Robust and Real-Time Bangladeshi Currency Recognition: A Dual-Stream MobileNet and EfficientNet Approach

TL;DR

This paper introduces a robust, real-time Bangladeshi currency recognition system using a hybrid CNN architecture combining MobileNetV3-Large and EfficientNetB0, achieving high accuracy and interpretability for assistive tech.

Contribution

It presents a new diverse Bangladeshi banknote dataset, a hybrid CNN model for improved recognition, and incorporates explainable AI for transparency, optimized for resource-limited devices.

Findings

Achieved 97.95% accuracy on controlled datasets

Attained 92.84% accuracy on complex backgrounds

Combined datasets yield 94.98% overall accuracy

Abstract

Accurate currency recognition is essential for assistive technologies, particularly for visually impaired individuals who rely on others to identify banknotes. This dependency puts them at risk of fraud and exploitation. To address these challenges, we first build a new Bangladeshi banknote dataset that includes both controlled and real-world scenarios, ensuring a more comprehensive and diverse representation. Next, to enhance the dataset's robustness, we incorporate four additional datasets, including public benchmarks, to cover various complexities and improve the model's generalization. To overcome the limitations of current recognition models, we propose a novel hybrid CNN architecture that combines MobileNetV3-Large and EfficientNetB0 for efficient feature extraction. This is followed by an effective multilayer perceptron (MLP) classifier to improve performance while keeping computational costs low, making the system suitable for resource-constrained devices. The experimental results show that the proposed model achieves 97.95% accuracy on controlled datasets, 92.84% on complex backgrounds, and 94.98% accuracy when combining all datasets. The model's performance is thoroughly evaluated using five-fold cross-validation and seven metrics: accuracy, precision, recall, F1-score, Cohen's Kappa, MCC, and AUC. Additionally, explainable AI methods like LIME and SHAP are incorporated to enhance transparency and interpretability.