Quantitative Currency Evaluation in Low-Resource Settings through Pattern Analysis to Assist Visually Impaired Users

2025-09-08

AI Summary

Existing currency recognition systems for visually impaired users in low-resource settings neglect usability (e.g., physical damage) and authenticity (e.g., counterfeiting) assessment. Method: We propose a lightweight, on-device currency evaluation system featuring a Unified Currency Damage Index (UCDI), integrating a compact CNN, binary mask-based degradation analysis, chromatic distortion modeling, structural feature degradation quantification, and feature-level template matching—enabling simultaneous denomination classification, physical damage quantification, and counterfeit detection. Results: Evaluated on 82,000 banknote images from multiple countries, the model achieves ≤98.6% denomination accuracy, ≥97.3% F1-score for counterfeit identification, and strong agreement with human damage annotations (Spearman ρ = 0.91), while maintaining low parameter count and real-time edge inference capability. This work is the first to jointly model integrity, authenticity, and readability, significantly enhancing practical security under resource constraints.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Currency recognition systems often overlook usability and authenticity assessment, especially in low-resource environments where visually impaired users and offline validation are common. While existing methods focus on denomination classification, they typically ignore physical degradation and forgery, limiting their applicability in real-world conditions. This paper presents a unified framework for currency evaluation that integrates three modules: denomination classification using lightweight CNN models, damage quantification through a novel Unified Currency Damage Index (UCDI), and counterfeit detection using feature-based template matching. The dataset consists of over 82,000 annotated images spanning clean, damaged, and counterfeit notes. Our Custom_CNN model achieves high classification performance with low parameter count. The UCDI metric provides a continuous usability score based on binary mask loss, chromatic distortion, and structural feature loss. The counterfeit detection module demonstrates reliable identification of forged notes across varied imaging conditions. The framework supports real-time, on-device inference and addresses key deployment challenges in constrained environments. Results show that accurate, interpretable, and compact solutions can support inclusive currency evaluation in practical settings.

Problem

• Currency recognition overlooks usability and authenticity in low-resource settings
• Existing methods ignore physical degradation and forgery detection limitations
• Visually impaired users need offline validation in constrained real-world environments

Innovation

• Lightweight CNN models for classification
• Unified Currency Damage Index for usability
• Feature-based template matching for counterfeit detection