Sökning: "perceptual similarity"

Visar resultat 1 - 5 av 10 uppsatser innehållade orden perceptual similarity.

1. 1. Using Approximate Computing Circuits to Optimize Power of an ASIC

   Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

   Författare :Padmashree Nuggehalli Srinivasa; Shi-Tien Hsing; [2023]
   Nyckelord :ASIC; Power; Optimization; Approximate Arithmetic Circuits; Approximate Computing; Technology; Technology and Engineering;

   Sammanfattning : The growing demand for network cameras to support real-time image processing and machine-learning applications has created a need for low-power solutions. Although technology scaling makes complex computations feasible, voltage scaling is limited, leading to higher power density and dark silicon problems. LÄS MER

3. 2. An evaluation of U-Net’s multi-label segmentation performance on PDF documents in a medical context

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Fredrik Sebek; [2021]
   Nyckelord :U-Net; SS-U-Net; MultiResUNet; Portable; Document; Format; PDF; Segmentation; Multi-label; Conversion; U-Net; SS-U-Net; MultiResUNet; Bärbart; Dokumentformat; PDF; Segmentering; Konvertering;

   Sammanfattning : The Portable Document Format (PDF) is an ideal format for viewing and printing documents. Today many companies store their documents in a PDF format. However, the conversion from a PDF document to any other structured format is inherently difficult. LÄS MER

4. 3. Content-based music recommendation system : A comparison of supervised Machine Learning models and music features

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Marine Chemeque Rabel; [2020]
   Nyckelord :;

   Sammanfattning : As streaming platforms have become more and more popular in recent years and music consumption has increased, music recommendation has become an increasingly relevant issue. Music applications are attempting to improve their recommendation systems in order to offer their users the best possible listening experience and keep them on their platform. LÄS MER

5. 4. Deep Learning based Video Super- Resolution in Computer Generated Graphics

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Vinit Jain; [2020]
   Nyckelord :Deep Learning; Convolutional Neural Networks; Video Super-Resolution; Computer Generated Graphics; Gaming.; Deep Learning; Convolutional Neural Networks; Video Super-Resolution; Computer Generated Graphics; Gaming.;

   Sammanfattning : Super-Resolution is a widely studied problem in the field of computer vision, where the purpose is to increase the resolution of, or super-resolve, image data. In Video Super-Resolution, maintaining temporal coherence for consecutive video frames requires fusing information from multiple frames to super-resolve one frame. LÄS MER

7. 5. Indoor scene verification : Evaluation of indoor scene representations for the purpose of location verification

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Filip Finfando; [2020]
   Nyckelord :computer vision; perceptual similarity; visual place recognition; indoor scene localization; deep neural networks; datorseende; perceptuella likheter; visuell platsigenkänning; inomhusbild lokalisering; djupa neuronnät;

   Sammanfattning : When human’s visual system is looking at two pictures taken in some indoor location, it is fairly easy to tell whether they were taken in exactly the same place, even when the location has never been visited in reality. It is possible due to being able to pay attention to the multiple factors such as spatial properties (windows shape, room shape), common patterns (floor, walls) or presence of specific objects (furniture, lighting). LÄS MER