Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Yasuharu Shimeki"'
Autor:
Tetsuo Ishikawa, Yasuharu Shimeki, Atsushi Koike, Shuichi Matsumoto, Mutsumi Ohta, Atsushi Marugame, Yoshiaki Katoh, Kenya Uomori, Osamu Matsunaga, Kazuhiro Matsuzaki
Publikováno v:
The Journal of the Institute of Image Information and Television Engineers. 52:1573-1580
テレビ電話画像から超高精細画像, そしてデータを階層化・統合化して伝送する統合ディジタル放送 (ISDB, Integrated Servlces Digltal Broadcastlng) において必要となる, 動画像の階層化技術と階層
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60fc9c984b104e2d31c777e70c8db720
https://doi.org/10.3169/itej.52.1573
https://doi.org/10.3169/itej.52.1573
Autor:
Hiroshi Yamamoto, Hisao Niwa, Kazuhiro Kayashima, Yasuharu Shimeki, Yoshihiro Kojima, Susumu Maruno
Publikováno v:
Systems and Computers in Japan. 26:47-58
A newly developed character recognition method is proposed that can be applied to low quality printed documents. In this method, the cooperation of pattern processing with neural networks and symbolic processing with knowledge of language is adopted.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d307352f820e83bc66236bec405fccf5
https://doi.org/10.1002/scj.4690261005
https://doi.org/10.1002/scj.4690261005
Publikováno v:
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
Whereas a character segmentation is an essential pre-process for performing a character recognition, this has been an extremely complicated task for Japanese document recognition. The difficulties of it are due to the irregularities of sizes and disp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4251dd52d8d7009d59a057663e1fe16f
https://doi.org/10.1109/ijcnn.1993.714131
https://doi.org/10.1109/ijcnn.1993.714131
Autor:
Y. Kojima, K. Kawakami, M. Mizutani, Hiroshi Yamamoto, Yasuharu Shimeki, Shigeo Sakaue, Susumu Maruno, Toshiyuki Kohda
Publikováno v:
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
We have newly developed a handwritten numeric character recognition system with neural networks based on an approximate reasoning architecture (NARA). Handwritten character recognition is one of the most difficult tasks in an area of pattern recognit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03a390efb61788346a905105998efedb
https://doi.org/10.1109/ijcnn.1993.714153
https://doi.org/10.1109/ijcnn.1993.714153
Publikováno v:
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
One of the biggest issues of an object recognition is the recognition with rotation invariance under a fluctuating noisy environment. We developed an object recognition system using temporal pattern recognition network with quantizer neuron chip (QNC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee0694150a332b74811f5c3d8d021709
https://doi.org/10.1109/ijcnn.1993.716780
https://doi.org/10.1109/ijcnn.1993.716780
Publikováno v:
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
The authors have previously proposed a multi functional layered network (MFLN) employing a quantizer neuron model and proved that a learning speed of MFLN is the fastest among RCE networks, LVQ3 and multi-layered neural network with backpropagation.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20f0586bbbf684cbf66b746e4202bae2
https://doi.org/10.1109/ijcnn.1993.713933
https://doi.org/10.1109/ijcnn.1993.713933
Autor:
Akira Motohara, Toshinori Hosokawa, Hidetsugu Maekawa, Michiaki Muraoka, Seichi Shin, Yasuharu Shimeki, Kazuhiro Kayashima
Publikováno v:
DAC
A state traversal algorithm based on control theory and its application to sequential ATPG is presented. In the algorithm, next states are evaluated by an objective function representing "unlikeliness" to reach each of the previously traversed states
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b9498d7d492a615dc8d68ec180e621a
https://doi.org/10.1145/157485.164590
https://doi.org/10.1145/157485.164590
Publikováno v:
IEEE transactions on neural networks. 4(2)
The number of precision bits for operations and data are limited in the hardware implementations of backpropagation (BP). Reduction of rounding error due to this limited precision is crucial in the implementation. The new learning algorithm is based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67704ee6689381729cb72766effa30c0
https://pubmed.ncbi.nlm.nih.gov/18267726
https://pubmed.ncbi.nlm.nih.gov/18267726
Publikováno v:
[Proceedings] 1991 IEEE International Joint Conference on Neural Networks.
The authors propose a novel learning algorithm with weighted error function (WEF). They have reduced the necessary precision for the learning of multi-font alpha-numeric recognition to 10-bit fixed point precision using the WEF. The WEF raises the re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::34910aa4a26af2862b99f29a7f13b423
https://doi.org/10.1109/ijcnn.1991.170355
https://doi.org/10.1109/ijcnn.1991.170355
Publikováno v:
[Proceedings] 1991 IEEE International Joint Conference on Neural Networks.
The authors propose a multifunctional layered network (MFLN) with a quantizer neuron model and describe the principles of the quantizer neuron and the structure of the network for a character recognition system. Each layer of the MFLN has a specific
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7d9fa0b05a46ed560ca3ad4bfc0d07b
https://doi.org/10.1109/ijcnn.1991.170456
https://doi.org/10.1109/ijcnn.1991.170456