11 Citations (Scopus)

Abstract

Current image indexing methods are based on measures of visual content. However, this approach provides only a partial solution to the image retrieval problem. For example, an artist might want to retrieve an image (for use in an advertising campaign) that evokes a particular "feeling" in the viewer. One technique for measuring evoked feelings, which originated in Japan, indexes images based on the inner impression (i.e. the kansei) experienced by a person while viewing an image or object - impressions such as busy, elegant, romantic, or lavish. The aspects of the image that evoke this inner impression in the viewer are called kansei factors. The challenge in kansei research is to enumerate those factors, with the ultimate goal of indexing images with the "inner impression" that viewers experience. Thus, the focus is on the viewer, rather than on the image, and similarity measures derived from kansei indexing represent similarities in inner experience, rather than visual similarity. This paper presents the results of research that indexes images based on a set of kansei impressions, and then looks for correlations between that indexing and traditional content-based indexing. The goal is to allow the indexing of images based on the inner impressions they evoke, using visual content.

Original languageEnglish (US)
Pages (from-to)363-375
Number of pages13
JournalUnknown Journal
Volume5292
DOIs
StatePublished - 2004

Fingerprint

retrieval
Emotions
Image retrieval
Research
Marketing
Japan
sensory feedback

Keywords

  • Affective basis functions
  • Affective content
  • Content based image retrieval
  • High-level content
  • Image content
  • Kansei
  • Lexical basis functions
  • NaturePix
  • Semantic content
  • Visual content

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Indexing natural images for retrieval based on kansei factors. / Black, John A.; Kahol, Kanav; Tripathi, Priyamvada; Kuchi, Prem; Panchanathan, Sethuraman.

In: Unknown Journal, Vol. 5292, 2004, p. 363-375.

Research output: Contribution to journalArticle

Black, John A. ; Kahol, Kanav ; Tripathi, Priyamvada ; Kuchi, Prem ; Panchanathan, Sethuraman. / Indexing natural images for retrieval based on kansei factors. In: Unknown Journal. 2004 ; Vol. 5292. pp. 363-375.
@article{89f239d35c5c442da95be64986ea1b0a,
title = "Indexing natural images for retrieval based on kansei factors",
abstract = "Current image indexing methods are based on measures of visual content. However, this approach provides only a partial solution to the image retrieval problem. For example, an artist might want to retrieve an image (for use in an advertising campaign) that evokes a particular {"}feeling{"} in the viewer. One technique for measuring evoked feelings, which originated in Japan, indexes images based on the inner impression (i.e. the kansei) experienced by a person while viewing an image or object - impressions such as busy, elegant, romantic, or lavish. The aspects of the image that evoke this inner impression in the viewer are called kansei factors. The challenge in kansei research is to enumerate those factors, with the ultimate goal of indexing images with the {"}inner impression{"} that viewers experience. Thus, the focus is on the viewer, rather than on the image, and similarity measures derived from kansei indexing represent similarities in inner experience, rather than visual similarity. This paper presents the results of research that indexes images based on a set of kansei impressions, and then looks for correlations between that indexing and traditional content-based indexing. The goal is to allow the indexing of images based on the inner impressions they evoke, using visual content.",
keywords = "Affective basis functions, Affective content, Content based image retrieval, High-level content, Image content, Kansei, Lexical basis functions, NaturePix, Semantic content, Visual content",
author = "Black, {John A.} and Kanav Kahol and Priyamvada Tripathi and Prem Kuchi and Sethuraman Panchanathan",
year = "2004",
doi = "10.1117/12.527309",
language = "English (US)",
volume = "5292",
pages = "363--375",
journal = "Scanning Electron Microscopy",
issn = "0586-5581",
publisher = "Scanning Microscopy International",

}

TY - JOUR

T1 - Indexing natural images for retrieval based on kansei factors

AU - Black, John A.

AU - Kahol, Kanav

AU - Tripathi, Priyamvada

AU - Kuchi, Prem

AU - Panchanathan, Sethuraman

PY - 2004

Y1 - 2004

N2 - Current image indexing methods are based on measures of visual content. However, this approach provides only a partial solution to the image retrieval problem. For example, an artist might want to retrieve an image (for use in an advertising campaign) that evokes a particular "feeling" in the viewer. One technique for measuring evoked feelings, which originated in Japan, indexes images based on the inner impression (i.e. the kansei) experienced by a person while viewing an image or object - impressions such as busy, elegant, romantic, or lavish. The aspects of the image that evoke this inner impression in the viewer are called kansei factors. The challenge in kansei research is to enumerate those factors, with the ultimate goal of indexing images with the "inner impression" that viewers experience. Thus, the focus is on the viewer, rather than on the image, and similarity measures derived from kansei indexing represent similarities in inner experience, rather than visual similarity. This paper presents the results of research that indexes images based on a set of kansei impressions, and then looks for correlations between that indexing and traditional content-based indexing. The goal is to allow the indexing of images based on the inner impressions they evoke, using visual content.

AB - Current image indexing methods are based on measures of visual content. However, this approach provides only a partial solution to the image retrieval problem. For example, an artist might want to retrieve an image (for use in an advertising campaign) that evokes a particular "feeling" in the viewer. One technique for measuring evoked feelings, which originated in Japan, indexes images based on the inner impression (i.e. the kansei) experienced by a person while viewing an image or object - impressions such as busy, elegant, romantic, or lavish. The aspects of the image that evoke this inner impression in the viewer are called kansei factors. The challenge in kansei research is to enumerate those factors, with the ultimate goal of indexing images with the "inner impression" that viewers experience. Thus, the focus is on the viewer, rather than on the image, and similarity measures derived from kansei indexing represent similarities in inner experience, rather than visual similarity. This paper presents the results of research that indexes images based on a set of kansei impressions, and then looks for correlations between that indexing and traditional content-based indexing. The goal is to allow the indexing of images based on the inner impressions they evoke, using visual content.

KW - Affective basis functions

KW - Affective content

KW - Content based image retrieval

KW - High-level content

KW - Image content

KW - Kansei

KW - Lexical basis functions

KW - NaturePix

KW - Semantic content

KW - Visual content

UR - http://www.scopus.com/inward/record.url?scp=8844244640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8844244640&partnerID=8YFLogxK

U2 - 10.1117/12.527309

DO - 10.1117/12.527309

M3 - Article

AN - SCOPUS:8844244640

VL - 5292

SP - 363

EP - 375

JO - Scanning Electron Microscopy

JF - Scanning Electron Microscopy

SN - 0586-5581

ER -