Sökning: "Bildförbättring"

Visar resultat 1 - 5 av 10 uppsatser innehållade ordet Bildförbättring.

1. 1. High Resolution Quality Enhancement of Digitized Artwork using Generative Adversarial Networks

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

   Författare :Dennis Magnusson; [2022]
   Nyckelord :Image enhancement; Image style transfer; Image superresolution; Machine Learning; Bildförbättring; Bildstilöversättning; Bildsuperupplösning; Maskininlärning;

   Sammanfattning : Digitization of physical artwork is usually done using image scanning devices in order to ensure that the output is accurate in terms of color and is of sufficiently high resolution, usually over 300 pixels per inch, however the usage of such a device is in some cases unfeasible due to medium or size constraints. Photography of the artwork is another method of artwork digitization, however such methods often produce results containing camera artifacts such as shadows, reflections or low resolution. LÄS MER

3. 2. Unsupervised Image Enhancement Using Generative Adversarial Networks : An attempt at real-time video enhancement

   Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för visuell information och interaktion

   Författare :Fredrik Gustafsson; [2021]
   Nyckelord :machine learning; GAN; image enhancement; unsupervised training; maskininlärning; GAN; bildförbättring; oövervakad inlärning;

   Sammanfattning : As the world has become more connected meetings have moved online. However, since few have access to studio lighting and uses the embedded webcam the video quality can be far from good. Hence, there is an interest in using a software solution to enhance the video quality in real time. LÄS MER

4. 3. Object Detection with Deep Convolutional Neural Networks in Images with Various Lighting Conditions and Limited Resolution

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

   Författare :Roman Landin; [2021]
   Nyckelord :Object detection; Super Resolution image generation; Low-Light image enhancement; Computer Vision; Detektion av objekt; Bildgenerering med superupplösning; Förbättring av bilder med dålig belysning; Datorseende;

   Sammanfattning : Computer vision is a key component of any autonomous system. Real world computer vision applications rely on a proper and accurate detection and classification of objects. A detection algorithm that doesn’t guarantee reasonable detection accuracy is not applicable in real time scenarios where safety is the main objective. LÄS MER

5. 4. How post-processing effects imitating camera artifacts affect the perceived realism and aesthetics of digital game graphics

   Kandidat-uppsats, Södertörns högskola/Institutionen för naturvetenskap, miljö och teknik

   Författare :Charlie Raud; [2018]
   Nyckelord :post-processing effects; 3D graphics; image enhancement; qualitative study; focus groups; realism; aesthetics; post-processing effekter; 3D-grafik; bildförbättring; kvalitativ studie; fokusgrupper; realism; estetik;

   Sammanfattning : This study investigates how post-processing effects affect the realism and aesthetics of digital game graphics. Four focus groups explored a digital game environment and were exposed to various post-processing effects. LÄS MER

7. 5. Trainable Activation Functions For Artificial Neural Networks

   Kandidat-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; Lunds universitet/Institutionen för astronomi och teoretisk fysik - Genomgår omorganisation

   Författare :Jim Öhman; [2018]
   Nyckelord :ANN; ARTIFICIAL NEURAL NETWORKS; ACTIVATION FUNCTIONS; REGULARIZATION; Science General;

   Sammanfattning : Artificial Neural Networks (ANNs) are widely used information processing algorithms based roughly on biological neural networks. These networks can be trained to find complex patterns in datasets and to produce certain output signals given a set of input signals. LÄS MER