Sökning: "flexible images"

Visar resultat 6 - 10 av 54 uppsatser innehållade orden flexible images.

  1. 6. Artificial Neural Networks and Inductive Biases for Multi-Instance Multi-Modal Tabular Data : A Case Study for Default Probability Estimation in Small-to-Medium Enterprise Lending

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

    Författare :Gustav Röhss; [2022]
    Nyckelord :;

    Sammanfattning : The success of artificial neural networks in homogeneous data domains such as images, textual data, and audio and other signals has had considerable impact on Machine Learning and science in general. The domain of heterogeneous tabular data, while arguably much more common, remains much less explored with regards to artificial neural networks and deep learning. LÄS MER

  3. 7. Quantification and Detection of Motion Artifacts in Laser Speckle Contrast Imaging

    Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

    Författare :Dennis Amphan; [2022]
    Nyckelord :Laser speckle contrast imaging; Image registration; Motion artifacts; Detection;

    Sammanfattning : Laser speckle contrast imaging (LSCI) is a non-invasive method for assessment of microcirculatory blood flow. The technique is based on analysis of speckle patterns to build 2D maps of perfusion with high spatial and temporal resolution. LÄS MER

  4. 8. Evaluating Methods for Show-through or Bleed-through Cancellation

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

    Författare :Erik Martin Welin; Andreas Åström; [2021]
    Nyckelord :show-through; bleed-through; cancellation; ICA; thresholding;

    Sammanfattning : The theme of this paper is show-through andbleed-through cancellation of degraded images or manuscripts.Show-through and bleed-through is when the reverse side of amanuscripts shows/bleeds through to the front side. This canseverely impact readability. Four different cancellation algorithmswas chosen for evaluation. LÄS MER

  5. 9. An automated unmanned aerial vehicle – structure from motion pipeline to create analysis-ready digital surface models for coastal monitoring

    Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

    Författare :Maximilian Rafael Huber; [2021]
    Nyckelord :physical geography; ecosystem analysis; geomatics; GIS; UAV; structure-from-motion; machine learning; coastal monitoring; Earth and Environmental Sciences;

    Sammanfattning : Anthropogenic pressure on coastal areas continues to increase, thus intensifying coastal erosion. Coastal monitoring programs are therefore essential to prevent severe ecosystem and economic consequences. Successful coastal monitoring schemes require highly accurate analysis-ready Digital surface models (DSMs) derived using the same workflow. LÄS MER

  7. 10. A Phantom Based Comparison of Image Segmentation Algorithms for Adaptive Functional Volume Determination of the Thyroid Gland using SPECT

    Uppsats för yrkesexamina på avancerad nivå, Stockholms universitet/Fysikum

    Författare :Henrik Berg; [2021]
    Nyckelord :Hyperthyroidism; Nuclear Medicine; SPECT; Functional Volume; Phantom Study; Adaptive Image Segmentation; Thresholding; Region Growing;

    Sammanfattning : Background One of the most used treatments for hyperthyroidism, is therapy with radioactive iodine (131I), which is accumulated in the thyroid gland. To determine the activity of 131I to be administered for a certain absorbed dose, the volume of the gland is of great importance but the historically used methods for estimating the functional volume of the gland are based on large approximations. LÄS MER