Welcome!

  I am currently open to deep learning advisory (industrial) and internship (for PhD students) positions.

I am a PhD student at the University of Wollongong working with Assoc. Prof. Lei Wang, Prof. Changming Sun, and Luping Zhou. I am also part of the Commonwealth Scientific and Industrial Research Organisation (CSIRO)'s Data61 (previously known as NICTA)'s Quantitative Imaging team.

My current research focuses on the development of machine learning algorithms for visual recognition. I am specifically interested in enabling fine-grained recognition in large-scale image and video data with the use of higher-order visual features.

I received MRes in Computer Vision & Machine Learning from the Multimedia University (MMU), Cyberjaya in 2016. I was advised by John See and Chiung Ching Ho in the Visual Processing Lab as a part of the Center for Visual Computing (CVC). Before joining PhD, I was the lead of machine learning sub-group at Advanced Robotic Vision, Vitrox Corporation. Prior to that, I was a lecturer in information technology at International Islamic Univerisity Chittagong and a senior software engineer of web systems at FS Systems.

Research Interests: Computer Vision, Machine Learning, Fine-grained Visual Recognition.


Recent News

21 Nov 2019 : A survey on 'deep learning based HEp-2 image classification' is out in arXiv.
06 Nov 2019 : Awarded 'Best Presentation Award' at UOW SCIT 2019 HDR Workshop.
01 Oct 2019 : The SPD archive website has been released for public use.
01 Apr 2018 : My personal website is on hold until further notice.
21 Mar 2018 : Website up and running!

Recent Research

Masters by Research Thesis

Fine-grained Image Recognition

Fine-grained image classification targets at distinguishing fine-level image categories in images, such as bird species, airplane types, and animal breeds. In addition to the difficulties inheriting from generic image classification such as large intra-class variations and insufficient training data, finegrained classification is much more challenging due to subtle inter-class differences. Read more...


Masters by Research Thesis

Industrial Machine Vision Inspection

At ViTrox, I lead the effort in machine learning in industrial Machine Vision Inspection. It was a effort in developing custom machine learning and computer vision solutions for complex machine vision inspections. My efforts help Vitrox's Advanced Robotic Vision solutions achieve near perfect results. Read more...


Masters by Research Thesis

Human Activity Recognition in Low Quality Videos

Human action recognition (HAR) in video is presently one of fastest growing areas in computer vision research due to the ubiquity and abundance of video data. This research was aimed to investigate the visual recognition of human activities in low quality surveillance videos. Spatio-temporal texture features as tool was proposed in this research to improve the performance of shape and motion features extracted from low quality videos. Read more...


Recent Talks

06 Nov 2019 : Gave a talk on "Applications of Deep Learning for Efficient Autoimmune Disease Detection" at SCIT 2019 HDR Workshop, University of Wollongong.
[Presentation Slides]   [Talk Page]   [Slideshare link]  
16 Apr 2018 : Gave an invited talk on "Computer Vision in Industrial Applications: Standards and Practice" at ViPr Lab, Multimedia Univerisity.
[Presentation Slides]   [Talk Page]   [Slideshare link]  
15 Jun 2017 : Gave a talk on "Making Machine Understand Beauty: A Photography Perspective" at Center of Excellence Machine Vision, Vitrox Corporation, Penang, Malaysia.
[Presentation Slides]   [Talk Page]   [Slideshare link]  
13 Apr 2017 : Gave a talk on "Beyond the traditional: Learning based defect inspection; A case study on V920i" at Center of Excellence Machine Vision, Vitrox Corporation, Penang, Malaysia.
[Presentation Slides]   [Talk Page]   [Slideshare link]  

Students

2017-2018: Cheong Leong Kean, BEng (Hons.), Universiti Sains Malaysia, Penang. Now with Vitrox, Malaysia


Important Downloads


Action Recogniton Toolbox
 
[JIVP] YouTube-LQ-CRFs



© 2018 Saimunur Rahmnan. CC-NC-SA-4.0. Built with Bootstrap v3.3.6. Style adopted from Animesh Garg.