Counters for various kinds of bank notes require high-speed distinctive point extraction and recognition for notes. In this paper we propose a new point extraction and data extraction method from specific parts of a bank note representing the same col...
Counters for various kinds of bank notes require high-speed distinctive point extraction and recognition for notes. In this paper we propose a new point extraction and data extraction method from specific parts of a bank note representing the same color. The recognition algorithm uses a back-propagation neural network that has coordinate data input. The proposed algorithm is designed to minimize recognition time.