The 2nd IEEE International Workshop on Arabic and derived Script Analysis and Recognition (ASAR 2018) will be hosted by The Alan Turing Institute, London, in collaboration with the LORIA laboratory (University Lorraine, France) and REGIM-Lab. (University of Sfax, Tunisia), and will be held in London (United Kingdom) on March 12-14, 2018.
ASAR 2018 is technically co-sponsored by IEEE Region 8, IEEE UK and Ireland section, IEEE Tunisia section, and IAPR.
The 2nd ASAR 2018 workshop provides an excellent opportunity for researchers and practitioners at all levels of experience to meet colleagues and to share new ideas and knowledge about Arabic and derived script document analysis and recognition methods. The workshop enjoys strong participation from researchers in both industry and academia.
Proceedings published in IEEE Xplore: <link>
Photos:
Program
Monday 12 March 2018
10:00am Registration & Breakfast
10:30am Opening Session
11:00am Keynote 1: “Identifying and dating scribes’ hands in pre-modern Arabic manuscripts: guess-work, intuition or intersubjectively comprehensible argumentation?” by Tilman Seidensticker, Friedrich-Schiller-Universität Jena, Germany
12:00pm Oral session on Printed/Handwritten Text Recognition
- “Case Study Fine Writing Style Classification Using Siamese Neural Network” Alaa Abdalhaleem, Berat Kurar and Jihad El-Sana
- “Space Anomalies in OCRs for Arabic Like Scripts” Riaz Ahmad (TU-Kaiserslautern & DFKI, Germany), Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki and Andreas Dengel
- “Arabic Bank Cheque Words Recognition Using Gabor Features” Qais Al-Nuzaili, Somaya Al-Maadeed (Qatar university, Qatar), Hanadi Hassen and Ali Hamdi
- “How to Efficiently Increase Resolution in Neural OCR Models” Stephen Rawls (University of Southern California, United States), Huaigu Cao, Joe Mathai and Premkumar Natarajan
1:00pm Lunch
2:00pm Keynote 2: “Two decades of Arabic manuscript processing: IFN/ENIT Competitions and historical manuscript analysis” by Volker Märgner, Technische Universität Braunschweig, Germany
3:00pm Oral session on Arabic Document Databases and Digital Libraries
- 5 “Generic method for grid line detection and removal in scanned documents” Romain Karpinski (University of Lorraine, France) and Abdel Belaid
- “Towards the Machine Reading of Arabic Calligraphy: A Letters Dataset and Corresponding Corpus of Text” Seetah Alsalamah (Univesity of Manchester, United Kingdom) and Ross King
- “Developing bilingual Arabic-English Ontologies of Al-Quran” Mohammad Alqahtani (University of Leeds, United Kingdom) and Eric Atwell
- “Multiple Model Kalman Filter Approach for Show-through Cancellation” Sabita Langkam and Alok Kanti Deb (Indian Institute of Technology Kharagpur, India)
4:00pm Coffee Break
4:05pm British Library Activities
- “Show and Tell” of important items from the British Library collections
- Tour of Qatar digitisation facility
5:00pm Welcome Reception at The Alan Turing Institute
Tuesday 13 March 2018
10:00am Registration & Breakfast
10:30am Oral session on Historical Arabic Document Analysis
- “Discovering Qur’anic Knowledge through AQD: Arabic Qur’anic Database, a Multiple Resources Annotation-level Search” Sameer Alrehaili (University of Leeds, United Kingdom) and Eric Atwell
- “A Hybrid Methods of Aligning Arabic Qur’anic Semantic Resources” Sameer Alrehaili, Mohammad Alqahtani and Eric Atwell (University of Leeds, United Kingdom)
- “Synthesizing versus Augmentation for Arabic Word Recognition with Convolutional Neural Networks” Reem Alaasam, Berat Kurar and Jihad El-Sana
- “Data Collection and Image Processing System for Ancient Arabic Manuscripts” Somaya Al-Maadeed (Qatar university, Qatar), Syed Peer and Nandhini Subramanian
11:30am Keynote 3: “Arabic collections in the British Library” by Daniel Lowe, The British Library, United Kingdom
12:30pm Discussion groups
1:00pm Lunch
2:00pm Oral session on Arabic Document Understanding
- “Deep Convolutional Neural Network for Recognition of Unified Multi-Language Handwritten Numerals” Ghazanfar Latif (Prince Mohammad University, Saudi Arabia), Jaafar Alghazo, Loay Alzubaidi, M. Muzzamal Naseer and Yazan Alghazo
- “A Path Signature Approach to Online Arabic Handwriting Recognition” Daniel Wilson-Nunn (The Alan Turing Institute, United Kingdom), Terry Lyons, Anastasia Papavasiliou and Hao Ni
- “Diacritization of a Highly Cited Text: A Classical Arabic Book as a Case” Abdulrahman Alosaimy (University of Leeds, United Kingdom) and Eric Atwell
- “An Arabic Word Similiarty Measure for Semantic Conversational Agents” Zaid Noori (Ministry of Foreign Affairs/ Iraq, United Kingdom), Keeley Crockett, Zuhair Bandar and Mohammed Al-Mousa
3:00pm Industrial presentation 1: “The A2IA Arabic Text Reader system: Progress and Challenges” Med Faouzi Benzeghiba, A2IA, France
3:30pm Coffee Break
4:00pm Oral session on Machine and Deep Learning for Script Recognition
- “Improving Sentiment Analysis in Arabic Using Word Representation” Abdulaziz M. Alayba (Coventry University, United Kingdom), Vasile Palade, Matthew England and Rahat Iqbal
- “Arabic words Recognition using CNN and TNN on a Smartphone” Alaa Alsaeedi (University of Jeddah, Saudi Arabia), Hanan Al Mutawa, Sumaya Ahmed, Wisam Al Subhi, Samia Snoussi and Kaouther Omri
- “Binarization Free Layout Analysis for Arabic Historical Documents Using Fully Convolutional Networks” Berat Barakat and Jihad El-Sana
- “MHDID: A Multi-distortion Historical Document Image Database” Atena Shahkolaei (École de technologie supérieure, Canada), Azeddine Beghdadi, Somaya Al-Maadeed and Mohamed Cheriet
- “Deep FCN for Arabic Scene Text Detection” Ines Beltaief and Mohamed Ben Halima (University of Sfax, Tunisia)
- “A hybrid approach for standardized Dictionary-based knowledge extraction for Arabic morpho-semantic retrieval” Nadia Soudani (ENSI, University of Manouba, Tunisia), Ibrahim Bounhas and Yahya Slimani
- “A Novel Term Weighting Scheme and an approach for Classification of Agricultural Arabic Text Complaints” Devanur Guru, Mostafa Ali (University of Mysore, India) and Mahamad Suhil
- “Urdu Natural Scene Character Recognition using Convolutional Neural Networks” Asghar Ali (UNSW, Australia), Mark Pickering and Kamran Shafi
- “Baseline-based zoning design for the NSHPZ-HMM 2-D model applied to Arabic script” Hanene Boukerma (Ecole Normale Supérieure d’Enseignement Technologique (ENSET), Algeria), Christophe Choisy, Nadir Farah and Mohamed Cheriet
6:00pm Dinner at Drake & Morgan in King’s Cross
Wednesday 14 March 2018
10:00am Registration & Breakfast
10:30am Oral session on Arabic Document Analysis
- “A Reliable Method to Predict Parkinson’s Disease Stage and Progression based on Handwriting and Re-sampling Approaches” Catherine Taleb (University of Balamand, Lebanon), Laurence Likforman (University of Balamand, Lebanon), Chafic Mokbel and Maha Khachab
- “LABA: Logical Layout Analysis of Book Page Images in Arabic Using Multiple Support Vector Machines” Wenda Qin, Randa Elanwar (Boston University, United States) and Margrit Betke
- “Smartphone Arabic Signboard Images Reading” Samia Snoussi (FCIT. University of JEDDA, Saudi Arabia)
- “Information Extraction from Arabic and Latin scanned invoices” Najoua Rahal, Maroua Tounsi, Mohamed Benjlaiel and Adel M. Alimi (University of Sfax, Tunisia)
11:30am Industrial presentation 1: “A Web-based OCR Service” by Ashok Popat, Google Inc., USA
12:00pm Layout Analysis Challenge
- “Page Layout Analysis Using Fully Convolutional Networks” Berat Kurar Barakat, Ahmad Droby and Jihad El-Sana
- “Analyzing scanned Arabic documents using Random Forests” Rana S.M. Saad, Randa Elanwar (Boston University, United States), N.S. Abdel Kader, Samia Mashali and Margrit Betke
- “Adoptive Thresholding and Geometric Features based Physical Layout Analysis of Scanned Arabic Books” Maitham A Al-Dobais, Ghazanfar Latif (Prince Mohammad University, Saudi Arabia), Fahad Abdulrahman G Alrasheed and Loay Alzubaidi
- “Physical Layout Analysis of Scanned Arabic Books” Randa Elanwar (Boston University, United States) and Margrit Betke
1:00pm Awards and Closing session
1:30pm Lunch
Keynote Speakers:
