J-MOCR-AND - September 17, 2011
 
8:50 am
 Welcome
9:00 am
 Invited talk by Ashok Popat
10:00 am
 MOCR Session I: 3 talks @ 15 minutes
10:00 am
 Recognition of Tibetan Wood Block Prints with Generalized Hidden Markov Model and Kernelized Modified Quadratic Distance Function
Fares Hedayati, Jike Chong and Kurt Keutzer

10:15 am
 Script based Text Identification: A Multi-level Architecture
Ehtesham Hassan, Ritu Garg, Santanu Chaudhury and Madan Gopal
10:30 am
 Sparsity-based super-resolution for offline handwriting recognition
Shiv Vitaladevuni, Huaigu Cao, David Belanger, Krishna Subramanian, Rohit Prasad and Prem Natarajan
10:45 am
 Coffee break
11:15 am
 AND Session I: 4 talks @ 15 minutes
11:15 am
 Acquiring Competitive Intelligence from Social Media
Lipika Dey, Sk Mirajul Haque, Arpit Khurdiya and Gautam Shroff

11:30 am
 Segmenting eBay Item Descriptions into Coherent Sections
Smruthi Mukund, Nitin Indurkhya and Neel Sundaresan

11:45 am
 Adapting a WSJ trained Part-of-Speech tagger to Noisy Text: Preliminary Results
Phani Gadde, L. Venkata Subramaniam and Tanveer Faruquie
12:00 pm
 Tackling Content Spamming with a Term Weighting Scheme
Saptaditya Maiti, Deba Prasad Mandal and Pabitra Mitra

12:15 pm
 Lunch
1:15 pm
 MOCR Session II: 3 talks @ 15 minutes
1:15 pm
 Experiences of Integration and Performance Testing of Multilingual OCR for Printed Indian Scripts
Deepak Arya, Tushar Patnaik, Santanu Chaudhury, Jawahar Cv, Bidyut Baran Chaudhury, Ramakrishna Ag, Gs Lehal and Chakravorty Bhagvati

1:30 pm
 Topological Features for Recognizing Printed and Handwritten Bangla Characters
Soumen Bag, Gaurav Harit and Partha Bhowmick
1:45 pm
 Unconstrained Bangla online handwriting recognition based on MLP and SVM
Sk. Mohiuddin, Ujjwal Bhattacharya and Swapan K. Parui
2:00 pm
 AND Session II: 4 talks @ 15 minutes
2:00 pm
 New Method for the Selection of Binarization Parameters based on Noise Features of Historical Documents
Ines Ben Messaoud, Haikal El Abed, Volker Märgner and Hamid Amiri

2:15 pm
 Recognizing Garbage in OCR Output on Historical Documents
Richard Wudtke, Christoph Ringlstetter and Klaus U. Schulz

2:30 pm
 A Real-World Noisy Unstructured Handwritten Notebook Corpus for Document Image Analysis Research
Jin Chen, Daniel Lopresti and Bart Lamiroy
2:45 pm
 Experiments with artificially generated noise for cleansing noisy text
Phani Gadde, Rahul Goutam, Rakshit Shah, Hemanth Bayyarapu and L. Venkata Subramaniam

3:00 pm
 Coffee break
3:30 pm
 MOCR Session III: 4 talks @ 15 minutes
3:30 pm
 Automatic Localization of Page Segmentation Errors
Dheeraj Mundhra, Anand Mishra and C. V. Jawahar

3:45 pm
 MAST: Multi-Script Annotation Toolkit for Scenic Text
Thotreingam Kasar, Deepak Kumar, M N Anil Prasad, D Girish and A G Ramakrishnan
4:00 pm
 Text Level Performance Evaluation of Indic OCR using Split & Merge
Sushil Manwar, Manish Kumar Gupta and Swapnil Belhe
4:15 pm
 Lampung - a new handwritten character benchmark: Database, Labeling and Recognition
Akmal Junaidi, Szilard Vajda and Gernot A. Fink
4:30 pm
 Closing, presentation of Best Student Paper Awards