美元识别检伪及新旧等级分类系统的设计与实现-软件工程专业毕业论文.docxVIP

哈尔滨工业大学工程硕士学位论文 哈尔滨工业大学工程硕士学位论文 - - II - Abstract The technology of paper currency recognition is a typical issue in the field of recognition, and application of the technology developed the paper currency sorter has also been widely used and promoted. Paper currency sorter has count money, currency examines, paper currency and other features, and it play a more and more important role in bank area. How to identify images is a key problem of paper currency sorter processing system. Because the systems real-time requirements, the image processing algorithms in-depth study has great significance. The system of paper currency sorter is consist of image processing and identifying subsystem, control subsystem and counterfeit detection subsystem. Our system is the image processing and identifying subsystem, and the counterfeit detection subsystem, it uses the techniques of digital image processing to analyze paper images and identify it, and sort papers finally. This system was been developed and designed aiming at the dollar machine system. It included the image preprocessing, recognition of the face value of the image, recognition of the old and new degree of the paper, identification of incomplete degree of the paper. Image preprocessing of the paper included three functional modules: the brightness compensation of the image, tilt correction of the image, the edge detection of the image. Recognition of the face value of the image included the selection and extraction of the image characteristics and classifier design. The key technology of the sorter system is the real-time image processing and the image recognition. The banknotes image recognition is a very wide application of pattern recognition techniques. With the banknotes image recognition technology using in the banking business sorter, the paper brings out an algorithm based on directional features for the use of banknotes currency recognition in bank notes currency classifiers, mainly on the denomination and t