Sökning: "Ben Bilder"
Visar resultat 1 - 5 av 18 uppsatser innehållade orden Ben Bilder.
1. Dense Foot Pose Estimation From Images
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : There is ongoing research into building dense correspondence between digital images of objects in the world and estimating the 3D pose of these objects. This is a difficult area to conduct research due to the lack of availability of annotated data. Annotating each pixel is too time-consuming. LÄS MER
2. Magnetresonanstomografi av barn - Alternativa tillvägagångssätt för att minska behovet av sedering och generell anestesi
Kandidat-uppsats,Sammanfattning : Sammanfattning Bakgrund: Barn som genomgår MR-undersökning upplever miljön som obehaglig och skrämmande. För att framställa bilder av diagnostisk kvalitet krävs det att barnet ligger helt stilla i magnetkameran under en längre tid, detta kan barn uppleva svårigheter med. LÄS MER
3. Material decomposition using a photon counting X-ray detector in low energy range
Master-uppsats, Lunds universitet/SjukhusfysikerutbildningenSammanfattning : Material decomposition in X-ray imaging is used to separate different materials or elements in an image and to quantify their respective concentration. The material decomposition and quantification are made possible by the dependency of attenuation on the attenuating material and photon energy. LÄS MER
4. 2D & 3D phase retrieval for propagation-based X-ray phase-contrast tomography
Master-uppsats, Lunds universitet/Synkrotronljusfysik; Lunds universitet/Fysiska institutionenSammanfattning : Propagation-based X-ray phase-contrast tomography is a 3d imaging technique that utilizes two-dimensional projections from different angular views $\theta =[0,\pi]$ to reconstruct the 3D object information. The phase-contrast allows for higher feature contrast than conventional transmission tomography, as the phase interference gives rise to a sharp edge contrast. LÄS MER
5. Detection and categorization of suggestive thumbnails : A step towards a safer internet
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The aim of this work is to compare methods that predict whether an image has suggestive content, such as pornographic images and erotic fashion. Using binary classification, this work contributes to an internet environment where these images are not seen out of context. LÄS MER