Dimosthenis Karatzas

LinkedInLink

Bio: 

(last updated: Feb 2025)


A physicist by education, I received my PhD in Computer Science from the University of Liverpool, UK in 2003. I have held research contracts at the Univ. of Liverpool, UK and the Univ. of Southampton, UK, and a Marie Curie visiting researcher stay at ITESOFT, France. Since 2007 I work at the Universitat Autònoma de Barcelona, Spain, and I am attached at the Computer Vision Centre, where I lead the Vision, Language and Reading research group. I am an associate director of the Centre since 2014.

I am also a co-director of the ELLIS Unit Barcelona, and a visiting researcher at the IDAKS group at the Osaka Prefecture University, Japan.

My research focuses on computer vision and machine learning, and my particular interests include robust reading systems and the joint modelling of vision and language. Have a look at my Google Scholar profile for recent publications.

In 2013 I received the IAPR/ICDAR Young Investigator Award for “innovative research in human perception-based document analysis” as well as “outstanding service to the ICDAR community in a variety of roles”. This recognition is awarded by the International Association of Pattern Recognition, after an international nomination and evaluation process to one individual every two years.

In 2016, I received a Google Research Award, in the line of Machine Perception, for pursuing research in the line of modelling the interplay between visual and textual information in images. In 2019 I received an Amazon Web Services Machine Learning Research Award and in 2022 an Amazon Research Award for pursuing research in the line of Document Visual Question Answering.

Since 2019, I have ranked within the top 2% of top-cited scientists in the field of Artificial Intelligence based on Scopus data by Elsevier.

I have been the principal investigator of various research projects, funded through European and national competitive calls.

In 2007 I set up with fellow-researchers the spin-off company TruColour Ltd, UK, specializing in perception-based colour calibration solutions. In 2019 I co-founded with colleagues the spin-off company AllRead, Spain, backed by the Mobile World Capital, which automates logistics operations by integrating our reading models in industry workflows.

I am currently leading a technology transfer network in Catalonia (1M EUR) involving all 28 research groups on AI in Catalonia and lead the ELIAS node Barcelona.

I have secured numerous research and technology transfer contracts with industry. Technologies I have transferred are used daily in sectors such as banking (administrative documents classification for CaixaBank: thousands of images processed automatically per day) and utilities (automatic reading of consumption from gas meters for Naturgy: >10k images analysed per week, >2M images over the past two years).

On the antipode of commercial exploitation, a key driver in my professional activity is ensuring the social impact of my research. In this line, I conceived and led the creation of the “Library Living Lab” (L3), converting a public library in Sant Cugat del Vallés, Barcelona, into an open, participatory innovation space. The project, aligned with European and regional innovation policies, is a collaboration between the public administration, research institutions, industry partners and citizens’ associations. L3 is an authentic implementation of the quadruple helix innovation model and a framework for social innovation in a real-world context. Under my leadership L3 became a member of the European Network of Living Labs in 2015 and was nominated for the city awards of Sant Cugat del Vallés in 2016.

Between 2016 and 2021 I served as the chair of the Technical Committee 11 (Reading Systems) of the International Association of Pattern Recognition (IAPR). TC11 coordinates the activities of the >1,200 members strong international research community in this area.

I am a member of the IAPR Education Committee, a senior member of IEEE, an ELLIS fellow and member of the ELLIS multimodal learning program. In the past I have served in the IAPR Industry Liaison Committee, and I have been a founding member and a member of the executive committee of the UK Chapter of the SPIE.

In 2018 I was invited by the Secretary of Telecommunications, Cybersecurity and Digital Society of the Generalitat de Catalunya to participate on the work group that helped define the Catalan Strategy on Artificial Intelligence, under the name “Catalonia.AI”[4].

I have served the international research community in several roles. I have been involved in the organisation of the main international events in my research field in various capacities. I serve on the editorial board of Springer Int Journal of Computer Vision and Springer Int Journal on Document Analysis and Recognition. I act as an evaluator of research projects in national and EU calls.

I have launched and run since 2011 the Robust Reading Competition portal, that has been established as the de-facto international benchmark in my research domain, serving more than 55,000 registered researchers from 157 countries and having received and evaluated more than 100,000 submissions to date.

I have >25 years’ worth of teaching experience at different undergraduate and postgraduate levels. I represent the CVC at the Artificial Intelligence Doctoral Academy. I participated in the launch of the Doctoral Consortium of the Int. Conf. on Document Analysis and Recognition in and the IAPR TC10/11 Summer School series.