Despite the quickly expanding utilization of Master cards and other electronic types of payment, money is still broadly utilized for ordinary exchanges because of its convenience. However, the visually impaired people may suffer from knowing each currency paper apart. Currency Recognition Systems (CRS) can be used to help blind and visually impaired people who suffer from monetary transactions. In this paper, a Currency Recognition System based on Oriented FAST and rotated BRIEF (ORB) algorithm is proposed. The ORB is based on the FAST detector and the visual descriptor BRIEF (Binary Robust Independent Elementary Features). Its aim is to provide a fast and efficient alternative to Local Scale-Invariant Features (SIFT). The proposed system is applied to Egyptian paper currencies including six kinds of currency papers. Initially, some pre-processing operations are performed on a given currency paper input image. Then, important ROI is extracted from the background. The ORB Algorithm is used for a feature detection and description the input image. Finally, Hamming Distance is used for matching binary descriptors obtained from feature extraction stage. The proposed method is compared with another system (CRSFVI). The experimental results showed that the proposed system can be used in real-world scenarios to recognize unknown currency paper image with a higher accuracy of 96 % and a shorter running time of 0.682 s when compared with the CRSFVI system. |
