scispace - formally typeset
Search or ask a question
Institution

Ricoh

CompanyTokyo, Japan
About: Ricoh is a company organization based out in Tokyo, Japan. It is known for research contribution in the topics: Image processing & Information processing. The organization has 17693 authors who have published 29565 publications receiving 342960 citations. The organization is also known as: Ricoh Company Ltd. & Kabushiki-gaisha Rikō.


Papers
More filters
Proceedings Article
30 Nov 1992
TL;DR: Of OBS, Optimal Brain Damage, and magnitude-based methods, only OBS deletes the correct weights from a trained XOR network in every case, and thus yields better generalization on test data.
Abstract: We investigate the use of information from all second order derivatives of the error function to perform network pruning (i.e., removing unimportant weights from a trained network) in order to improve generalization, simplify networks, reduce hardware or storage requirements, increase the speed of further training, and in some cases enable rule extraction. Our method, Optimal Brain Surgeon (OBS), is Significantly better than magnitude-based methods and Optimal Brain Damage [Le Cun, Denker and Solla, 1990], which often remove the wrong weights. OBS permits the pruning of more weights than other methods (for the same error on the training set), and thus yields better generalization on test data. Crucial to OBS is a recursion relation for calculating the inverse Hessian matrix H-1 from training data and structural information of the net. OBS permits a 90%, a 76%, and a 62% reduction in weights over backpropagation with weight decay on three benchmark MONK's problems [Thrun et al., 1991]. Of OBS, Optimal Brain Damage, and magnitude-based methods, only OBS deletes the correct weights from a trained XOR network in every case. Finally, whereas Sejnowski and Rosenberg [1987] used 18,000 weights in their NETtalk network, we used OBS to prune a network to just 1560 weights, yielding better generalization.

1,785 citations

Patent
Gregory J. Wolff1, David G. Stork1
01 Nov 1995
TL;DR: A pen-like instrument with a writing point for making written entries upon a physical document and sensing the three-dimensional forces exerted on the writing tip as well as the motion associated with the act of writing is described in this article.
Abstract: A manual entry interactive paper and electronic document handling and process system uses a pen-like instrument (PI) with a writing point for making written entries upon a physical document and sensing the three-dimensional forces exerted on the writing tip as well as the motion associated with the act of writing. The PI is also equipped with a CCD array for reading pre-printed bar codes used for identifying document pages and other application defined areas on the page, as well as for providing optical character recognition data. A communication link between the PI and an associated base unit transfers the transducer data from the PI. The base unit includes a programmable processor, a display, and a communication link receiver. The processor includes programs for written character and word recognition, memory for storage of an electronic version of the physical document and any hand-written additions to the document. The display unit displays the corresponding electronic version of the physical document on a CRT or LCD as a means of feedback to the user and for use by authorized electronic agents.

1,024 citations

Journal ArticleDOI
01 Jul 1992
TL;DR: Both template matching and structure analysis approaches to R&D are considered and it is noted that the two approaches are coming closer and tending to merge.
Abstract: Research and development of OCR systems are considered from a historical point of view. The historical development of commercial systems is included. Both template matching and structure analysis approaches to R&D are considered. It is noted that the two approaches are coming closer and tending to merge. Commercial products are divided into three generations, for each of which some representative OCR systems are chosen and described in some detail. Some comments are made on recent techniques applied to OCR, such as expert systems and neural networks, and some open problems are indicated. The authors' views and hopes regarding future trends are presented. >

892 citations

Patent
Hiroshi Morohoshi1
27 Sep 2002
TL;DR: In this article, a coordinate input device detects coordinates of a position by indicating a screen of a display device with fingers of one hand, and transfers information of the detected coordinates to a computer through a controller.
Abstract: A coordinate input device detects coordinates of a position by indicating a screen of a display device with fingers of one hand, and transfers information of the detected coordinates to a computer through a controller The computer receives an operation that complies with the detected coordinates, and executes the corresponding processing For example, when it is detected that two points on the screen have been simultaneously indicated, an icon registered in advance is displayed close to the indicated position

876 citations

Journal ArticleDOI
Dar-Shyang Lee1
TL;DR: An effective scheme to improve the convergence rate without compromising model stability is proposed by replacing the global, static retention factor with an adaptive learning rate calculated for each Gaussian at every frame.
Abstract: Adaptive Gaussian mixtures have been used for modeling nonstationary temporal distributions of pixels in video surveillance applications. However, a common problem for this approach is balancing between model convergence speed and stability. This paper proposes an effective scheme to improve the convergence rate without compromising model stability. This is achieved by replacing the global, static retention factor with an adaptive learning rate calculated for each Gaussian at every frame. Significant improvements are shown on both synthetic and real video data. Incorporating this algorithm into a statistical framework for background subtraction leads to an improved segmentation performance compared to a standard method.

867 citations


Authors

Showing all 17697 results

NameH-indexPapersCitations
Chihaya Adachi11290861403
Hiroshi Maeda10389363370
Silvio Savarese8938635975
Yasuyuki Yamashita7372720229
Jonathan J. Hull7233516583
Toshihiko Baba5852913500
Jamey Graham561597723
Motoichi Ohtsu5565212280
Peter E. Hart4911394120
David G. Stork4730840597
Makoto Kobayashi471549777
Yasuo Kitaoka464207363
Berna Erol461485931
Ajay Divakaran452426913
Hiroyuki Kato451906652
Network Information
Related Institutions (5)
Panasonic
71.1K papers, 942.7K citations

86% related

Hitachi
101.4K papers, 1.4M citations

85% related

Toshiba
83.6K papers, 1M citations

85% related

Tokyo Institute of Technology
101.6K papers, 2.3M citations

84% related

Hewlett-Packard
59.8K papers, 1.4M citations

84% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20232
20224
2021173
2020500
2019713
2018723