An image retrieval system by impression words and specific object names-IRIS

Kazuhiro Kuroda, Masafumi Hagiwara

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

In this paper, we describe a new image retrieval system for scenery images named IRIS (Image Retrieval by Impression words and Specific object names) which uses specific object names in addition to impression words which can reflect ambiguous human kansei (impression and sensitivity) as the retrieval keywords. IRIS has not only the function which retrieves images but also that can estimate keywords to images automatically. In IRIS, first an image is divided into some regions. Next each region is roughly classified into the sky, earth and water categories by the image recognition method using a neural network. Then the image characteristics are extracted from each category, and the impression words are given to the image automatically. After the regions are classified into sky/earth/water categories, they are classified into much more detailed objects such as mountain or cloudy weather sky. By the hierarchical recognition, the specific object names are given to an image automatically. Using concrete object names with vague impression words as keywords, flexible retrieval is possible. We carried out extensive experiments to test the performance of the developed IRIS. The retrieval experiments has shown the efficiency of retrieval when the impression words and the specific object names are used together. Also, they have shown the high retrieval performances of IRIS.

Original languageEnglish
Pages (from-to)259-276
Number of pages18
JournalNeurocomputing
Volume43
DOIs
Publication statusPublished - 2002

Fingerprint

Image retrieval
Names
Earth (planet)
Image recognition
Water
Experiments
Concretes
Neural networks
Weather

Keywords

  • Fuzzy
  • Image retrieval
  • Impression
  • Neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

An image retrieval system by impression words and specific object names-IRIS. / Kuroda, Kazuhiro; Hagiwara, Masafumi.

In: Neurocomputing, Vol. 43, 2002, p. 259-276.

Research output: Contribution to journalArticle

@article{ad0299cabb0645f2882986a29853abfd,
title = "An image retrieval system by impression words and specific object names-IRIS",
abstract = "In this paper, we describe a new image retrieval system for scenery images named IRIS (Image Retrieval by Impression words and Specific object names) which uses specific object names in addition to impression words which can reflect ambiguous human kansei (impression and sensitivity) as the retrieval keywords. IRIS has not only the function which retrieves images but also that can estimate keywords to images automatically. In IRIS, first an image is divided into some regions. Next each region is roughly classified into the sky, earth and water categories by the image recognition method using a neural network. Then the image characteristics are extracted from each category, and the impression words are given to the image automatically. After the regions are classified into sky/earth/water categories, they are classified into much more detailed objects such as mountain or cloudy weather sky. By the hierarchical recognition, the specific object names are given to an image automatically. Using concrete object names with vague impression words as keywords, flexible retrieval is possible. We carried out extensive experiments to test the performance of the developed IRIS. The retrieval experiments has shown the efficiency of retrieval when the impression words and the specific object names are used together. Also, they have shown the high retrieval performances of IRIS.",
keywords = "Fuzzy, Image retrieval, Impression, Neural networks",
author = "Kazuhiro Kuroda and Masafumi Hagiwara",
year = "2002",
doi = "10.1016/S0925-2312(01)00344-7",
language = "English",
volume = "43",
pages = "259--276",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - An image retrieval system by impression words and specific object names-IRIS

AU - Kuroda, Kazuhiro

AU - Hagiwara, Masafumi

PY - 2002

Y1 - 2002

N2 - In this paper, we describe a new image retrieval system for scenery images named IRIS (Image Retrieval by Impression words and Specific object names) which uses specific object names in addition to impression words which can reflect ambiguous human kansei (impression and sensitivity) as the retrieval keywords. IRIS has not only the function which retrieves images but also that can estimate keywords to images automatically. In IRIS, first an image is divided into some regions. Next each region is roughly classified into the sky, earth and water categories by the image recognition method using a neural network. Then the image characteristics are extracted from each category, and the impression words are given to the image automatically. After the regions are classified into sky/earth/water categories, they are classified into much more detailed objects such as mountain or cloudy weather sky. By the hierarchical recognition, the specific object names are given to an image automatically. Using concrete object names with vague impression words as keywords, flexible retrieval is possible. We carried out extensive experiments to test the performance of the developed IRIS. The retrieval experiments has shown the efficiency of retrieval when the impression words and the specific object names are used together. Also, they have shown the high retrieval performances of IRIS.

AB - In this paper, we describe a new image retrieval system for scenery images named IRIS (Image Retrieval by Impression words and Specific object names) which uses specific object names in addition to impression words which can reflect ambiguous human kansei (impression and sensitivity) as the retrieval keywords. IRIS has not only the function which retrieves images but also that can estimate keywords to images automatically. In IRIS, first an image is divided into some regions. Next each region is roughly classified into the sky, earth and water categories by the image recognition method using a neural network. Then the image characteristics are extracted from each category, and the impression words are given to the image automatically. After the regions are classified into sky/earth/water categories, they are classified into much more detailed objects such as mountain or cloudy weather sky. By the hierarchical recognition, the specific object names are given to an image automatically. Using concrete object names with vague impression words as keywords, flexible retrieval is possible. We carried out extensive experiments to test the performance of the developed IRIS. The retrieval experiments has shown the efficiency of retrieval when the impression words and the specific object names are used together. Also, they have shown the high retrieval performances of IRIS.

KW - Fuzzy

KW - Image retrieval

KW - Impression

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=0036138382&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036138382&partnerID=8YFLogxK

U2 - 10.1016/S0925-2312(01)00344-7

DO - 10.1016/S0925-2312(01)00344-7

M3 - Article

VL - 43

SP - 259

EP - 276

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -