[image 03438] 【開催案内】 3/11 15:30 ＠ NII Document Analysis and Character Recognition, 10th CODH Seminar

[KITAMOTO Asanobu]

皆様

文書解析と文字認識に関するセミナーを開催いたします。

中国科学院のCheng-Lin Liu教授をお招きし、中国のNational Laboratory of Pattern 
Recognitionにおける文書解析と認識に関する最新の研究成果をご紹介いただきます。

その他、人文学オープンデータ共同利用センター（CODH)で進めるくずし字の認識や近代書籍の認識に関しても、あわせてご紹介します。

参加無料です。詳しくは以下のウェブサイトをご確認ください。
積極的なご参加をお待ちしております。

=======================================================================
10th CODH Seminar
Document Analysis and Character Recognition
http://codh.rois.ac.jp/seminar/document-analysis-20190311/

Date	15:30-17:30, March 11 (Mon), 2019
Venue	1208 Meeting Room (12F), National Institute of Informatics

Invited talk 16:00-17:00

Advances in Document Analysis and Recognition Research at NLPR
Professor 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.
=======================================================================

北本 朝展
人文学オープンデータ共同利用センター
国立情報学研究所
http://researchmap.jp/kitamoto/