KTH Royal Institute of Technology in Stockholm has grown to become one of Europe’s leading technical and engineering universities, as well as a key centre of intellectual talent and innovation. We are Sweden’s largest technical research and learning institution and home to students, researchers and faculty from around the world. Our research and education covers a wide area including natural sciences and all branches of engineering, as well as architecture, industrial management, urban planning, history and philosophy.
The research group in Mathematical Imaging within the Department of Mathematics at KTH is offering a two-year postdoctoral fellowship based on a grant from the Tandem Forest Values programme at the Royal Swedish Academy of Agriculture and Forestry.
The position is part of a larger international project supported by the Academy of Finland involving collaboration with researchers at LUT-University and University of Oulu. The overall goal is to develop theory and algorithms for image guided optimization of the sawline in processing of forest logs. The position includes research into theory and development of algorithms for joint 3D reconstruction and semantic segmentation. The reconstruction step is done by a trained deep neural network with an architecture that includes a handcrafted physics model for x-ray imaging. The semantic segmentation step is performed using a suitable deep neural network architecture, like a U-Net. The large-scale nature of the reconstruction problem coupled with the time-critical nature of the use requires algorithms that not only execute fast but also minimize memory footprint. Prototype algorithms will be implemented as software components in ODL (http://github.com/odlgroup/odl), which is a python-based software framework for prototyping image reconstruction methods. Ideally one utilizes the couplings in ODL between tomographic projection software (ASTRA) and deep learning frameworks, like PyTorch or TensorFlow.
The research will be pursued at the Department of Mathematics at KTH in close collaboration with researchers at LUT-University and University of Oulu. As a postdoctoral fellow, you will have access to expertise in forestry and unique processing data from the sawline. You will also benefit from the strong research environments at KTH in mathematical sciences and x-ray imaging physics.
What we offer
We seek a candidate with a PhD degree in mathematics, signal processing, computer science, or computational physics/engineering. The candidate should have a strong background from machine learning or signal/image processing, preferably in the context of image processing or tomographic image reconstruction. The candidate should also have experience from software development in scientific computing using Python and/or C/C++ in the context of machine learning. Finally, a successful applicant must be strongly motivated and have the capability to work independently as well as in collaboration with members of the research group.
Great emphasis will be placed on personal competence and suitability.
Trade union representatives
You will find contact information to trade union representatives at KTH's webbpage.
Log into KTH's recruitment system in order to apply to this position. You are the main responsible to ensure that your application is complete according to the ad.
Your complete application must be received at KTH no later than the last day of application, midnight CET/CEST (Central European Time/Central European Summer Time).
Fixed term employment/temporary contract two years from starting date: start April 1, 2020 or according to agreement.
About the employment
The position offered is for, at the most, two years.
A position as a postdoctoral fellow is a time-limited qualified appointment focusing mainly on research, intended as a first career step after a dissertation.
Gender equality, diversity and zero tolerance against discrimination and harassment are important aspects of KTH's work with quality as well as core values in our organization.
For information about processing of personal data in the recruitment process please read here.
We firmly decline all contact with staffing and recruitment agencies and job ad salespersons.
Disclaimer: In case of discrepancy between the Swedish original and the English translation of the job announcement, the Swedish version takes precedence.
Type of employment: Temporary position longer than 6 months
|Title||Postdoc in segmentation and CT-reconstruction with deep learning|
|Employer||KTH Royal Institute of Technology|
|Job location||Valhallavägen 79, 100 44 Stockholm|
|Published||January 17, 2020|
|Application deadline||March 9, 2020|
|Job types||Postdoc  |
|Fields||Software Engineering,   Computational Physics,   Computational Mathematics,   Computational Engineering,   Machine Learning,   Signal Processing,   Image Processing  |