10th CODH Seminar
Document Analysis and Character Recognition


We are pleased to announce that Prof. Cheng-Lin Liu from the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, China will give a talk about document analysis and recognition research. You are all invited. Registration in advance is required. #codh10

Basic Information

Date 15:30-17:30, March 11 (Mon), 2019
Venue 1208 Meeting Room (12F), National Institute of Informatics. Access to NII.
Language English


15:00 Open the venue
15:30-15:40 Kuzushiji Challenge: Public Datasets and Machine Learning for Old Japanese Characters Asanobu Kitamoto (CODH/NII)
15:40-16:00 N2I project: Recognizing Modern Japanese Magazines with Deep Learning Anh Le Duc (CODH/ISM)
16:00-17:00 Advances in Document Analysis and Recognition Research at NLPR Cheng-Lin Liu (National Laboratory of Pattern Recognition, Institute of Automation of Chinese Academy of Sciences, China)
17:00-17:30 Discussion All

Invited Talk

Title Advances in Document Analysis and Recognition Research at NLPR
Speaker Cheng-Lin Liu
Abstract In this talk, I will introduce some recent advances in Document Analysis and Recognition research at the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences. Oriented to the analysis and recognition of document images of complex layout or background interference, I will mainly introduces our techniques in layout analysis of handwritten documents, scene text detection, text line recognition, classifier learning and adaptation. Our layout analysis method is based on full convolutional network (FCN) and conditional random field (CRF). For scene text detection, we proposed a deep direct regression based method for multi-oriented texts and a local region based method for end-to-end detection and recognition of arbitrary shape texts. For text line recognition, we promoted the over-segmentation based method with deep learning models, and proposed a sliding character model based method which performs superiorly for both scene texts and handwriting of different scripts. For classifier learning for document recognition, we are developing algorithms for designing models for open world recognition, small sample learning and adaptation. Last, I will introduce a new database of historical handwritten Chinese characters. This database contains more than 2.2 million character samples of 9,630 categories, segmented from ancient books and Buddist scriptures. The database have large variation of writing style and sample number per class, and can facilitate research for classifier learning and adaptation, aimed to solve the challenges of huge category set, large variation and small sample size.
Bio Cheng-Lin Liu is a Professor at the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China, and is now the director of the laboratory. He received the B.S. degree in electronic engineering from Wuhan University, Wuhan, China, the M.E. degree in electronic engineering from Beijing Polytechnic University, Beijing, China, the Ph.D. degree in pattern recognition and intelligent control from the Chinese Academy of Sciences, Beijing, China, in 1989, 1992 and 1995, respectively. He was a postdoctoral fellow at Korea Advanced Institute of Science and Technology (KAIST) and later at Tokyo University of Agriculture and Technology from March 1996 to March 1999. From 1999 to 2004, he was a research staff member and later a senior researcher at the Central Research Laboratory, Hitachi, Ltd., Tokyo, Japan. His research interests include pattern recognition, image processing, neural networks, machine learning, and especially the applications to character recognition and document analysis. He has published over 200 technical papers at prestigious international journals and conferences. He won the IAPR/ICDAR Young Investigator Award of 2005. He is an associate editor-in-chief of Pattern Recognition Journal, an associate editor of Image and Vision and Computing, International Journal on Document Analysis and Recognition, and Cognitive Computation. He is a Fellow of the IAPR and the IEEE.


You are all invited, free of charge. Registration in advance is required using the following form.

The seminar has fininshed. Thank you for your participation.


This seminar is supported by ROIS-DS-JOINT 027RP2018. About ROIS-DS-JOINT, see Collaboration.

Past CODH Seminars


22th CODH Seminar - Hentaigana in the Digital Age: The Inheritance and New Developments of the Japanese Written Character Culture


21th CODH Seminar - Digital History: Concepts and Practices


20th CODH Seminar - The end of lexicography, welcome to the machine: On how ChatGPT can already take over all of the dictionary maker's tasks


19th CODH Seminar - Collective Intelligence and Creative AI: A framework for augmenting creative human expression


18th CODH Seminar - Micro Typology and Digital Archive: Case Studies on Bantu languages and Japanese-Ryukyuan languages


DH 2022 Tokyo Commemorative Lecture Series / 17th CODH Seminar - Historical Big Data - THE DARK MATTER OF HISTORY


16th CODH Seminar - Digital Archives for Cities and Towns - Historical Big Data and Usage in the Real World


15th CODH Seminar - Art History Research to be Transformed by IIIF and AI - Interpreting Japanese Painting Scrolls in Middle Ages by Style Comparative Study on Large-Scale Facial Expression Data


14th CODH Seminar - 100 Recipes for IIIF Curation Platform


13th CODH Seminar - Present and Future of Historical Big Data Research


12th CODH Seminar (Online) - AI for Culture: From Japanese Art to Anime


12th CODH Seminar - AI for Culture: From Japanese Art to Anime


11th CODH Seminar - Text Mining for Analyzing Research Communities: Sociological Topics and Socio-Technical Imaginaries


10th CODH Seminar - Document Analysis and Character Recognition


9th CODH Seminar - Computer Vision with Limited Labeled Data


8th CODH Seminar - Exploring Deep Learning for Classical Japanese Literature, Machine Creativity, and Recurrent World Models!


7th CODH Seminar - Manifold Mixup: Encouraging Meaningful On-Manifold Interpolation as a Regularizer


6th CODH Seminar - Historical Big Data - Challenges in Transforming Historical Documents to Structured Data for the Integrated Analysis of Records in the Past -


5th CODH Seminar - Trustworthy Data Repositories - Forum for Sharing Practical Information about CoreTrustSeal Certification -


4th CODH Seminar - A New Trend on Image Delivery in Digital Archives - IIIF's Potential for Standardization and Sophistication of Image Access -


3rd CODH Seminar - Usage of DOI for Humanities - Assignment of DOI for Scholarly Resources such as Research Data and Museum Collections -


2nd CODH Seminar - Old Japanese Character Challenge - Future of Machine Recognition and Human Transcription -


1st CODH Seminar - Big Data and Digital Humanities