Trainable pattern classifier using a computer-generated hologram

Ken Yuh; Chau Jern Cheng

doi:10.1143/JJAP.33.1910

Trainable pattern classifier using a computer-generated hologram

Research output: Contribution to journal › Article › peer-review

Abstract

A novel technique for pattern classification is proposed and demonstrated. The perceptron learning algorithm is used for training, and the trained interconnection weight matrix is transferred into a computer-generated hologram. The hologram is used as a correlation filter in the optical system for pattern classification. Both computer simulation and optical experiment results are presented.

Original language	English
Pages (from-to)	1910-1913
Number of pages	4
Journal	Japanese Journal of Applied Physics
Volume	33
Issue number	4R
DOIs	https://doi.org/10.1143/JJAP.33.1910
Publication status	Published - 1994 Apr
Externally published	Yes

ASJC Scopus subject areas

General Engineering
General Physics and Astronomy

Access to Document

10.1143/JJAP.33.1910

Cite this

@article{dbbfef33d67040dba0ed19f0103c73e5,

title = "Trainable pattern classifier using a computer-generated hologram",

abstract = "A novel technique for pattern classification is proposed and demonstrated. The perceptron learning algorithm is used for training, and the trained interconnection weight matrix is transferred into a computer-generated hologram. The hologram is used as a correlation filter in the optical system for pattern classification. Both computer simulation and optical experiment results are presented.",

author = "Ken Yuh and Cheng, {Chau Jern}",

year = "1994",

month = apr,

doi = "10.1143/JJAP.33.1910",

language = "English",

volume = "33",

pages = "1910--1913",

journal = "Japanese Journal of Applied Physics",

issn = "0021-4922",

publisher = "Japan Society of Applied Physics",

number = "4R",

}

TY - JOUR

T1 - Trainable pattern classifier using a computer-generated hologram

AU - Yuh, Ken

AU - Cheng, Chau Jern

PY - 1994/4

Y1 - 1994/4

N2 - A novel technique for pattern classification is proposed and demonstrated. The perceptron learning algorithm is used for training, and the trained interconnection weight matrix is transferred into a computer-generated hologram. The hologram is used as a correlation filter in the optical system for pattern classification. Both computer simulation and optical experiment results are presented.

AB - A novel technique for pattern classification is proposed and demonstrated. The perceptron learning algorithm is used for training, and the trained interconnection weight matrix is transferred into a computer-generated hologram. The hologram is used as a correlation filter in the optical system for pattern classification. Both computer simulation and optical experiment results are presented.

UR - http://www.scopus.com/inward/record.url?scp=0028422293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028422293&partnerID=8YFLogxK

U2 - 10.1143/JJAP.33.1910

DO - 10.1143/JJAP.33.1910

M3 - Article

AN - SCOPUS:0028422293

SN - 0021-4922

VL - 33

SP - 1910

EP - 1913

JO - Japanese Journal of Applied Physics

JF - Japanese Journal of Applied Physics

IS - 4R

ER -

Trainable pattern classifier using a computer-generated hologram

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this