Key Algorithms Research For Bill Sorter Based On Digital Image Process

With the great development of economy, the circulation of commodity and money become faster and faster. At the same time, there are more and more damaged and defiled bills. These bills result in a inconvenience of people' daily life which become a block of the commodity circulation .And bills used in ATM specially demand high quality. But in bank, the bills classification is still accomplished by manpower that is inefficient. The work of bills classification becomes a burden in finance system. So the domestic demand of bill sorter is very exigent.For consummation of indigenous bill sorters, on basis of reviewing the existent effort, the author do research on some key algorithms for small bill sorter based on digital image process .The major achievements of this paper include: 1 Bring forward an effective skew image correction algorithm for the first time. The edge line of skew image can be quickly located using the algorithm. It helps bill sorter to quickly correct the skew bill images. 2 A quick method of printed digits recognition is brought forward. For quickly recognize the printed digits, we extract two features by projecting the digit image on the horizontal and vertical median line, then encode them. 3 Bring forward an algorithm which can classify the new and used bills. This is the stress and difficulty of the bill sorter system. We classify bills according to the histogram similarity between template and samples which is calculated by the algorithm of DTW. It is very efficient through many experiments.