Ekta Vats

Forskningsingenjör vid Institutionen för ABM, Centrumbildning i Digital Humaniora

E-post:
ekta.vats[AT-tecken]abm.uu.se
Besöksadress:
Engelska parken
Thunbergsvägen 3H
752 38 Uppsala
Postadress:
Box 625
751 26 UPPSALA

Kort presentation

Detta stycke finns inte på svenska, därför visas den engelska versionen.

I am a Research Engineer at the Centre for Digital Humanities Uppsala, Department of ALM, Uppsala University. My research interests broadly span computer vision, document image processing, machine learning and handwritten text recognition, with applications in Digital Humanities and Social Sciences. I have spent my last 5 years (++) working on developing methods and tools for Digital Humanities.

Nyckelord: image analysis digital humanities data science machine learning human action recognition handwritten text recognition ocr

Detta stycke finns inte på svenska, därför visas den engelska versionen.

I am a Research Engineer at the Centre for Digital Humanities where I work as an image analysis and data science expert. I am interested in investigating how research-oriented AI solutions can be adopted in real-world applications in the field of Humanities and Social Science. At CDHU, I would like to help scholars and researchers gain an understanding of AI and data-driven methods, teach relevant courses, share knowledge through creative workshops, and also support their infrastructure needs.

By training, I am a PhD in Computer Vision, and also work as an AI Scientist (part-time) at Silo AI Stockholm, and prior to that, as a researcher/postdoc at the Center for Image Analysis at Uppsala University. I have also worked as a Computer Scientist AI/HTR at Folkrörelsearkivet for Uppsala Län on the Labour’s Memory project, which aimed at making large scale material from The Swedish Trade Union Confederation-sphere (from the 1880s until today) available and accessible.

Detta stycke finns inte på svenska, därför visas den engelska versionen.

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.

Kontakta katalogansvarig vid den aktuella organisationen (institution eller motsv.) för att rätta ev. felaktigheter.

Ekta Vats
Senast uppdaterad: 2021-03-09