Image Analysis for Risk Item Detection Using CT Images
Location: Sydney, NSW
Duration: 6 months
Rapiscan Systems is a global leading designer, manufacturer and supplier of security technology equipment for use in airport security, port and border security and the protection of public spaces such as government buildings, hotels and sporting stadiums.
Rapiscan Systems is also working with government, industry and academic partners in Australia and New Zealand to develop solutions based on its real-time 3D X-ray computed tomography baggage screening system to automatically detect biosecurity risks at airports and mail pathways, such that these can be confiscated before becoming a risk to the rural economy.
The object of this program is to develop machine learning based methods for image processing and analysis, harnessing the power of deep learning to imaging data, using high speed computational methods to achieve high throughput automatic screening of baggage, parcels and mail.
Research to be Conducted
Rapiscan Systems will utilise 2-3 interns to support its Research and Development program in Australia. The positions will be based alongside the Rapiscan Systems Algorithm Development team in St Leonards, Sydney, NSW. The Rapiscan Systems Algorithm Development team for this project comprises three engineers in Sydney and a further 30 engineers internationally, is focused on 3D image processing and signal analysis. The interns will work within the St Leonards based team and will be involved in the process of developing a data science project:
- Conducting literature review in the field of machine learning as well as its application to the imaging data
- Collecting and developing training and validation data sets for algorithm development
- Designing and implementing Deep Neural Network based methods for object recognition
- Contribute to the integration of Deep Learning algorithms into the software platform
We are looking for a PhD student with the following:
- Programming in Python or C/C++
- Knowledge in Machine Learning, Deep Learning, Image Processing, Computer Vision
- Medical Image Processing and Analysis
The outcome from the intern positions shall include
- a constructed data set which can be used to for developing and validating machine learning risk item detection algorithms
- a set of source code with associated executables to address the specific topic in question
- a detailed technical report to outline the methods considered for the work, the methods implemented during the work and the results obtained using the methods on real image data sets.
In addition, the interns shall be expected to provide recommendations for future work to be conducted under this research and development program. These ideas may be subsequently worked on by members of the full-time engineering staff or future interns. Interns shall be encouraged to publish their work in the scientific literature in partnership with their academic and industry mentors.
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
23 October 2019
APR – 1221