Download presentation
Presentation is loading. Please wait.
1
Image Alignment / Reconstruction
Evelyn Cueva, Matthias Ehrhardt, Paul Quinn, Shaerdan Shataer, Jordan TayloR
2
The Problem Object
3
The Problem Object Ideal Sinogram
4
The Problem Object Reality
5
The Problem Reconstruction Reality
6
Options De-jitter the sinogram before image reconstruction (Variational Method; Machine Learning) Joint de-jitter and image reconstruction from sinogram data
7
De-noising using Auto-Encoders
8
What are Auto-Encoders?
X
9
What are Auto-Encoders?
X Encoder π
10
What are Auto-Encoders?
X Xβ² =π(π X ) Decoder π
11
What are Auto-Encoders?
X Xβ² =π(π X ) min ΞΈ XβXβ²
12
De-jitter Auto-Encoders
X Xβ² =π(π X ) min ΞΈ X βXβ²
13
Direct Reconstruction
π π π’
14
Direct Reconstruction
π π π’ π π
15
Direct Reconstruction
π π π’ π
( π π π , π π β₯ (π’)) = π₯ π + π π π
16
Direct Reconstruction
π π π’ π
π π ( π π π , π π β₯ (π’)) = π₯ π + π min π’, π π π π
π π ( π π π , π π β₯ (π’)) β π₯ π 2 π π
17
Going Forward β’ Sinogram reconstruction (Variational Method; Machine Learning) β’ Direct image reconstruction
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.