Automatic Counterfeit Currency Detection Using a Novel Snapshot Hyperspectral Imaging Algorithm

Abstract

In this study, a snapshot-based hyperspectral imaging (HSI) algorithm that converts RGB images to HSI images is designed using the Raspberry Pi environment. A Windows-based Python application is also developed to control the Raspberry Pi camera and processor. The mean gray values (MGVs) of two distinct regions of interest (ROIs) are selected from three samples of 100 NTD Taiwanese currency notes and compared with three samples of counterfeit 100 NTD notes. Results suggest that the currency notes can be easily differentiated on the basis of MGV values within shorter wavelengths, between 400 nm and 500 nm. However, the MGV values are similar in longer wavelengths. Moreover, if an ROI has a security feature, then the classification method is considerably more efficient. The key features of the module include portability, lower cost, a lack of moving parts, and no processing of images required.

Evaluation of Spectrum-Aided Visual Enhancer (SAVE) in Esophageal Cancer Detection Using YOLO Frameworks

“…Conversely, the green filter, synchronized with the secondary absorption peak, unveils deeper lesions in cyan. HSI, extensively applied in diverse fields like air pollution detection [17,18], satellite photography [19][20][21], geology [22][23][24], counterfeit detection [25], military [26,27], agriculture [28,29], etc., emerges as a promising technology when integrated with artificial intelligence deep learning for EC spectral data analysis. Tsai et al, [30] used the HSI method in conjunction with single-shot multibox detector algorithms.…”

Detection of counterfeit holograms using hyperspectral imaging

“…The majority of optical technologies have been used to identify various forms of fraud, such as fake money, prescription medications, papers, and artwork [1]. Nonetheless, the identification and categorization of duplicate holograms is one area where optical devices are not often used.…”

Early esophageal detection using hyperspectral engineering and convolutional neural network

“…The use of hyperspectral imaging (HSI) technology in conjunction with artificial intelligence (AI) deep learning (DL) techniques for the analysis of spectral data pertaining to esophageal cancer (EC) has the potential to enhance the efficiency and precision of diagnostic procedures [5]. Hyperspectral pictures possess spectral intervals at the nanoscale level, resulting in a much greater capacity to detect spectrum information compared to multispectral images [6][7][8][9]. Spectrum conversion refers to the application of an imaging spectrometer to capture a picture including a broad range of wavelengths [10,11].…”