Sökning: "Distorted Images"

Visar resultat 6 - 10 av 27 uppsatser innehållade orden Distorted Images.

  1. 6. Image inpainting methods for elimination of non-anatomical objects in medical images

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

    Författare :Andrea Lorenzo Polo; [2021]
    Nyckelord :Medical Imaging; Tumor Ablation; Inpainting; U-Net; Convolutional Neural Network;

    Sammanfattning : This project studies the removal of non-anatomical objects from medical images. During tumor ablation procedures, the ablation probes appear in the image, hindering the performance of segmentation, registration, and dose computation algorithms. These algorithms can also be affected by artifacts and noise generated by body implants. LÄS MER

  3. 7. Low latency object detection on the Edge-cloud AprilTag-assisted object detection and positioning

    Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Dong Wang; [2021]
    Nyckelord :;

    Sammanfattning : This study proposes a low-latency video processing pipeline for object detection and positioning. The pipeline employs GPU-based inferenceframeworks and lightweight models for fast detection. LÄS MER

  4. 8. Effekten av syntetiska cannabinoider med avseende på symtomen av posttraumatiskt stressyndrom : En litteraturstudie om vilken påverkan syntetiska cannabinoider har på symtomen av posttraumatiskt stressyndrom

    Kandidat-uppsats, Linnéuniversitetet/Institutionen för kemi och biomedicin (KOB)

    Författare :Medina Mahmutovic; [2021]
    Nyckelord :Posttraumatiskt stressyndrom; Syntetiska cannabinoider;

    Sammanfattning : Background - Posttraumatic stress disorder, PTSD, is a complex disease that occurs when different kinds of traumatic events happen. The symptoms are individual and vary due to the kind of traumatic experience and the persons reaction. LÄS MER

  5. 9. Disocclusion Inpainting using Generative Adversarial Networks

    Master-uppsats, Mittuniversitetet/Institutionen för informationssystem och –teknologi

    Författare :Nadeem Aftab; [2020]
    Nyckelord :depth image-based rendering DIBR ; generative adversarial network GAN ; neural network; disocclusion;

    Sammanfattning : The old methods used for images inpainting of the Depth Image Based Rendering (DIBR) process are inefficient in producing high-quality virtual views from captured data. From the viewpoint of the original image, the generated data’s structure seems less distorted in the virtual view obtained by translation but when then the virtual view involves rotation, gaps and missing spaces become visible in the DIBR generated data. LÄS MER

  7. 10. Optimisation of card recognition routine

    Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Emil Bagge; [2020]
    Nyckelord :;

    Sammanfattning : Card-dealing machines for the game Bridge are used to automate the time-consuming process of sorting cards. They require methods to recognize each card's suit and value during the process, as the sorting is predetermined. The machine considered in      this thesis uses a webcam that feeds a 30 FPS video stream to a contour analysis algorithm. LÄS MER