Classificando Cédulas Brasileiras (R$) Usando Análise De Imagem Por Smartphone

Abstract

A new method to identify the authenticity of Brazilian banknotes (R$) is proposed using digital image analysis by a smartphone application, Photometrix ® , associated with chemometric tools. Authentic banknotes (n = 4) obtained in local bank and falsified (n = 12) by the author himself by means of three printers (laser-Deskjet ® , wax-Color Qube ® and inkjet-Deskjet ®) were used for the development of the methodology. An experimental planning was performed to evaluate the authenticity of the banknotes determining: the best region (holographic band, tactile region in the lower left and right upper number, effigy microimpressions, lower number left, animal figure, watermark and puzzle); Region of Interest (ROI) (16x16; 32x32 and 64x64 pixels), focal length (8, 12, 15 and 20 cm) and variation of the smartphone (Motorola G5 Plus, Samsung S7 and LG K10). The best regions chosen were effigy microimpressions and round the animal. Promising results were obtained from ROI 16x16 pixels with focal length fixed at 10 cm. Thus, the application presents promising features for analyzing the authenticity of banknotes by digital images making it fast, non-destructive, portable, with low cost, and can be accessed by all society.

Use of a Portable Microscope Combined with a Smartphone to Determine the Authenticity of Brazilian Banknotes and National Driver’s Licenses

“…Vittorazzi et al 22 presented a study using the PhotoMetrix ® application to classify Real banknotes through digital images for the R$20, R$50 and R$100 denominations. An optimization test was performed to determine the best parameters for classifying the images; the best region was the microimpression in the effigy and around the animal, which were acquired at 16 × 16 pixels, with a focal length of 10 cm and with controlled ambient luminosity.…”

“…To carry out an exploratory analysis of the results, a principal component analysis (PCA) and a hierarchical cluster analysis (HCA) were performed using the PhotoMetrix ® application with the portable microscope and the images obtained with the smartphone (Samsung S7, android 9.0 pie, 12 megapixel camera, optical stabilization, 4290 × 2800 pixel resolution, and F 1.7 aperture). In the PCA, the data were autoscaled using the channels red (R), green (G), blue (B), hue (H), saturation (S), value (V), lightness (L) and intensity (I), 22,23 with a region of interest (ROI) of 64 × 64 and a magnification factor of 120×. Using the intensity of the channels to compose the data matrix, we had a total of 2,048 variables/information, since each component generates an intensity of 256 values from the pre-processed data by autoscaling.…”

“…This approach is used widely since it allows for visualizing the safety items developed by CBB. 2 The use of simple and low-cost analyses in scientific settings has been growing due to recent technological advances such as the use of portable equipment for analyzing digital images, [19][20][21][22][23] which have been shown to be fast, non-destructible and reliable for specific forensic applications. 1 In this context, a portable microscope was combined with a smartphone (equipped with the PhotoMetrix ® application) to investigate the authenticity of Brazilian banknotes (R$50 and R$100) and national driver's licenses (NDLs).…”

PhotoMetrix and colorimetric image analysis using smartphones

“…Vittorazzi et al 136 proposed a method for classifying Brazilian banknotes from analysis by digital images using a smartphone. The objective of the work was to identify the authenticity of Brazilian banknotes of R$ 10, 20, 50, and 100 using the PhotoMetrix application.…”

“…Through the researches that used PhotoMetrix ® early presented, it is possible to visualize the versatility of this application, because it was used in different analysis, presenting significant results. It is possible to carry out direct analysis, 126,136 that is, without performing sample preparation, analysis of solid 120 and liquid samples, [131][132][133]135 with the use of chambers to store the samples, 121,124,125,129,134 or without lighting control accessories, 127 in addition to allowing the sample to be conditioned in different ways to capture images such as paper 122,123 and SDS-PAGE 128,130 for example. Figure 12 shows four different ways of acquiring images related to the previously presented articles that used Photo-Metrix app in their analysis, where in some works, chambers were made to capture images, and in others, the image acquisition was performed without light control.…”