HIPs鉴别图像识别-模式识别与智系统专业毕业论文.docx

北京邮电大学硕士学位论文HIPs浆别图像识别RECOGNIZING 北京邮电大学硕士学位论文HIPs浆别图像识别 RECOGNIZING HUM埝N INTERACTION PR00FS HI醚，Human Interaction Proofs，is used as the first gate to protect network servers from attacking，and ke印users’private information safe． HIPs act like a Turing machine，when try to access to service，HIPs will provide one picture and ask the client to supply the answer．Through analyzing the response，HIPs will automatically classify the client as human being or code，and then take predefined actions．弧e rational is the gap between natural intelligence and machine perception． In the context of HIPs image，many factors，such as textural background，random noise，occlusion，and deformation，decrease the probability of being hacked．羽：lis thesis is dedicated to deal with deformation。 First，we introduce our recognizing system and details about implementing the system． Then，we use graphical model to model the generation process of HIPs．Under the control of the inner variables，the distribution of the characters extracted from the HIPs images is one low-dimensionality non-linear manifold embedding in high—dimensionality feature space． We propose one method to model this distribution e籁ciently crossing over the non—linearity．In this thesis，we use piece—wise linear manifold to approach to the non-linear manifold，transferring the global non—linearity to local linearity．Through experiments，the system’S performance is boosted． ’A￡the end，our model can be applied to recognize the handwritten digits．For MNIST our result iS 96．54％，and for USPS the result is 96．32％． m 北京邮电大学硕士学位论文 北京邮电大学硕士学位论文 I-nl,s鉴别图像识别 KEY WORDS：linear manifold；linear sub-space；mixture of Gaussian models；EM parameter estimation； Mahalanobis distance；digit recognition IV 北京邮电大学硕士学位论文 北京邮电大学硕士学位论文 HIPs鉴别图像识别 独创性(或创新性)声明 本人声明所呈交的论文是本人在导师指导下进行的研究工作及取得的研究 成果。尽我所知，除了文中特别加以标注和致谢中所罗列的内容以外，论文中不 包含其他人已经发表或撰写过的研究成果，也不包含为获得北京邮电大学或其他 教育机构的学位或证书