network with random masks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[6]  Yang Gao,et al.  Paper money number recognition based on intersection change , 2010, Third International Workshop on Advanced Computational Intelligence.

[7]  Saeed Mozaffari,et al.  Eroded money notes recognition using wavelet transform , 2010, 2010 6th Iranian Conference on Machine Vision and Image Processing.

[8]  Muhammad Sarfraz,et al.  An Intelligent Paper Currency Recognition System , 2015 .

[9]  Yingyong Zou,et al.  Study on Money Number Recognition Arithmetic , 2014, MUE 2014.

[10]  Kazuyuki Murase,et al.  A Paper Currency Recognition System Using Negatively Correlated Neural Network Ensemble , 2010, J. Multim..

[11]  Xiaodong Yang,et al.  Robust and Effective Component-Based Banknote Recognition for the Blind , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[12]  Natasha Gelfand,et al.  Efficient Extraction of Robust Image Features on Mobile Devices , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[13]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[14]  CervantesJair,et al.  Recognition of Mexican banknotes via their color and texture features , 2012 .

[15]  Parminder Singh Reel,et al.  Image Processing based Feature Extraction of Indian Currency Notes , 2010 .

[16]  Shie-Jue Lee,et al.  Employing multiple-kernel support vector machines for counterfeit banknote recognition , 2011, Appl. Soft Comput..

[17]  Michifumi Yoshioka,et al.  Implementing a reliable neuro-classifier for paper currency using PCA algorithm , 2002, Proceedings of the 41st SICE Annual Conference. SICE 2002..

[18]  Jun Ho Oh,et al.  High Speed Paper Currency Recognition by Neural Networks , 1997 .

[19]  Oskar Andersson,et al.  A comparison of object detection algorithms using unmanipulated testing images : Comparing SIFT, KAZE, AKAZE and ORB , 2016 .

[20]  Haman Nurlaila.  Currency recognition and converter system , 2008 .

[21]  F. Takeda,et al.  A neuro-paper currency recognition method using optimized masks by genetic algorithm , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[22]  Guowei Yang,et al.  Employing quaternion wavelet transform for banknote classification , 2013, Neurocomputing.

[23]  C. V. Jawahar,et al.  Currency Recognition on Mobile Phones , 2014, 2014 22nd International Conference on Pattern Recognition.

[24]  Ahmed Ali,et al.  Recognition System for Pakistani Paper Currency , 2013 .

[25]  F. Takeda,et al.  Recognition of paper currencies by hybrid neural network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[26]  Marco Gori,et al.  A neural network-based model for paper currency recognition and verification , 1996, IEEE Trans. Neural Networks.

[27]  F. P. Ahangaryan,et al.  Persian Banknote Recognition Using Wavelet and Neural Network , 2012, 2012 International Conference on Computer Science and Electronics Engineering.

[28]  D. A. K. S. Gunaratna,et al.  ANN Based Currency Recognition System using Compressed Gray Scale and Application for Sri Lankan Currency Notes - SLCRec , 2008 .

[29]  Anni Cai,et al.  A reliable method for paper currency recognition based on LBP , 2010, 2010 2nd IEEE InternationalConference on Network Infrastructure and Digital Content.

[30]  Farid García,et al.  Recognition of Mexican banknotes via their color and texture features , 2012, Expert Syst. Appl..

[31]  Fumiaki Takeda,et al.  Multiple kinds of paper currency recognition using neural network and application for Euro currency , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[32]  Kwang-Kyu Seo.  An Ant Colony Optimization Algorithm Based Image Classification Method for Content-Based Image Retrieval in Cloud Computing Environment , 2012 .

[33]  Tien Dat Nguyen,et al.  Recognizing Banknote Fitness with a Visible Light One Dimensional Line Image Sensor , 2015, Sensors.