• Keine Ergebnisse gefunden

43075-01 Probabilistic Shape Modelling

N/A
N/A
Protected

Academic year: 2022

Aktie "43075-01 Probabilistic Shape Modelling"

Copied!
1
0
0

Wird geladen.... (Jetzt Volltext ansehen)

Volltext

(1)

43075-01 Probabilistic Shape ModellingProject description Spring 2020

43075-01 Probabilistic Shape Modelling

Lecturers

Dr. Marcel L¨uthihmarcel.luethi@unibas.chi

Introduction 31. March 2020

Deadline 13. April 2020, 23.55 (submission on Adam)

Introduction

The goal in this project is to complete the femur project, as described in the online course, Step 6.8. More precisely, you will build a femur model from a number of example datasets as detailed in the exercise sheets 1 and 2. Using this model, the goal is to compute a reconstruction (completion) of a set of femur bones with missing parts.

Your tasks

Please follow the detailed instructions given in Step 6.8 on FutureLearn:

https://www.futurelearn.com/courses/statistical-shape-modelling/5/steps/630830.

Submission

To submit your solution, please upload a zip file containing the following items to Adam:

• Data resulting from your work (i.e. the bone reconstructions, your model, ...)

• The Scala source code of your solution

• A short report (approximately 3-5 pages)

Our main source for grading your work will be the report. Please make sure that it is well written and clearly explains the methods you used and your choices of parameters. Also include a discussion of your results.

Grading We will grade the report according to the following criteria:

• Structure of the report, Clarity of exposition (20 %) – How easy is it to understand what you did?

• Theoretical correctness (30 %)

– Does your report show an understanding of the concepts.

• Originality / Own thoughts and ideas (25 %)

– Does your method include ideas that go beyond the “recipe’s“ given in the tutorials

• Quality of the results (25 %)

• – How well did your method reconstruct the given target surfaces.

Challenge

The same project is organized as a challenge, with international participation. We encourage you to participate in this challenge and compete with international researchers and former students of this course. To participate, simply upload your results to the SMIR for evaluation, as described in Step 6.8.

Referenzen

ÄHNLICHE DOKUMENTE

• Global (static) data: The loader allocates a global data area (64 KB) and loads its address into register EDI. The first 8 bytes of the global data area hold the address- es of

Sampling

Once your SMIR account is created, you can proceed to downloading the femur data, by following the instructions in step 5.11.. ”Femur project: data download

Statistical Shape model: A probability distribution of shapes, learned from example data.. Statistical

Once your SMIR account created, you can proceed to downloading the femur data and rigidly align it to the reference, by following the instructions in step 5.11: ”Femur project:

Evaluation: Before designing your Gaussian process, think about properties of the model, which allow you to decide whether your model is a good model of the femur shape or

The goal in this project is to complete the femur project, as described in the online course, Step 6.8.. More precisely, you will build a femur model from a number of

In this hybrid form of data sharing, primary researchers and secondary analysts simultaneously use and re-use qualitative data thereby conserving the intersubjective nature of