I'm involved in the following international project as coordinator
Global currents
Indian Ocean World (IOW)
QNRF (Qatar national research fund
1. Global currents
Global currents projects is an international research project using visual language processing and feature modeling to study western and non-western manuscript and print textual heritages so far resistant to large-scale data (visual big data) analysis.
Computational methods to investigate:
Deep learning (CNN, Auto-encoders)
Data mining (association rules mining for visual feature co-occurence)
Pattern recognition and correlation learning (visual keyword detection, matching, recognition)
Image processing (manuscript image enhancement)
Document image analysis (layout analysis)
Machine learning (deep learning for manuscript classification)
Graph theory (structural similarity modeling)
1.1. Modeling of literary networks (link)
This project undertakes the cross-cultural study of literary networks in a global context, ranging from post-classical Islamic philosophy to the European Enlightenment. Integrating new image-processing techniques with social network analysis, we examine how different cultural epochs are characterized by unique networks of intellectual exchange. Research on ''world literature'' has become a central area of inquiry today within the humanities, and yet so far data-driven approaches have largely been absent from the field. Our combined approach of visual language processing (VLP) and network modeling allows us to study the non-western and pre-print textual heritages so far resistant to large-scale data analysis as well as develop a new model of global comparative literature that preserves a sense of the world’s cultural differences.
Collaborators
Canada: McGill university
Prof. Andrew Piper (Department of art history and communication studies)
Prof. Grace Fong (East Asian Studies department)
Prof. Robert Wisnovsk (Institut of islamic studies)
Prof. Derek Ruths (Computer science department)
Prof. Gwyn Campbel (Director of the Indian Ocean World Centre )
Ecole de technologie superieure de Monteral
Prof. Mohamed Cheriet (Departement genie de la production automaitisee)
USA: Stanford university
Prof. Elaine Treharne (Department of Englsih)
Prof. Mark Algee-Hewitt ( director of the Stanford Literary Lab)
The Netherlands: University of Groningen
Lambert Schomaker ( director of Artificial intelligence and cognitive engineering laboratory)
Students involved
Ehsan Arabnejad (PhD), Hossein Ziae Nafchi (PhD), Mohamed Mhiri (PhD), Sherif Abulwafa (PhD), Sara Zalehpour (MSc)
1.2. Twelfth century' British manuscript analysis (link)
This project is a part of the Global currents projects which is an international research project using visual language processing and feature modeling to study western and non-western manuscript and print textual heritages so far resistant to large-scale data (visual big data) analysis. Its aim is to use computational techniques to detect some specific visual features from Twelfth century' British manuscripts. Furthermore, the aim is also to find out the co-occurence of these feature within a large collection.
Litterae Notabiliores
Rubrics
Inter-textual Space
Enlarged Capitals
Students involved
Ehsan Arabnejad (PhD) and Hossein Ziae Nafchi (PhD)
2. Indian Ocean World (link)
Recently, significant human efforts have been focused on the preservation and restoration of visual cultural heritage using signal processing and imaging technologies. Advanced progresses in this area allow us to dig into the memory of our heritage by computational techniques to understand its evolution over the years. Historical geographic maps and manuscripts are among the very important visual elements of our cultural heritage that need to be digitized in the form of digital images and then analyzed using image processing tools in order to automatically explore, recognize and understand their contents. Our aim is to develop advanced techniques of image processing to help scholars in their investigation of historical maps and manuscripts images.
Funder
This project is being funded by the Social Sciences and Humanities Research Council of Canada (SSHRC) for a period of seven years and a budget of $2.5 million.
Collaborators
Thurty-six (36) world-class academic members (Canada, USA, Australia, Japan, France,Germany, South-Africa).
3. Qatar national research foundation project
The objective of this project is two folds:
Historical document enhancement
Non destructive imaging of the historical ink (Infrared, Ultraviolet, X-ray fluorescence)
Collaborators
Canada
Ecole de technologie superieure de Monteral
Qatar
University of Qatar
UKA
University of
Funder
Qatar foundation
Students involved
Atena Shahkolaei
Some sample of restoration results
before
after
before
after
Multispectral imaging (see the invisible) for historical document investigation
RGB
Ultraviolet