基于多光谱图像的纸币防伪鉴定技术分析-analysis of banknote anti-counterfeiting identification technology based on multispectral images.docxVIP

华 中 科 技 大 学 硕 士 学 位 论 文 II Abstract Banknote multispectral image security identification technology has been the hot spot in the field of paper currency anti-counterfeiting, relating to the national financial security. The research has great theoretical research value and widespread application background. Banknote image contains the image information of visible light, infrared light and UV light. Through analysis and understanding of the notes multispectral image, we can classify these banknotes high reliably. Also we can stably detect the fake money that the traditional anti-counterfeit technology is unable to distinguish, as well as the money that are altered and in small circulation. Thus guarantee the security and reliability of the currency notes. Multispectral image security identification technology of paper money includes four process, namely the image acquisition, preprocessing, denomination and direction recognition, and authenticity identification. At present, researchers have proposed many ideas regarding to these processes and made good progress. But the main problem lies in the stage of authenticity identification, where extracted features and the design of classifier can’t apply to different illumination, types, old and new, and noise pollution of banknote images. Its ability to detect the fake money is weak, leading to the misinformation of real currency. In this paper the authenticity identification stage, through the use of many regional contrast type strategy puts forward the multispectral image feature selection algorithm area; By the use of the same spectrum of different block image effective gray information of the relative relationship between, and puts forward the gray feature extraction algorithms; By the use of different spectral the same block image matching relation between eight to structure, and puts forward the structure of grain feature extraction algorithms; In order to improve the classification ability, this paper also introduced