3612

3411

كارشناسي ارشد

هوش مصنوعي و رباتيك

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1386

ده، 106، [II] ص.:مصور، جدول، عكس

ص. ع. به فارسي و انگليسي

جواد عسكري، رسول امير فتاحي

محمد حسين سرايي

6/6/86

مهندسي برق و كامپيوتر

ID3411

به فارسي و انگليسي :قابل رويت در نسخه ديجيتال

AbstractImage alignment and stitching are among the oldest and most important applications ofmachine vision Image alignment is used in every video camera with image stabilizationproperty Stitching algorithms which have made the creating of mosaic images are usedin constructing digital maps and stitching satellite pictures In constructing panoramaswhich recently has found important applications in virtual environment advertising andso on a combination of these algorithms is used Meanwhile each particular application is defined under special conditions while thereare efforts to manage these applications automatically and without any preconditions Inthe early attempts for automatic image alignment and stitching these tasks have beenbased on the pixel intensity or color Hence every pixel of images is processed and thenthe transformation between images is derived Because of a huge number of variables pixels and blind search on the transformation parameters these algorithms have highorder of complexity which leads to expensive memory and time cost In addition sincethese algorithms rely on the pixel intensity they are sensitive to illumination view rotation and zooming More recent approaches implement object recognition methods that eliminate the need forcomplete process of the entire images Image alignment is achieved by focusing oninterest regions instead This leads to optimization of time and memory In additiontheses methods are insensitive to illumination change and any other transformation thatmay happen to the images In this thesis we introduce image alignment and stitching and review some existingalgorithms We describe how object recognition approach can be applied in thisprocedure Furthermore we suggest two new algorithms for image alignment andstitching that improve some stages of the algorithms and evaluate them

جواد عسكري، رسول امير فتاحي

محمد حسين سرايي