Robust and Effective Banknote Recognition Model for Aiding Visual Impaired People

Abstract

Visual disabled Ethiopians find great difficulty in recognizing banknotes. Each Ethiopian banknote has an identical feel, with no Braille markings, irregular edges, or other tangible features that make it easily recognizable by blind persons. In Ethiopia, there's only one device available that will assist blind people to acknowledge their notes. Internationally, there are devices available; however, they're expensive, complex, and haven't been developed to cater to Ethiopian currency. Because of these facts, visually impaired people may suffer from recognizing each folding money. This fact necessitates a higher authentication and verification system that will help visually disabled people to simply identify and recognize the banknotes. This paper presents a denomination-specific component-based framework for a banknote recognition system. Within the study, the dominant color of the banknotes was first identified and so the exclusive feature for every denomination-specific ROI was calculated. Finally, the Colour-Momentum, dominant color, and GLCM features were calculated from each denomination-specific ROI. Designing the recognition system by thereby considering the denomination-specific ROI is simpler as compared to considering the entire note in collecting more class-specific information and robust in copying with partial occlusion and viewpoint changes. The performance of the proposed model was verified by using a larger dataset of which containing banknotes in several conditions including occlusion, cluttered background, rotation, and changes of illumination, scaling, and viewpoints. The proposed algorithm achieves a 98% recognition rate on our challenging datasets.