پديد آورنده :
مالكي ورنوسفادراني، شيوا
عنوان :
پياده سازي سخت افزاري شبكه موجك به منظور آشكار سازي چهره
مقطع تحصيلي :
كارشناسي ارشد
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
چهارده، 107ص.: مصور، جدول، نمودار
استاد راهنما :
مسعود سيدي
توصيفگر ها :
آناليز اجزاي اصلي , شبكه هاي عصبي
تاريخ نمايه سازي :
1394/06/08
تاريخ ورود اطلاعات :
1396/10/04
رشته تحصيلي :
برق و كامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي
چكيده انگليسي :
108 Hardware Implementation of Wavelet Network for Face Detection Shiva Maleki shiva maleki@ec iut ac ir June 17 2015 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor S M Sayedi Assoc prof m sayedi@cc iut ac irAbstract Accurate detection of human faces in static or video images is the basis in manyapplications such as face recognition human machine interface system tracking and videosurveillance model based video coding and security access control There are manychallenges for intelligent proposed systems that face detection is one of them Detectionrate and number of false detection are used for comparisons with face detection systems The purpose of this research is to provide a face detection system which is based on waveletnetwork The density of each image window first is equalized for reduction of illumination effectsand PCA is used for dimensionality reduction and feature extraction This step is extremelyeffective to streamline the complexity of the system Then wavelet network is used forclassification This wavelet network is a member of Fixed Grid Wavelet Network that is formedwith no need of training Another goal of this research is to compare the neural network withwavelet network To get this aim wavelet network has been replaced with neural network and theresults had been compared with each other To reduce computation of the hardware implementationon FPGA input and output parameters of wavelet function are computed and stored in a LUT thatthe norm of input vector is connected to its address line To calculate the norm of input vector aproposed structure based on the parallel squares units and Carry Save Adders CSA is used Aftercalculation of product phrase Wallace Tree Adder WTA is used to sum the products in squareunits The proposed structure has a low power consumption and short hardware data path Thesimulation results have demonstrated the good performance of the structure Keywords face detection principal component analysis neural networks wavelet network
استاد راهنما :
مسعود سيدي
