پديد آورنده :
جمشيدي، مريم
عنوان :
شبكه موجك رشته‌ثابت بتا و كاربرد آن در بازشناسي تصاوير برش‌خورده
مقطع تحصيلي :
كارشناسي ارشد
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
سيزده، ۸۳ص.: مصور، جدول، نمودار
توصيفگر ها :
شبكه موجك رشته‌ثابت , خانواده موجك بتا , استخراج ويژگي , تصوير برش‌خورده
استاد داور :
فريد شيخ الاسلام، بهزاد نظري
تاريخ ورود اطلاعات :
1397/07/21
رشته تحصيلي :
برق و كامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
چكيده انگليسي :
Fixed Grid Beta Wavelet Network and its Application in Cropped Image Detection Maryam Jamshidi Maryam jamshidi@ec iut ac ir 12 May 2018 Department of Elecrical and Computer engineering Isfahan University of Thechnology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Dr Maryam Zekri mzekri@cc iut ac ir Advisor Dr Saeid Sadri sadri@cc iut ac ir Abstract Nowadays digital multimedia data plays an important role in everyday s life These data canbe easily generated by a variety of devices such as cell phones cameras and so on On the otherhand a lot of images editing softwares exist Among these volumes of everyday publishing andbroad casting images property rights are also an important issue Also original image detectionbecomes more and more difficult for humans To help solve this upcoming issue many waysproposed Image cropping is one of the most common ways of image changing In this thesis inorder to recognize the original image correspond to a cropped image a smart network based on thewavelet network but with structural change and also neurons type change is presented Ourproposed smart network is a fixed grid wavelet network with the explanation that in standard typewavelet network neurons are from both wavelet function forms and scale function forms and eithertheir combination So our proposed fixed grid wavelet network expanding its neurons library andcan approximate output with more accuracy For proposed network neurons an analytic waveletfamily beta wavelet family is used In this wavelet family shape of wavelet and scale functionscan be changed by two shape controlling parameters In the first step by using the orthogonal leastsquares method we find our dominate network neurons and determined scale and shift parametersof each selected neurons Scale and shift parameters don t change anymore in the following steps Then by using least square method the network output weights are updated After our proposednetwork structural formation is accomplished we use our fixed grid beta wavelet network toidentify images of a library In our proposed method we transmit color image from RGB to HSVcolor form Thus our network output is three weight vectors In order to correctly identify theoriginal image corresponding to a cut image it is necessary to classify weight vectors according toneuron function types Each classified vector is screened with a type appropriate threshold Simulation results show that our proposed network for recognizing up to 80 percent cut imagedrives to better results than other well known network in this field It should also be noted that thisnetwork can be used for other applications such as function approximation Keywords Fixed Grid Wavelet Network Beta Wavelet Family Feature Extraction Cuttedimages
استاد داور :
فريد شيخ الاسلام، بهزاد نظري
