基于图像分析的人民币清分方法研究与实现-计算机应用技术专业论文.docxVIP

优秀毕业论文 精品参考文献资料 研究生优秀毕业论文 硕士学位论文 硕士学位论文 基于图像分析的人民币清分方法研究与实现 Abstract The paper currency soner is an imponant tool fbr banks and other nnancial institutions in paper cun．ency soning，counting，and identi矽ing counterfbit money． It do the banknote sorting work fast and emciently inStead of manual work．The criticaltechnology of bills clearing system is based the image analysis and processing of paper currency． The paper use refIection，transmission and coIor images of RMB and theories that incIude digital image processing，machine leaming and neural ne觚ork to achieVe these aIgorithms include preprocessing of RMB images， detecting note’s direction and denomination，identi母ing new and old bi¨s and recognition of RMB crown word numbe The main contents follows： (1)In the image preprocessing module ofthis paper，firstly，according to the gray scale diff．erence between ta唱et and back伊ound，we put forward a fast method to find these dots that in the RMB image edges．Then the least square method is appIied fbr ntting a straight Jine．FinaJJy，we obtain fbur boundaJy lines of the banknote image．The paper correct banknote image by translating pixels instead of a nornlal algorithm that rotate pixels for tilt correction for banknotes．The computation loads of the method is low，so it’s speed is faster than rotating pixeIs． (2)In the module of detecting note’s direction and denomination，the grid featllre is applied．The featlJres are obtained from banknote gray and color image．When we extract features from color image，the RGB space and H in HSV space is used．For classi矗er section， we select LVQ for classification． In this paper，a simple and reIiable bin identification system is designed that the Value of the bill were successiVely oriented identification (3)In the part of detecting new old bills，the Rl、，IB transmission image is anaIyzed． The paper get feature from the histo伊am of the trans