Smartphone Enabled Counterfeit Note Detection using Siamese Network
Dhanush C.1, Adith Kumar B. A.2, Ajay Umakanth3, Ajay Deshpande4, Bhavanishankar K.5
1Dhanush C, Department of CSE, RNSIT, Bangalore (Karnataka), India.
2Adith Kumar B A, Department of CSE, RNSIT, Bangalore (Karnataka), India.
3Ajay Umakanth, Department of CSE, RNSIT, Bangalore (Karnataka), India.
4Ajay Deshpande, Department of CSE, RNSIT, Bangalore (Karnataka), India.
5Dr. Bhavanishankar K, Professor, Department of CSE, RNSIT, Bangalore (Karnataka), India.
Manuscript received on 07 December 2019 | Revised Manuscript received on 15 December 2019 | Manuscript Published on 31 December 2019 | PP: 598-604 | Volume-9 Issue-2S December 2019 | Retrieval Number: B10581292S19/2019©BEIESP | DOI: 10.35940/ijitee.B1058.1292S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Counterfeit note has a disastrous impact on a country’s economy. The circulation of such fake notes not only diminishes the value of genuine note but also results in inflation. The feasible solution to this burning issue is to create awareness about the counterfeit notes among public and to equip them with a technology to detect fake notes on their own. Though there exist numerous research articles on detection of fake notes, they are not handy. The reason for this could be the unavailability or unaffordability in acquiring the equipment for the same. This paper proposes an approach whose implementation can easily be deployed on a smart phone and hence anyone with access to them can use the application to detect the fake notes. The proposed approach consists of the processing phases including image procurement, pre-processing, data augmentation, feature extraction and classification. ₹500 notes are considered for experimentation analysis. Out of 17 distinctive features, 3 such from the obverse side are considered to evaluate the genuineness of the note. Siamese neural network is employed to build a model for effective classification of the notes. The performance of the proposed approach is evaluated at 85% with respect to accuracy.
Keywords: Contrastive Loss, Counterfeit Note, Siamese Network, Smartphone.
Scope of the Article: Ubiquitous Networks