Lahore University of Management Sciences

Symposium on Document Image Analysis at LUMS

March 20, 2012

Share this page on Facebook Share this page on Twitter LUMS Official Vimeo Channel LUMS Official YouTube Channel

Symposium on Document Image Analysis

Date: March 20, 2012
Venue: Lahore University of Management Sciences, Pakistan
Organising Committee:

Shahab Baqai
Department of Computer Science, LUMS School of Science and Engineering (SBASSE), Lahore

Sohaib Khan
Department of Computer Science, LUMS-SBASSE, Lahore

Imtnan Qazi
Pakistan Space and Upper Atmosphere Research Commission, SUPARCO, Islamabad.

The event has been organised by:

Computer Vision Lab, LUMS-SBASSE, Lahore

Image Understanding and Pattern Recognition (IUPR) research group, TU Kaiserslautern, Germany

German Research Centre for Artificial Intelligence (DFKI), Kaiserslautern, Germany

With support from: DAAD German Academic Exchange Service

Speakers:

Syed Saqib Bukhari
Image Understanding and Pattern Recognition (IUPR) Research Group, Technical University Kaiserslautern, Germany
Topic: A Generic Text-Line Extraction Method for A Collection of Diverse Document Images

Sarmad Hussain
Center for Language Engineering, Khawarizmi Institute of Computer Science, UET, Lahore
Topic: Challenges in Developing Urdu Nastaleeq Optical Character Recognition (OCR) Systems

Khurram Khurshid
Institute of Space Technology, Islamabad
Topic: Word Spotting for Digital Urdu Libraries

Faisal Shafiat
German Research Centre for Artificial Intelligence (DFKI) Kaiserslautern, Germany
Topic: Document Image Analysis - Historical Overview, Current Challenges, and Future Directions

Arif Zaman
Department of Computer Science, LUMS-SSE
Topic: Practical and Adaptive Optical Mark Recognition (OMR)

Hands-On OCR Lab Session

Post-lunch session will be conducted in a lab in which participants will be guided to write their own OCR programme. Programming environment will be Python. This session is optional - only those participants who are familiar with programming need to attend.

Programme is available here

About the Symposium

Document Image Analysis is concerned with the automatic interpretation of images of printed and handwritten documents, including text, engineering drawings, maps, and music score sheets. Research in this field descends in an unbroken tradition from the earliest experiments in computer vision, and remains distinguished by close and productive ties between the academic and industrial communities. This symposium on document image analysis will provide the participants an overview of this research field, its historical development, recent progress and open issues; highlight research efforts done in the last years on processing Urdu documents; and would give a hands-on tutorial to build an OCR system involving an algorithmic description of the core processing steps in OCR systems.  

Intended Audience

* Students and faculty members in computer science, electrical engineering and allied disciplines with an interest in image processing, machine learning and language processing.

* Professionals interesting in automating data entry from large number of documents, such as those conducting field surveys or receiving many forms that need to be entered in a computer system.

* Professionals with an interest in exploring management of archival documents, such as librarians, and museum curators.