Signal Processing and Communications Laboratory

Department of Engineering

Amarjot Singhas2436.jpg

Position: PhD Student

E-mail: as2436 [@] cam.ac.uk

Office: BN3-02

Thesis Title: Deep Hybrid Architectures for Image Understanding

Supervisor: Prof Nick Kingsbury

Personal Webpage: www.amarjotsingh.com

"I've worked in so many areas—I'm sort of a dilettante. Basically, I'm not interested in doing research and I never have been. I'm interested in understanding, which is quite a different thing. And often to understand something you have to work it out yourself because no one else has done it." — David Blackwell

Background

Amarjot Singh is a third year Ph.D. student in Signal Processing and Communications Laboratory at the University of Cambridge. He is affiliated as a student at the Jesus College, Cambridge.

Before Joining the University of Cambridge, He received a MASc. degree in Biomedical Engineering from Simon Fraser University, Canada in 2014. Prior to his master's degree, he worked as a research engineer at National University of Singapore (2012) focusing on developing beamforming algorithms for underwater imaging. Previous to NUS, He received his Bachelor of Technology in Electrical Engineering from NIT Warangal, India in 2011. In addition to the above-mentioned institutes, he has worked as a research intern for INRIA Sophia Antipolis, University of Bonn, IIT Kanpur, IISc Bangalore and DRDO, India.

He regularly serves as a reviewer for the journals, IEEE Transactions on Medical Imaging, IET Computer Vision and ICTACT Journal on Image and Video Processing.

Research Interests

Amarjot's research is focused on creating Deep Hybrid Architectures for Image Understanding that can learn efficient translation and rotation invariant image representations using hand-engineered filters, non-linear modulus and averaging operators.

Publications (Selected)

1. Amarjot Singh, Nick Kingsbury, "Dual-tree Wavelet Scattering Network with Parametric Log Transformation for Object Classification". 42th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. [ Paper (pdf)]

2. Amarjot Singh, Nick Kingsbury, "Multi-Resolution Dual-Tree Wavelet Scattering Network for Signal Classification". 11th IMA International Conference on Mathematics and Signal Processing, 2016. [ Paper (pdf)] (Oral Presentation)

3. Sandeep Nadella, Amarjot Singh, SN Omkar, "Aerial Scene Understanding Using Deep Wavelet Scattering Network and Conditional Random Field". 14th European Conference on Computer Vision (ECCV) workshops, 2016. [ Paper (pdf)]

4. Naveen Madiraju, Amarjot Singh, SN Omkar, "Level Set Segmentation of Brain Matter using a Trans-Roto-Scale Invariant High Dimensional Feature". 13th Asian Conference on Computer Vision (ACCV) workshops, 2016. [ Paper (pdf)]

5. Amarjot Singh, Jason Au, Parvaneh Saeedi, Jon Havelock. "Automatic Trophectoderm Segmentation of Human Embryo Images by Combining Retinex and Level Sets". IEEE Transactions on Biomedical Engineering, Volume. 62, 2014. [ Paper (pdf)]

6. Amarjot Singh, John Bounassisi, Parvaneh Saeedi, Jon Havelock. "Automatic Blastomere Detection in Day 1 to Day 2 Human Embryo Images using Partitioned Graphs and Ellipsoids". IEEE International Conference on Image Processing (ICIP), 2014. [ Paper (pdf)]