Fake Currency Detection with Machine Learning Algorithm and Image Processing

Bhatia, Aman; Kedia, Vansh; Shroff, Anshul; Kumar, Mayand; Shah, Bickey Kumar

doi:10.1109/iciccs51141.2021.9432274

Cited by 29 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Employing convolutional neural networks to identify portraits in a brand-new collection of banknotes that are resistant to changes in how they are displayed, such as size and the orientation of the face [4].The system employs deep neural networks to identify and then calculate the various denominations of currency notes in a set for a ROI (Region of interest). The fact that counterfeit currency detection was improperly integrated is a serious flaw in this system [5].A strategy which uses image processing and K-Nearest Neighbors to identify counterfeit currencies.The money confirmation gathering was created using cutting-edge analytical and computation techniques, and it offers precise data and details about the people, places, and things connected to the cash [6].…”

Section: Literature Surveymentioning

confidence: 99%

Fake Currency Detection

Shamini,

Nandhini,

Varshini

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

Due to the great technological developments in the field of color printing in the past few years, it is becoming increasingly recognized that counterfeiting is a serious problem. It used to be possible and very simple for anyone to quickly prepare and print counterfeit currency notes using a computer and a laser printer at homes or places of employment. In the past, only printing houses had these facilities. The most crucial issue is now how to accurately distinguish fake currency from real currency using automatic machines. Almost all nations struggle greatly with the issue of counterfeit currency notes. But since counterfeiting has become such a pressing issue in India, it is thought to be the most serious issue there. Therefore, it is necessary to create a module that will aid in the quick and efficient recognition and detection of paper currency notes. An approach for the identification and verification of Indian currency is described in this proposed system. The authenticity of the currency will be verified using image processing methods, regardless of whether it is genuine.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Fake Currency Detection

Shamini,

Nandhini,

Varshini

et al. 2024

E3S Web Conf.

View full text Add to dashboard Cite

show abstract

“…This proposed system has the potential to improve the accuracy and reliability of currency note detection using deep learning and image processing techniques. The first layer is a Conv2D layer with 32 filters, each of size (3,3), and ReLU activation function. This layer takes an input image of size (250, 250, 3) and applies the 32 filters to produce 32 feature maps.The second layer is a MaxPooling2D layer that performs down-sampling by taking the maximum value of each 2x2 subregion of the feature maps produced by the previous layer.…”

Section: Proposed Systemmentioning

confidence: 99%

Fake Currency Detection Using Convolution Neural Network

2023

IRJMETS

View full text Add to dashboard Cite

Counterfeit currency paper notes pose a significant threat to the economy of a country, as they are produced without the legal sanction of the state. It is imperative to detect and distinguish between real and fake currency notes to prevent the proliferation of such notes in circulation. However, it is often challenging for an ordinary person to identify counterfeit notes. While banks and other financial institutions have sophisticated systems to detect fake notes, there is no such system readily available to the public. In this research paper, we propose a system that utilises deep learning algorithms, specifically Convolutional Neural Networks (CNNs), to accurately classify between real and fake currency paper notes. The system can operate in real-time, processing a picture of the paper note to determine its authenticity. We evaluate the performance of the proposed system using a dataset of real and counterfeit currency notes and achieve high accuracy in detecting fake notes. Our proposed system can be useful in various settings, including banks, financial institutions, and businesses that handle cash transactions. By detecting counterfeit currency notes promptly, we can prevent their circulation, thereby safeguarding the economy and the public from financial losses.

show abstract

“…Ada banyak contoh semacam ini di sekitar [1]. Salah satu kegiatan tersebut adalah produksi mata uang palsu yang dipraktikkan untuk menipu orang [2]. Mata uang palsu digambarkan sebagai mata uang yang diproduksi tanpa persetujuan hukum pemerintah.…”

Section: Pendahuluanunclassified

Rancang Bangun Sistem Pendeteksi Keaslian Uang Kertas Rupiah Menggunakan Sinar UV dengan Metode Machine Learning

Zulfiansyah,

Kusuma,

Attamimi

2023

JTITS

View full text Add to dashboard Cite

Abstrak-Sistem pendeteksi keaslian uang kertas rupiah merupakan metode yang dibutuhkan karena uang merupakan materi penting sehingga sering terjadi tindak kriminalitas. Metode yang sering digunakan adalah image processing untuk scaling dan color conversion, segmentasi untuk mendapatkan pola tertentu, atau dengan memperhatikan ciri fisik uang kertas rupiah, seperti tekstur dan pola terawang. Namun, metodemetode tersebut dapat dikatakan kurang efektif apabila terjadi peningkatan pemalsuan uang kertas rupiah dalam bentuk fisik. Sehingga penulis merancang sistem counting yang menggunakan sinar ultraviolet untuk menampilkan hidden pattern sebagai fitur khusus mendeteksi keaslian uang dengan metode machine learning dan menambahkan sistem counting buatan sendiri dengan fitur rotation invariant untuk melakukan pendeteksian lebih dari satu lembar uang kertas rupiah. Perpaduan image processing dan machine learning pada penelitian ini mampu memberikan hasil pengujian prototipe dengan metode k-NN dan CNN memberikan persentase keberhasilan prediksi sebesar lebih dari 90% dibandingkan dengan SVM, Random Forest, dan Naive Bayes yang kurang dari 85%. Mekanik prototipe ini mampu melakukan pendeteksian kurang dari 4 detik dengan 10 lembar uang kertas yang dideteksi. Dengan meningkatkan metode detection yang lebih expert, seperti deep learning dengan model yang fleksibel jika ingin digunakan dalam pendeteksi mata uang selain rupiah.

show abstract

Fake Currency Detection with Machine Learning Algorithm and Image Processing

Cited by 29 publications

References 8 publications

Fake Currency Detection

Fake Currency Detection

Fake Currency Detection Using Convolution Neural Network

Rancang Bangun Sistem Pendeteksi Keaslian Uang Kertas Rupiah Menggunakan Sinar UV dengan Metode Machine Learning

Contact Info

Product

Resources

About