Deadline: 24 November 2017
Research Associate/Fellow (Fixed-term)
- Closing Date
- Friday, 24th November 2017
- Job Type
- Computer Science
- £26495 to £38833 per annum, depending on skills and experience (minimum £29799 with relevant PhD). Salary progression beyond this scale is subject to performance
An outstanding candidate is required join the Computer Vision Laboratory, in the School of Computer Science to develop computer vision techniques for high-resolution image segmentation. This will support of the University of Nottingham’s BBSRC-funded project “LeMuR: Plant Root Phenotyping via Learned Multi-resolution Image Segmentation”.
The project aims to produce an accurate vision-based system capable of identifying and recovering 2D descriptions of root systems from colour images. Importantly, this system should be robust to widely varying image types and growth conditions, and capable of adapting to new image types with a minimum of annotated data. This project aims to provide a widely adopted software package for any lab performing root system phenotyping, and we will distribute the system internationally. Accurate analysis of root systems will drive improved phenotyping and genetic research, increasing biological understanding of root systems, and improving crop resilience in challenging growth conditions.
As well as the image analysis system, the project will also develop a framework to maintain versions of deep learning models, to allow new networks to be built by users by transferring knowledge from existing, similar networks. This aspect will require understanding of versioning systems, development of annotation tools, and web development skills.
The successful candidate will work within the School’s Computer Vision Laboratory, a well-established research group that has attracted over £2m in research funding within the last year. They will build on Nottingham’s strong track record in computer vision for plant phenotyping and incorporate state of the art machine learning approaches to produce novel image segmentation methods and software tools. The University of Nottingham has identified global food security and plant phenotyping as a research priority area, and is investing significantly in these areas over the next five years.
Applications are invited from highly skilled researchers in Computer Vision, Image Analysis or related areas. Strong programming skills are required, and experience of working in a multidisciplinary environment is an advantage.
Applicants must hold or have a PhD (or equivalent) or be near completion in Computer Vision, Image Analysis or a closely related discipline. They should be able to work both independently and collaboratively and be able to meet tight deadlines. Good communication skills, allowing effective work within distributed, multidisciplinary teams, are crucial. Candidates will be expected to disseminate research results in peer-reviewed journals and conferences.
This full-time post is fixed-term for a period of 18 months.
Informal enquiries may be addressed to Dr Michael Pound, tel: 0115 8466510 or email email@example.com. Please note that applications sent directly to this email address will not be accepted.
The University of Nottingham is an equal opportunities employer and welcomes applications from all sections of the community.