پديد آورنده :
علي خواجه، قاسم
عنوان :
تكرار متوالي تطبيق ويژگي و تخمين تبديل براي تشخيص جعل كپي-انتقال تصاوير
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
كامپيوتر - هوش مصنوعي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
يازده،83ص.: مصور،جدول،نمودار
يادداشت :
ص.ع.به فارسي و انگليسي
استاد راهنما :
عبدالرضا ميرزايي
استاد مشاور :
مهران صفاياني
توصيفگر ها :
تشخيص جرم چند رسانه اي , خوشه بندي c-means فازي
تاريخ نمايه سازي :
93/12/20
دانشكده :
مهندسي برق و كامپيوتر
چكيده انگليسي :
Alternating feature matching and transformation estimation for image copy move forgery detection Ghasem Alikhajeh g alikhajeh@ec iut ac ir Date of Submission 2015 01 11 Department of Electrical and Computer Engineering IsfahanUniversity of Technology Isfahan 84156 83111 IranDegree M Sc Language FarsiSupervisor Abdolreza Mirzaei mirzaei@cc iut ac irAbstractCopy move forgery is the simplest and most common method for image manipulation Inthis kind of forgery one zone from the image is copied and then post processed Theseprocesses could be rotation and scaling After that the transformed area is put into the goalzone The aim of copy move forgery is to hide an object objects or duplicate it them inthe image The copy move forgery detection methods have five main steps pre processing feature extraction matching transformation estimation and post processing Matching andtransformation estimation have important role in the detection process Some of these stepsmay be affected by existing noise in the images The current methods execute these stepsseparately and in case of existing error in a step it could be propagated to the nest steps andaffects the detection result In this thesis detection steps collaborate with each other tosolve the mentioned problem and if an error happens in a step it will be detected in nextsteps and it will be corrected We formulize this collaboration by defining and optimizing acost function This function includes matching and transformation estimation steps Afterthat in an iterative procedure the steps will be executed and in case of error detection itwill be corrected The efficiency of the proposed method is analyzed in terms of image andpixel level accuracy transformation matrix accuracy two dataset of simple and expertforgery images are used in the experiment and robustness against rotation and scaling Theexperimental results show the better efficiency of the proposed method Keywords copy move forgery detection transformation estimation multimedia forensic fuzzy c means clustering
استاد راهنما :
عبدالرضا ميرزايي
استاد مشاور :
مهران صفاياني
