Authentication of currency notes through printing technique verification

Abstract

An image analysis based pattern classification method is proposed to authentic the printing process used in printing different texts on currency notes. Features suitable for doing this are selected and then studied to detect fraudulent samples based on the printing method. This classification is done by using Support Vector Machines and Neural Nets. The discriminatory power of the selected features in authenticating the printing process is tested using the Linear Discriminate Analysis. Experimental results show that the proposed framework provides a highly accurate framework for authenticating the printing process in bank notes.

An Efficient Technique for Detection of Fake Currency

“…In the year 2010, Roy et al [9] have discussed an image analysis based example arrangement strategy that proposed to real the printing procedure used in printing different text on currency notes. Linear Discriminate Analysis (LDA) is proposed for validating the printing procedure.…”

Analisis Perbandingan Algoritma Classification Untuk Authentication Uang Kertas (Studi Kasus: Banknote Authentication)

“…Sehingga, apabila dikembalikan akan dapat menemui data yang hampir sama dengan data aslinya. Transformasi wavelet dibagi menjadi dua bagian besar, yaitu transformasi wavelet kontinu (TWK) dan transformasi wavelet diskrit (TWD) [2]. Cara kerja transformasi wavelet kontinu (TWK) adalah dengan menghitung konvolusi sebuah sinyal dengan sebuah jendela modulasi pada setiap waktu dengan setiap skala yang diinginkan.…”

“…Sinyal pertama-tama dilewatkan pada rangkain filter highpass dan low-pass, kemudian setengah dari masing-masing keluaran diambil sebagai sample melalui operasi sub-sampling. Proses ini disebut sebagai proses dekomposisi satu tingkat [2]. Keluaran dari filter low-pass digunakan sebagai masukkan di proses dekomposisi tingkat berikutnya.…”

Forensic authentication of banknotes on mobile phones

“…The resulting feature vector is used by a neural network to classify the denomination and serves as an indication of authenticity when the feature distance to a reference banknote is calculated. Work from [26] uses a combination of nine gray-scale, color, and geometrical features to determine if a banknote was manufactured using intaglio printing. Texture roughness features are deployed in [29] after which a 100 authentic banknotes are enrolled to determine the range variability of the final feature vectors for authentic notes.…”