Indian Currency Denomination Recognition and Fake Currency Identification

Abstract

Visually impaired and senior citizens find it difficult to identify different banknotes, driving the need for an automated system to recognize currency notes. This study proposes recognizing Indian currency notes of various denominations using Deep Learning through the CNN model. While not recognizing currency notes is one issue, identifying fake notes is another major issue. Currency counterfeiting is the illegal imitation of currency to deceive its recipient. The current existing methodologies for identifying a phony note rely on hardware. A method completely devoid of hardware that relies on specific security features to help distinguish a legitimate currency note from an illegitimate one is much needed. These features are extracted using the boundary box region of interest (ROI) and Canny Edge detection in OpenCV implemented in Python, and the multi scale template matching algorithm is applied to match the security features and differentiate fake notes from legitimate notes.

Fake Currency Detection using Modified Faster Region-Based Convolutional Neural Network

“…OCR has the lowest accuracy of the three image processing techniques with 73.33 percent across all models. The proposed procedure has an approximate overall accuracy of 93.33 percent and an average execution time of 6-7 seconds [8].…”

“…In [8], researchers looked on the topic of counterfeit currency detection. Detecting edges, extracting features, and identifying the authenticity of the currency notes.…”

“…Image processing and neural networks are two of the more common types of technology that are utilized in the process of existing currency identification systems available in literature. However, the amount of processing time required for all of these methods is rather extensive [8].…”

Developing a Model for Detection of Ethiopian Fake Banknote Using Deep Learning

“…We proposed a deep CNN model for the new Ethiopian banknotes. Since each banknote paper currency has unique features, the deep CNN method is used for fake detection (Padmaja et al, 2021). Deep learning techniques in computer vision (Devid and Surendra, 2020) focus on the extraction and learning of features in the image using a sum (S) of a kernel (generated elements) and those (m, n) (Mahesh et al, 2021) matrix data.…”

“…In this paper, the features map includes patterns from the provided banknote image. ReLU activation functions are passed through each value of the feature map (Padmaja et al, 2021). The recovered feature map is sent to the Max pooling layer, which lowers the feature map's resolution and the CNN network's computational cost.…”