Image segmentation for enahncing symbol recognition in prosthetic vision

Lachlan Horne; Nick Barnes; Christopher McCarthy; Xuming He

doi:10.1109/EMBC.2012.6346544

Image segmentation for enahncing symbol recognition in prosthetic vision

Lachlan Horne, Nick Barnes, Christopher McCarthy, Xuming He

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

Abstract

Current and near-term implantable prosthetic vision systems offer the potential to restore some visual function, but suffer from poor resolution and dynamic range of induced phosphenes. This can make it difficult for users of prosthetic vision systems to identify symbolic information (such as signs) except in controlled conditions. Using image segmentation techniques from computer vision, we show it is possible to improve the clarity of such symbolic information for users of prosthetic vision implants in uncontrolled conditions. We use image segmentation to automatically divide a natural image into regions, and using a fixation point controlled by the user, select a region to phosphenize. This technique improves the apparent contrast and clarity of symbolic information over traditional phosphenization approaches.

Original language	English
Title of host publication	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Editors	Michael C. K. Khoo; Gert Cauwenberghs; James Weiland
Place of Publication	Piscataway, New Jersey
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2792-2795pp
Edition	Peer Reviewed
ISBN (Print)	9781457717871
DOIs	https://doi.org/10.1109/EMBC.2012.6346544
Publication status	Published - 2012
Event	IEEE International Conference of the Engineering in Medicine and Biology Society (EMBS 2012) - San Diego, USA, United States Duration: 1 Jan 2012 → … http://dx.doi.org/10.1109/EMBC.2012.6347194

Conference

Conference	IEEE International Conference of the Engineering in Medicine and Biology Society (EMBS 2012)
Country/Territory	United States
Period	1/01/12 → …
Other	August 28-September 1 2012
Internet address	http://dx.doi.org/10.1109/EMBC.2012.6347194

Access to Document

10.1109/EMBC.2012.6346544

Cite this

Horne, L., Barnes, N., McCarthy, C., & He, X. (2012). Image segmentation for enahncing symbol recognition in prosthetic vision. In M. C. K. K. G. C. J. W. (Ed.), Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (Peer Reviewed ed., pp. 2792-2795pp). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2012.6346544

Horne, Lachlan ; Barnes, Nick ; McCarthy, Christopher et al. / Image segmentation for enahncing symbol recognition in prosthetic vision. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. editor / Michael C. K. Khoo; Gert Cauwenberghs; James Weiland. Peer Reviewed. ed. Piscataway, New Jersey : Institute of Electrical and Electronics Engineers Inc., 2012. pp. 2792-2795pp

@inproceedings{58487937e5264beab69e60a63295141f,

title = "Image segmentation for enahncing symbol recognition in prosthetic vision",

abstract = "Current and near-term implantable prosthetic vision systems offer the potential to restore some visual function, but suffer from poor resolution and dynamic range of induced phosphenes. This can make it difficult for users of prosthetic vision systems to identify symbolic information (such as signs) except in controlled conditions. Using image segmentation techniques from computer vision, we show it is possible to improve the clarity of such symbolic information for users of prosthetic vision implants in uncontrolled conditions. We use image segmentation to automatically divide a natural image into regions, and using a fixation point controlled by the user, select a region to phosphenize. This technique improves the apparent contrast and clarity of symbolic information over traditional phosphenization approaches.",

author = "Lachlan Horne and Nick Barnes and Christopher McCarthy and Xuming He",

year = "2012",

doi = "10.1109/EMBC.2012.6346544",

language = "English",

isbn = "9781457717871",

pages = "2792--2795pp",

editor = "{Michael C. K. Khoo; Gert Cauwenberghs; James Weiland}",

booktitle = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

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

address = "United States",

edition = "Peer Reviewed",

note = "IEEE International Conference of the Engineering in Medicine and Biology Society (EMBS 2012) ; Conference date: 01-01-2012",

url = "http://dx.doi.org/10.1109/EMBC.2012.6347194",

}

Horne, L, Barnes, N, McCarthy, C & He, X 2012, Image segmentation for enahncing symbol recognition in prosthetic vision. in MCKKGCJW (ed.), Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Peer Reviewed edn, Institute of Electrical and Electronics Engineers Inc., Piscataway, New Jersey, pp. 2792-2795pp, IEEE International Conference of the Engineering in Medicine and Biology Society (EMBS 2012), United States, 1/01/12. https://doi.org/10.1109/EMBC.2012.6346544

Image segmentation for enahncing symbol recognition in prosthetic vision. / Horne, Lachlan; Barnes, Nick; McCarthy, Christopher et al.
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. ed. / Michael C. K. Khoo; Gert Cauwenberghs; James Weiland. Peer Reviewed. ed. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers Inc., 2012. p. 2792-2795pp.

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

TY - GEN

T1 - Image segmentation for enahncing symbol recognition in prosthetic vision

AU - Horne, Lachlan

AU - Barnes, Nick

AU - McCarthy, Christopher

AU - He, Xuming

PY - 2012

Y1 - 2012

N2 - Current and near-term implantable prosthetic vision systems offer the potential to restore some visual function, but suffer from poor resolution and dynamic range of induced phosphenes. This can make it difficult for users of prosthetic vision systems to identify symbolic information (such as signs) except in controlled conditions. Using image segmentation techniques from computer vision, we show it is possible to improve the clarity of such symbolic information for users of prosthetic vision implants in uncontrolled conditions. We use image segmentation to automatically divide a natural image into regions, and using a fixation point controlled by the user, select a region to phosphenize. This technique improves the apparent contrast and clarity of symbolic information over traditional phosphenization approaches.

AB - Current and near-term implantable prosthetic vision systems offer the potential to restore some visual function, but suffer from poor resolution and dynamic range of induced phosphenes. This can make it difficult for users of prosthetic vision systems to identify symbolic information (such as signs) except in controlled conditions. Using image segmentation techniques from computer vision, we show it is possible to improve the clarity of such symbolic information for users of prosthetic vision implants in uncontrolled conditions. We use image segmentation to automatically divide a natural image into regions, and using a fixation point controlled by the user, select a region to phosphenize. This technique improves the apparent contrast and clarity of symbolic information over traditional phosphenization approaches.

U2 - 10.1109/EMBC.2012.6346544

DO - 10.1109/EMBC.2012.6346544

M3 - Conference contribution

SN - 9781457717871

SP - 2792

EP - 2795

BT - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

A2 - null, Michael C. K. Khoo; Gert Cauwenberghs; James Weiland

PB - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway, New Jersey

T2 - IEEE International Conference of the Engineering in Medicine and Biology Society (EMBS 2012)

Y2 - 1 January 2012

ER -

Horne L, Barnes N, McCarthy C, He X. Image segmentation for enahncing symbol recognition in prosthetic vision. In MCKKGCJW, editor, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS. Peer Reviewed ed. Piscataway, New Jersey: Institute of Electrical and Electronics Engineers Inc. 2012. p. 2792-2795pp doi: 10.1109/EMBC.2012.6346544

Image segmentation for enahncing symbol recognition in prosthetic vision

Abstract

Conference

Access to Document

Fingerprint

Cite this