Research engineer at Department of ALM, Centre for Digital Humanities
- Visiting address:
- Engelska parken
752 38 Uppsala
- Postal address:
- Box 625
751 26 UPPSALA
I am a Research Engineer (50%) at the Centre for Digital Humanities, Dept. of ALM, Uppsala University, and also a Computer Scientist AI/HTR (50%) at Folkrörelsearkivet för Uppsala Län, working on the Labour's Memory project.
My research interests broadly span computer vision, image processing, machine learning and handwritten text recognition, with applications in Digital Humanities and Social Sciences.
Keywords: image analysis digital humanities data science machine learning human action recognition handwritten text recognition computer vision fuzzy set theory
I am a computer vision researcher and a data scientist. I received my PhD in Computer Vision from University of Malaya in 2015. My doctoral work focused on solving the problem of early human action detection, with potential application in fall detection. For my postdoctoral research, I worked at the Center for Image Analysis, Uppsala University. My postdoc focussed on development of computational methods and tools for handwritten text recognition. I have also worked as an AI Scientist at Silo AI.
I am currently a Research Engineer (50%) at CDHU, Dept. of ALM, Uppsala University, and also a Computer Scientist AI/HTR (50%) at Folkrörelsearkivet för Uppsala Län, working on the Labour's Memory project.
Ph.D. Computer Vision (Computer Science), University of Malaya, Kuala Lumpur, Malaysia, 2016.
M.Sc. Computer Science, VIT University, Vellore, India, 2012.
B.Sc. (Honors) Computer Science, Hansraj College, University of Delhi, 2010.
My research interests broadly span computer vision, image processing, machine learning and fuzzy set theory. Some of the research problems I worked on during my PhD include image and video data analysis, motion tracking, action classification, early human action detection, and scene image understanding. The bulk of my doctoral work involved solving the problem of human action recognition and detecting ongoing human action as early as possible i.e. after an action starts, but before it finishes. This can potentially be useful in situations like monitoring elderly patients, babies, etc.
I find exploring new research challenges very satisfying as it accelerates learning at a personal level, and often enables novel out-of-the-box solutions. Therefore, during my postdoctoral work, I explored historical handwritten text recognition, which is a cross-domain research involving analysis of handwritten text manuscripts using computational methods from image analysis and linguistics. In general, I worked towards developing algorithms to improve historical document readability and render them searchable, where I explored document image binarization, modelling document quality metrics using surrogates, designing feature descriptor tailor-made for text images, and handwritten word spotting using training-free approaches. My recent work includes large-scale image analysis and machine learning for digital palaeography, where I explored computerized methods to automatically analyze Swedish medieval charters and Icelandic manuscripts.
Please contact the directory administrator for the organization (department or similar) to correct possible errors in the information.