Researcher

Professor Arcot Sowmya

My Expertise

Computer Vision; Medical Imaging; Remotely sensed image analysis

Keywords

Field of Research (FoR)

SEO tags

Biography

I obtained a PhD degree in Computer Science from Indian Institute of Technology, Bombay. I currently hold the position of Professor in the School of Computer Science and Engineering, UNSW. My major research interest is in the area of  Machine Learning for Computer Vision and includes learning object models, feature extraction, segmentation and recognition based on computer vision, machine learning and deep learning, with applications in...view more

I obtained a PhD degree in Computer Science from Indian Institute of Technology, Bombay. I currently hold the position of Professor in the School of Computer Science and Engineering, UNSW. My major research interest is in the area of  Machine Learning for Computer Vision and includes learning object models, feature extraction, segmentation and recognition based on computer vision, machine learning and deep learning, with applications in medical image analysis, computer aided diagnostics and high resolution remote sensing analysis. In recent years, applications in the broader health area are a focus, including biomedical informatics and rapid diagnostics in the real world. All of these areas have been supported by competitive, industry and government funding.
 
My research in machine learning has also  branched into other data rich domains where similar techniques can make an impact. In the social sciences domain, our research has led to an improved forecasting model for genocide and politicide based on political science datasets, that is useful for policy makers and analysts.

Real-time, concurrent and embedded systems has been a minor research interest over the years, with contributions in electronic design automation and embedded realtime software design.

 

 

 


My Grants

  • Larsen, Large, Sowmya, Baker, Song, Samarasinghe, CCTV analysis of a suicide hotspot –dentifying behaviours prior to suicide, SPRF Innovation Grant, AUD 97,255 (2019)
  • Jasgo R&D Pty Ltd, University of New South Wales (Sowmya, Cassis, Gibson), Amalgamated Holdings Ltd, Blue Ocean Equities Pty Limited, Artificial Intelligence System for Rapid Diagnostics of Disease Causing Mites and Insects, Cooperative Research Centres Projects Round 6,  AUD 2,951,126 (cash) 2019-2022  
  • Hameiri, Trupke, Sowmya, Cheaper PV energy using photoluminescence and a novel multi-method approach UNSW Goldstar award, 2019 AUD 40,000
  • Sowmya, Cassis, Deep Learning for Detection of House Dust Mites from Imagery TechVoucher scheme, NSW Department of Industry’s $18 million Boosting Business Innovation Program (BBIP) AUD 30,000 (2018-19)
  • Cassis, Sowmya, Development of HDM identification prototype Stage 2, Jasgo R&D Pty Ltd AUD 264K (2018-19)
  • Iyer, Sowmya, Blair, White, DeepLOOP: Deep Learning technologies to screen Radiology Films for Osteoporosis, PoWH Foundation grant AUD 60,000 (2018-20)
  • Holloway, Sowmya, Vinod, Dowling, Learning from and Improving target volume delineation in radiotherapy,  UNSW Biomedical Engineering Seed Fund AUD 443,588 (2018-2020)  
  • Cassis, Sowmya, Allergy Bug Project, Jasgo R&D Pty Ltd AUD 189K (2017)
  • Sowmya, Mateus Unified Framework for Medical Image Analysis for Prostate Cancer University of New South Wales/Go8 - Germany Joint Research Cooperation Scheme AUD 25,000 (2016-17)
  • Goldsmith, Sowmya, Butcher, Advancing Genocide Forecasting: New Definition, Methods, and Forecasts ARC DP AUD 285,000 (2016-18)
  • Roe, Sowmya, Jones, Professional Practicum  including programs such as: Social entrepreneur practicum for business students, Short Term Practicum for Engineering, Medical Clerkship Practicum New Colombo Plan 2016 mobility projects, Dept of Foreign Affairs and Trade AUD 198,000 (2016-18)
  • Kanhere, Sowmya, Hollick, Preserving Privacy in a Camera-Rich World Cyber Security Research Funding, UNSW AUD 55,000 (2015)

My Qualifications

PhD CompSci(IITB), MTech CompSci (IITB), MSc Math. (IITB), BSc. Math. (Madras)


My Awards

  • ARC Postgraduate Council Research Supervisor Award, 2019
  • Best Student Paper award, M. Gibson, D. Kaushik, A. Sowmya, Robust CNNs for detecting collapsed buildings with crowd-sourced data, Joint Urban Remote Sensing Event  JURSE 2019, Vannes France, May 22-24, 2019
  • Urban Prediction contest winner, JURSE 2019, Joint Urban Remote Sensing Event), May 2019, Vannes, France, Matthew Gibson, supervised by Sowmya
  • Invited Talk, DICTA 2018, Canberra Dec 11-13, 2018.
  • Highly commended Poster at FoE Postgraduate Research Symposium 2018, Manna Elizabeth Philip, supervised by Sowmya
  • FoE Women in Engineering Top-up scholarship, Priyanka Rana, PhD student jointly supervised by Sowmya, 2019-2022;
  • FoE Women in Engineering Top-up scholarship, Annette Spooner, PhD student under Sowmya’s supervision, 2018-2020 (awarded in July 2018)
  • Westpac Cadetship, 2018-21, Arathy Satheeshbabu, supervised by Sowmya
  • Westpac Cadetship, 2017-20, Upul Senayake, supervised by Sowmya
  • Faculty Writing Fellowship, Nov-Feb 2016, Banafsheh Pazokifard, supervised by Sowmya
  • 3M PhD Career Development Scholarship, Anastasia Levenkova, 2016, supervised by Sowmya
  • FoE Women in Engineering Top-up scholarship, Jing Ke, PhD student under Sowmya’ supervision, 2014-2016
  • Shortlisted for Best Student Paper Award, P. Anderson, Y. Yusmanthia, B. Hengst, and A. Sowmya, Robot Localisation Using Natural Landmarks, RoboCup Symposium 2012, Mexico City, Jun 18-24, 2012.
  • Runner-up in Dean’s Postgraduate Award for Research Excellence, 2008, K. Avnit, PhD candidate supervised by Sowmya
  • CISRA prize in 2007 for student project for EyeUI project, Shihab Hamid and Sunny Leung, students of COMP 9517 Computer Vision 2007, taught by Sowmya
  • Malcolm Chaikin Award for best PhD thesis in Faculty of Engineering for 2007, N. Yager, ``Hierarchical Fingerprint Verification'', 2007, jointly supervised by Sowmya
  • Shortlisted for Best Paper Award, P. Roop, A. Sowmya and S. Ramesh, Automatic Component Matching using Forced Simulation. Proc. 13th International Conference on VLSI Design, Calcutta, India, Jan 2000, IEEE Computer Society Press.
  • Best Student Paper Award, Peters, M. and Sowmya, A., A Real-time Variable Sampling Technique: DIEM, International Conference on Pattern Recognition, IEEE, Brisbane, Australia, 17-20 August, 1998.


My Research Activities

In remote sensing image analysis, new learning techniques for the extraction of linear features in remotely sensed images were designed, that take into account the additional challenges such as new sources of noise and varying image resolutions and spectral characteristics. The impact in this area is evidenced by the journal published in the topmost journal in the area, the International Journal of Photogrammetry and Remote Sensing, which was the second most downloaded paper from the journal's online archives in both 2001 and 2002. Techniques were developed  for automatic map updating in Geographic Information Databases (GIS), and new spatial reasoning techniques for map updating within ARC/Info for use within a mapping agency. A recent contribution to surveying and mapping has been made by building a reliable model for detecting building changes from remotely sensed data. Novel methods based on machine learning were developed to address imbalance and noise in the datasets and multiple correlations between image bands at the pixel level. Spectral, structural and contextual information were exploited and Markov Random Fields (MRF) based models built using geometric information. The different models were fused to improve the detection of building changes. In 2013, the change detection methods developed were applied to live images from WorldView-2 satellite by DigitalGlobe for the use of a government department.

In medical image analysis, my group has been developing innovative learning techniques, including new incremental learning algorithms and innovative image analysis techniques for anatomy and feature extraction based on machine learning and computer visoin. Anisotropic kernels for SVMs were developed and shown to produce improved diffuse disease detection in lung images. Incremental computer-aided diagnosis techniques for diffuse lung diseases based on machine learning were designed and implemented for HRCT lung images. These included multi-view learning for classification of emphysema that can identify severity incrementally; multi-view learning for incremental detection of local structural lung features, comparable to a radiologist; novel feature selection methods for disease classification. Computer-aided techniques based on multi-directional multi-resolution analysis and machine learning have been designed to classify automatically diffuse lung disease patterns. Further, a fully automatic method for 3D detection of calcified pleura in the diaphragmatic area and thickened pleura on the costal surfaces from multi detector computed tomography (MDCT) images has been developed and tested. The method uses other stable organs such as the ribs and costal cartilage, besides the lungs themselves, for referencing and landmarking in 3D. My group also developed techniques to mitigate the risks that ad-hoc incremental revisions pose to medical imaging systems through the ProcessRDR and ProcessNet frameworks. The role of quasi-expertise and its influences on system quality were also established. A fully automatic Computer Aided Diagnosis (CAD) system for diffuse lung diseases from High Resolution CT images was designed and implemented, in collaboration with Medical Imaging Australasia as  clinical and Philips Medical Systems Australasia as industry partners.  Other recent projects include novel feature design for prostate cancer detection, machine learning for recognition and survival analysis of Mild Cognitive Impairment and dementia, analysis of Ultra Wide Field imaging of the retina, early prediction of osteoporosis from incidental CT scans using deep learning,  evaluation of fetal heart function from 4D ultrasound using deep learning and outcomes driven radiotherapy planning using deep learning.  A distinguishing feature of my group’s research in this area is the development of close and sustained connections and collaborations with clinicians and medical scientists as well as application specialists; we are almost never satisfied by training and testing on public datasets alone. We work with radiologists, psychiatrists, obstetrician, endocrinologist, radiation oncologists and medical physicists in our quest to improve health care and delivery

Developing forecasting capability and technology is an important, cutting-edge area of political science research, and my group has made a contribution in a challenging area in collaboration with political scientists, and also translated this contribution into useful knowledge for policy makers and analysts, potentially improving the early warning capacity of governments and international organizations. The knowledge has been disseminated in accessible ways via policy reports, updates to a large group of relevant stakeholders, and via news media.


My Research Supervision


Supervision keywords


Areas of supervision

My major research focus in recent years is on methods to improve detection and diagnosis of disease conditions and survival analysis based on multimodal datasets, including 2D, 3D and 4 D medical images and collections of clinical, demographic, neuropsychological, genetic and other datasets that together are high duimensional and censored. Methods are drwan from computer vision, Artificial Intelligence, machine learning, deep learning and statistics. Details of my past and current projects are available under Research Activities and Grants.

My research collaborations and research grants help to provide a stimulating, multi-disciplinary environment that values teamwork and working with real world datasets. My teaching and research supervision aim to foster the growth of research students within the environment I work in and help to create. I value my students' achievements, growth and maturity and take prid ein their achievements. Almost all my former PhD  students are either in academia, research labs and centres, involved in startup activitie


Currently supervising

  • Jian Kang (on leave)
  •  Matthew Gibson
  •  Annette  Spooner
  •  Sankaran Iyer
  •  Manna Elizabeth Philip
  • Md Shariful Alam

Jointly supervised

  • Feng Zhou
  • Yongzhe Chang
  • Guoqing Wang
  • Mingzhe Wang
  • Priyanka Rana
  • Nuha Aldausari
  • Ramtin Gharleghi
  • Isabella Lee

External Students supervised

  • Mina Ghaffari (Macquarie University)
  • Janan Arslan ( Univerity of Melbourne)

My Teaching

My teaching portfolio is increasingly aligned with my research interests. I initiated the teaching of Computer Vision as a higher level elective and postgraduate course in the early 2000's, and have been solely responsible for it for a long time. The course has undergone many revisions in line with research and industry developments and student interest. The course is now a popular elective for Computer SCience and Engineering undergraduates and postgradutes, with interest also from other Engineering schools. We now have a strong teaching team and the coruse is growing strongly.

During 2011-2015, I was responsible for the Research Methods in Engineering course taken by all Faculty of Engineering research students in their first year. I have also taught second and third year core Computer Science and Engineering courses over the years.

 

View less

Location

Room 412-E, Building K-17 CSE Building
UNSW Kensington Sydney

Map reference (Google map)

Contact

+61 2 9385 6933
+61 2 9385 5995