10263

9481

كارشناسي ارشد

الكترونيك

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1393

هفده، 100ص.: مصور، جدول، نمودار

ص.ع. به فارسي و انگليسي

شادرخ سماوي، نادر كريمي

نادر كريمي

30/2/94

1396/10/03

كتابنامه

برق و كامپيوتر

مهندسي برق و كامپيوتر

ID9481

چكيده @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ 4 @ 3 @ 2 @ 1 6 5

NO REFERENCE IMAGE QUALITY ASSESSMENT Najmeh Soltanian n soltanian@ec iut ac ir Date of Submission 2014 12 7 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Shadrokh Samavi Samavi@cc iut ac ir Nader Karimi nader karimi@cc iut ac irAbstractNowadays with advances in technology and the pervasiveness of using 2D and 3D images we needmeasures that assess the visual quality of images Based on amount of information from reference image existing method are divided into three categories no reference reduced reference and full reference Thereare many full reference and reduced reference methods for 2D images but in many cases there is no accessto the original image Most of the existing no reference visual quality assessment methods are applicationspecific universal no reference schemes for 2D images have high computational complexity which are notsuitable for real time applications In this thesis a fast general purpose method for quality evaluation ofimages is presented Spatial and wavelet domain features are extracted from two dimensional images thatchange with the type and severity of distortions The most effective of these features are selected by afeature selection algorithm In addition to maintaining the performance reducing the number of features also minimizes the complexity of the procedure Afterward the selected features are used as inputs to theneural network The obtained values were tested on a standard database Experimental results show that theproposed method is not only computationally simple but is highly in accordance with the subjective scores Stereo image quality assessment is known as one of the challenges in image processing Compared with 2Dimage quality assessment methods current stereo techniques have less performance Most of them are full reference and almost all of the no reference ones are application specific The only no reference generalmethod documented in this context has shown poor performance compared to the two dimensionalmethods In this thesis a no reference general purpose method is proposed that creates the binocularcombined and anaglyph images from left and right stereo images After spatial domain feature extraction features of each synthesized image are given into the neural network separately The third neural network takes the outputs of these two networks in order to improve the results This criterion was tested on astandard database and experimental results show that the proposed approach is consistent with the results ofhuman evaluation Keywords 2D Image quality assessment Stereo image Quality Assessment Natural Scene Statistics Feature subset selection Nearal network Synthesized image

شادرخ سماوي، نادر كريمي

نادر كريمي