Proto-Object Based Saliency Model with Second-Order Texture Feature

Takeshi Uejima; Ernst Niebur; Ralph Etienne-Cummings

doi:10.1109/BIOCAS.2018.8584749

Proto-Object Based Saliency Model with Second-Order Texture Feature

Takeshi Uejima, Ernst Niebur, Ralph Etienne-Cummings

School of Medicine

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

1 Scopus citations

Abstract

The nervous system can rapidly select important information from a visual scene and pay attention to it. Bottom-up saliency models use low-level features such as intensity, color, and orientation to generate a saliency map that predicts human fixations. Such algorithms work well for many images, however they miss the influence of texture. In this paper, we add a second-order texture channel to a proto-object based saliency model. The extended model shows significantly improved performance in predicting human fixations.

Original language	English (US)
Title of host publication	2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538636039
DOIs	https://doi.org/10.1109/BIOCAS.2018.8584749
State	Published - Dec 20 2018
Event	2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Cleveland, United States Duration: Oct 17 2018 → Oct 19 2018

Other

Other	2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018
Country/Territory	United States
City	Cleveland
Period	10/17/18 → 10/19/18

Keywords

Gestalt
Proto-object
Saliency
Texture
Visual attention

ASJC Scopus subject areas

Electrical and Electronic Engineering
Health Informatics
Instrumentation
Signal Processing
Biomedical Engineering

Access to Document

10.1109/BIOCAS.2018.8584749

Cite this

Uejima, T, Niebur, E & Etienne-Cummings, R 2018, Proto-Object Based Saliency Model with Second-Order Texture Feature. in 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings., 8584749, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018, Cleveland, United States, 10/17/18. https://doi.org/10.1109/BIOCAS.2018.8584749

@inproceedings{acee39f04c7c40408c831400a4fd6384,

title = "Proto-Object Based Saliency Model with Second-Order Texture Feature",

abstract = "The nervous system can rapidly select important information from a visual scene and pay attention to it. Bottom-up saliency models use low-level features such as intensity, color, and orientation to generate a saliency map that predicts human fixations. Such algorithms work well for many images, however they miss the influence of texture. In this paper, we add a second-order texture channel to a proto-object based saliency model. The extended model shows significantly improved performance in predicting human fixations.",

keywords = "Gestalt, Proto-object, Saliency, Texture, Visual attention",

author = "Takeshi Uejima and Ernst Niebur and Ralph Etienne-Cummings",

year = "2018",

month = dec,

day = "20",

doi = "10.1109/BIOCAS.2018.8584749",

language = "English (US)",

booktitle = "2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings",

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

note = "2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 ; Conference date: 17-10-2018 Through 19-10-2018",

}

TY - GEN

T1 - Proto-Object Based Saliency Model with Second-Order Texture Feature

AU - Uejima, Takeshi

AU - Niebur, Ernst

AU - Etienne-Cummings, Ralph

PY - 2018/12/20

Y1 - 2018/12/20

N2 - The nervous system can rapidly select important information from a visual scene and pay attention to it. Bottom-up saliency models use low-level features such as intensity, color, and orientation to generate a saliency map that predicts human fixations. Such algorithms work well for many images, however they miss the influence of texture. In this paper, we add a second-order texture channel to a proto-object based saliency model. The extended model shows significantly improved performance in predicting human fixations.

AB - The nervous system can rapidly select important information from a visual scene and pay attention to it. Bottom-up saliency models use low-level features such as intensity, color, and orientation to generate a saliency map that predicts human fixations. Such algorithms work well for many images, however they miss the influence of texture. In this paper, we add a second-order texture channel to a proto-object based saliency model. The extended model shows significantly improved performance in predicting human fixations.

KW - Gestalt

KW - Proto-object

KW - Saliency

KW - Texture

KW - Visual attention

UR - http://www.scopus.com/inward/record.url?scp=85060895824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060895824&partnerID=8YFLogxK

U2 - 10.1109/BIOCAS.2018.8584749

DO - 10.1109/BIOCAS.2018.8584749

M3 - Conference contribution

AN - SCOPUS:85060895824

BT - 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018

Y2 - 17 October 2018 through 19 October 2018

ER -

Proto-Object Based Saliency Model with Second-Order Texture Feature

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this