Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system

Naoyuki Tsuruta, Takuma Akagi, Rin-Ichiro Taniguchi, Makoto Amamiya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

One of the most important tasks in image understanding is to map visual information into symbolic concepts which describe an input scene. However, the mapping presents the following difficulties: 1. How to resolve the ambiguity in visual information. 2. How to reduce the redundancy of visual information. 3. How to describe scenes efficiently using symbolic concepts. In this paper, we propose the ICE System, which is a framework of computer vision addressing the above three problems. First we will see a multi-layered model based on the hypercolumn with selective attention mechanism can solve the first two problems. Then, we will describe how the ICE System is structurally constructed on the basis of the multi-layered model.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages177-180
Number of pages4
Volume1
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1993
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: Oct 25 1993Oct 29 1993

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period10/25/9310/29/93

Fingerprint

Image understanding
Computer vision
Redundancy

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Tsuruta, N., Akagi, T., Taniguchi, R-I., & Amamiya, M. (1993). Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system. In Proceedings of the International Joint Conference on Neural Networks (Vol. 1, pp. 177-180). Publ by IEEE.

Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system. / Tsuruta, Naoyuki; Akagi, Takuma; Taniguchi, Rin-Ichiro; Amamiya, Makoto.

Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. p. 177-180.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Tsuruta, N, Akagi, T, Taniguchi, R-I & Amamiya, M 1993, Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system. in Proceedings of the International Joint Conference on Neural Networks. vol. 1, Publ by IEEE, pp. 177-180, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 10/25/93.
Tsuruta N, Akagi T, Taniguchi R-I, Amamiya M. Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system. In Proceedings of the International Joint Conference on Neural Networks. Vol. 1. Publ by IEEE. 1993. p. 177-180
Tsuruta, Naoyuki ; Akagi, Takuma ; Taniguchi, Rin-Ichiro ; Amamiya, Makoto. / Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system. Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. pp. 177-180
@inproceedings{52033a5800d44e5a955f884eced145c7,
title = "Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system",
abstract = "One of the most important tasks in image understanding is to map visual information into symbolic concepts which describe an input scene. However, the mapping presents the following difficulties: 1. How to resolve the ambiguity in visual information. 2. How to reduce the redundancy of visual information. 3. How to describe scenes efficiently using symbolic concepts. In this paper, we propose the ICE System, which is a framework of computer vision addressing the above three problems. First we will see a multi-layered model based on the hypercolumn with selective attention mechanism can solve the first two problems. Then, we will describe how the ICE System is structurally constructed on the basis of the multi-layered model.",
author = "Naoyuki Tsuruta and Takuma Akagi and Rin-Ichiro Taniguchi and Makoto Amamiya",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "1",
pages = "177--180",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Framework of image understanding based on PDP model-proposition of ICE(image CEntered) system

AU - Tsuruta, Naoyuki

AU - Akagi, Takuma

AU - Taniguchi, Rin-Ichiro

AU - Amamiya, Makoto

PY - 1993

Y1 - 1993

N2 - One of the most important tasks in image understanding is to map visual information into symbolic concepts which describe an input scene. However, the mapping presents the following difficulties: 1. How to resolve the ambiguity in visual information. 2. How to reduce the redundancy of visual information. 3. How to describe scenes efficiently using symbolic concepts. In this paper, we propose the ICE System, which is a framework of computer vision addressing the above three problems. First we will see a multi-layered model based on the hypercolumn with selective attention mechanism can solve the first two problems. Then, we will describe how the ICE System is structurally constructed on the basis of the multi-layered model.

AB - One of the most important tasks in image understanding is to map visual information into symbolic concepts which describe an input scene. However, the mapping presents the following difficulties: 1. How to resolve the ambiguity in visual information. 2. How to reduce the redundancy of visual information. 3. How to describe scenes efficiently using symbolic concepts. In this paper, we propose the ICE System, which is a framework of computer vision addressing the above three problems. First we will see a multi-layered model based on the hypercolumn with selective attention mechanism can solve the first two problems. Then, we will describe how the ICE System is structurally constructed on the basis of the multi-layered model.

UR - http://www.scopus.com/inward/record.url?scp=0027879106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027879106&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027879106

SN - 0780314212

SN - 9780780314214

VL - 1

SP - 177

EP - 180

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

ER -