پديد آورنده :
احمدي، مهدي
عنوان :
تغيير اندازه تصوير با استفاده از نقشه‌ي برجستگي مبتني بر بخش‌بندي معنايي
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
مخابرات سيستم
محل تحصيل :
اصفهان : دانشگاه صنعتي اصفهان
صفحه شمار :
يازده، 109ص.: مصور، جدول، نمودار
استاد راهنما :
شادرخ سماوي، نادر كريمي
توصيفگر ها :
تغيير اندازه تصوير , سيستم بينايي انسان , بخش‌بندي معنايي , شبكه عصبي , تشخيص برجستگي
استاد داور :
محمدرضا احمدزاده، رسول اميرفتاحي
تاريخ ورود اطلاعات :
1398/04/12
دانشكده :
مهندسي برق و كامپيوتر
تاريخ ويرايش اطلاعات :
1398/04/12
چكيده انگليسي :
Image Retargeting Using Semantic Segmentation Based Saliency Map Mahdi Ahmadi June 2019 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Persian Supervisors Dr Shadrokh Samavi Dr Nader KarimiAbstractImage retargeting is an image processing task to make images of arbitrary sizes capable of being displayed on screenswith different sizes This work should be done so that high level visual information and low level features such astexture remain as intact as possible to the human visual system while the output image may have different dimensions Thus simple methods such as scaling and cropping are not adequate for this purpose In recent years researchers havetried to improve the existing methods and introduce new ones However a specific method cannot be utilized to retargetall images In other words different images require different retargeting methods Image retargeting has a close rela tionship to image saliency detection which is relatively a new image processing task Earlier saliency detection methodswere based on local and global but low level image information These methods are called bottom up methods On theother hand newer methods are top down and mixed methods In this thesis after reviewing the existing methods inboth saliency detection and retargeting we introduce the proposed methods in both of them In saliency detection theconcept of image context and a saliency detection method based on semantic segmentation are introduced The proposedsaliency detection method is mixed bottom up and top down After saliency detection a modified version of an existingretargeting method is utilized to retarget the images The results suggest that the proposed image retargeting pipelinehas a good performance compared to other tested methods Also the subjective evaluations on the Pascal dataset canbe used as a dataset to image retargeting quality assessment Keywords Image Retargeting Human Visual System Semantic Segmentation Neural Networks Saliency De tection
استاد راهنما :
شادرخ سماوي، نادر كريمي
استاد داور :
محمدرضا احمدزاده، رسول اميرفتاحي
