2024-03-29T05:30:29Z
https://niigata-u.repo.nii.ac.jp/oai
oai:niigata-u.repo.nii.ac.jp:00002215
2022-12-15T03:35:05Z
423:424:425
453:454
Optical character recognition using a memory matrix generated from singular value decomposition
Optical character recognition using a memory matrix generated from singular value decomposition
Sasaki, Osami
Sakata, Kenichi
Shibahara, Akihito
Suzuki, Takamasa
Copyright 1998 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
associative memory
pattern recognition
singular value decomposition
optical signal processing
A memory matrix provides output vectors that are specified by the corresponding input vectors. If the input vectors represent input characters, the memory matrix performs character recognition. When the input characters contain noise, it is difficult to recognize the characters. To overcome this difficulty, we generate a new memory matrix by using singular value decomposition and manipulating the singular values. The effectiveness of the memory matrix is made clear by recognized 26 alphabets characters containing noise with an optical recognition system.
International Society for Optical Engineering, SPIE
1998-09
eng
journal article
http://hdl.handle.net/10191/27619
https://niigata-u.repo.nii.ac.jp/records/2215
info:doi/10.1117/1.601781
AA00333891
00913286
Optical Engineering
Optical Engineering
37
9
2592
2596
https://niigata-u.repo.nii.ac.jp/record/2215/files/37_9_2592-2596.pdf
application/pdf
449.9 kB
2019-07-29