Coinnet: platform independent application to recognize Indian currency notes using deep learning techniques

In India, nearly 12 million visually impaired people had difficulty in identifying the currency notes. There is a need to develop an application that can recognize the currency note and provide a vocal message. In this paper, a novel lightweight Convolutional Neural Network (CNN) model is developed for efficient web and mobile applications to recognize the Indian currency notes. A new dataset for Indian currency notes has been created to train, validate, and test the CNN model. This CNN based web and mobile applications will provide a text and audio output based on the recognized currency note. The proposed model is developed using TensorFlow and improved by selection of optimal hyperparameter value, and compared with existing well known CNN architectures using transfer learning. Based on the results it has been observed that proposed model perform well over six widely used existing architectures in terms of training and testing accuracy.

[1]  Kothandaraman Dhandapani,et al.  Ecofriendly and green synthesis of carbon nanoparticles from rice bran: characterization and identification using image processing technique , 2019, International Journal of Plastics Technology.

[2]  Aoba Masato,et al.  Euro Banknote Recognition System Using a Three - layered Perceptron and RBF Networks , 2003 .

[3]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[5]  Christophe Jouffrais,et al.  Assistive device for the blind based on object recognition: an application to identify currency bills , 2009, Assets '09.

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

[7]  Hiroshi Sako,et al.  A Hierarchical Classification Method for US Bank Notes , 2005, MVA.

[8]  Shiva Mittal,et al.  Indian Banknote Recognition using Convolutional Neural Network , 2018, 2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU).

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  Bhupesh Kumar Singh,et al.  Indian currency recognition based on texture analysis , 2011, 2011 Nirma University International Conference on Engineering.

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

[13]  Wei Qi Yan,et al.  An empirical approach for currency identification , 2013, Multimedia Tools and Applications.

[14]  Pramod Kumar,et al.  Opportunities for applying deep learning networks to tumour classification , 2018 .

[15]  Syed Ejaz Ali,et al.  Automatic Indian currency denomination recognition system based on artificial neural network , 2015, 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN).

[16]  Iyad Abu Doush,et al.  Currency recognition using a smartphone: Comparison between color SIFT and gray scale SIFT algorithms , 2017, J. King Saud Univ. Comput. Inf. Sci..

[17]  Christoph Busch,et al.  Fingerphoto recognition with smartphone cameras , 2012, 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG).

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

[19]  R. Gobinath,et al.  Models for Predictions of Mechanical Properties of Low-Density Self-compacting Concrete Prepared from Mineral Admixtures and Pumice Stone , 2018, SocProS.

[20]  R. Gobinath,et al.  Model Development for Strength Properties of Laterized Concrete Using Artificial Neural Network Principles , 2019, SocProS.

[21]  Khin Nyein Nyein Hlaing,et al.  Myanmar paper currency recognition using GLCM and k-NN , 2016, 2016 Second Asian Conference on Defence Technology (ACDT).

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Ching Y. Suen,et al.  Automatic recognition of serial numbers in bank notes , 2014, Pattern Recognit..

[24]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[26]  Yan Huang,et al.  Haar-SVM for Real-time Banknotes Recognition , 2014 .

[27]  Yaregal Assabie,et al.  Automatic Recognition and Counterfeit Detection of Ethiopian Paper Currency , 2016 .

[28]  Stavros Papastavrou,et al.  Blind-folded recognition of bank notes on the mobile phone , 2010, SIGGRAPH '10.

[29]  Sigeru Omatu,et al.  A reliable method for classification of bank notes using artificial neural networks , 2004, Artificial Life and Robotics.

[30]  Lakshminarayanan Subramanian,et al.  Recognizing currency bills using a mobile phone: an assistive aid for the visually impaired , 2011, UIST '11 Adjunct.