Image reconstruction using high-level constraints

N. Tsuruta; Rin-Ichiro Taniguchi; M. Amamiya

doi:10.1109/ICPR.1996.547597

Image reconstruction using high-level constraints

N. Tsuruta, Rin-Ichiro Taniguchi, M. Amamiya

Real world robotics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a strategy to improve the performance of image reconstruction using a selective attention mechanism in a multi-layered neural network. The selective attention mechanism enables us to use top-down information as high-level and global constraints. The traditional algorithms using regularization techniques are quite sensitive to values of parameters, and it is quite difficult to select their appropriate values, because the algorithms use low-level and local constraints. Our strategy uses high-level and global constraints, and modifies the values of parameters locally and automatically.

Original language	English
Title of host publication	Track D: Parallel and Connectionist Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	401-405
Number of pages	5
Volume	4
ISBN (Print)	081867282X, 9780818672828
DOIs	https://doi.org/10.1109/ICPR.1996.547597
Publication status	Published - 1996
Event	13th International Conference on Pattern Recognition, ICPR 1996 - Vienna, Austria Duration: Aug 25 1996 → Aug 29 1996

Other

Other	13th International Conference on Pattern Recognition, ICPR 1996
Country/Territory	Austria
City	Vienna
Period	8/25/96 → 8/29/96

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition

Access to Document

10.1109/ICPR.1996.547597

Cite this

@inproceedings{d77ee49c4d8f439c910f487dd12142df,

title = "Image reconstruction using high-level constraints",

abstract = "In this paper, we propose a strategy to improve the performance of image reconstruction using a selective attention mechanism in a multi-layered neural network. The selective attention mechanism enables us to use top-down information as high-level and global constraints. The traditional algorithms using regularization techniques are quite sensitive to values of parameters, and it is quite difficult to select their appropriate values, because the algorithms use low-level and local constraints. Our strategy uses high-level and global constraints, and modifies the values of parameters locally and automatically.",

author = "N. Tsuruta and Rin-Ichiro Taniguchi and M. Amamiya",

year = "1996",

doi = "10.1109/ICPR.1996.547597",

language = "English",

isbn = "081867282X",

volume = "4",

pages = "401--405",

booktitle = "Track D: Parallel and Connectionist Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "13th International Conference on Pattern Recognition, ICPR 1996 ; Conference date: 25-08-1996 Through 29-08-1996",

}

TY - GEN

T1 - Image reconstruction using high-level constraints

AU - Tsuruta, N.

AU - Taniguchi, Rin-Ichiro

AU - Amamiya, M.

PY - 1996

Y1 - 1996

N2 - In this paper, we propose a strategy to improve the performance of image reconstruction using a selective attention mechanism in a multi-layered neural network. The selective attention mechanism enables us to use top-down information as high-level and global constraints. The traditional algorithms using regularization techniques are quite sensitive to values of parameters, and it is quite difficult to select their appropriate values, because the algorithms use low-level and local constraints. Our strategy uses high-level and global constraints, and modifies the values of parameters locally and automatically.

AB - In this paper, we propose a strategy to improve the performance of image reconstruction using a selective attention mechanism in a multi-layered neural network. The selective attention mechanism enables us to use top-down information as high-level and global constraints. The traditional algorithms using regularization techniques are quite sensitive to values of parameters, and it is quite difficult to select their appropriate values, because the algorithms use low-level and local constraints. Our strategy uses high-level and global constraints, and modifies the values of parameters locally and automatically.

UR - http://www.scopus.com/inward/record.url?scp=84898806706&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898806706&partnerID=8YFLogxK

U2 - 10.1109/ICPR.1996.547597

DO - 10.1109/ICPR.1996.547597

M3 - Conference contribution

AN - SCOPUS:84898806706

SN - 081867282X

SN - 9780818672828

VL - 4

SP - 401

EP - 405

BT - Track D: Parallel and Connectionist Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th International Conference on Pattern Recognition, ICPR 1996

Y2 - 25 August 1996 through 29 August 1996

ER -

Image reconstruction using high-level constraints

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this