Hardware implementation of fast pupil segmentation using region properties

Taiq M. Khan; Yinan Kong; Muhammad A.U. Khan

doi:10.1117/12.2182881

Hardware implementation of fast pupil segmentation using region properties

Taiq M. Khan, Yinan Kong, Muhammad A.U. Khan

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

3 Citations (Scopus)

Abstract

This paper presents a novel approach for automatic pupil segmentation. The proposed algorithm uses local histogram-based threshold, area and eccentricity that looks for the region that has the highest probability of having the pupil. Proposed algorithm is implemented on FPGA using a non-iterative scheme along with hardware optimized median filter and connected component logic algorithm. The proposed algorithm is tested on two public databases namely: CASIA v1.0 and MMU v1.0. Experimental results show that the proposed method has satisfying performance and good robustness against the reflection in the pupil.

Original language	English
Title of host publication	Twelfth International Conference on Quality Control by Artificial Vision
Subtitle of host publication	Proceedings of SPIE
Editors	Fabrice Meriaudeau, Olivier Aubreton
Place of Publication	Bellingham, WA
Publisher	SPIE
Pages	1-10
Number of pages	10
Volume	9534
ISBN (Electronic)	9781628416992
DOIs	https://doi.org/10.1117/12.2182881
Publication status	Published - 2015
Event	12th International Conference on Quality Control by Artificial Vision - Le Creusot, France Duration: 3 Jun 2015 → 5 Jun 2015

Other

Other	12th International Conference on Quality Control by Artificial Vision
Country/Territory	France
City	Le Creusot
Period	3/06/15 → 5/06/15

Access to Document

10.1117/12.2182881

Cite this

@inproceedings{9fe96a97db5448f9a3c622901f577bb7,

title = "Hardware implementation of fast pupil segmentation using region properties",

abstract = "This paper presents a novel approach for automatic pupil segmentation. The proposed algorithm uses local histogram-based threshold, area and eccentricity that looks for the region that has the highest probability of having the pupil. Proposed algorithm is implemented on FPGA using a non-iterative scheme along with hardware optimized median filter and connected component logic algorithm. The proposed algorithm is tested on two public databases namely: CASIA v1.0 and MMU v1.0. Experimental results show that the proposed method has satisfying performance and good robustness against the reflection in the pupil.",

author = "Khan, {Taiq M.} and Yinan Kong and Khan, {Muhammad A.U.}",

year = "2015",

doi = "10.1117/12.2182881",

language = "English",

volume = "9534",

pages = "1--10",

editor = "Fabrice Meriaudeau and Olivier Aubreton",

booktitle = "Twelfth International Conference on Quality Control by Artificial Vision",

publisher = "SPIE",

address = "United States",

note = "12th International Conference on Quality Control by Artificial Vision ; Conference date: 03-06-2015 Through 05-06-2015",

}

Khan, TM, Kong, Y & Khan, MAU 2015, Hardware implementation of fast pupil segmentation using region properties. in F Meriaudeau & O Aubreton (eds), Twelfth International Conference on Quality Control by Artificial Vision: Proceedings of SPIE. vol. 9534, 95340F, SPIE, Bellingham, WA, pp. 1-10, 12th International Conference on Quality Control by Artificial Vision, Le Creusot, France, 3/06/15. https://doi.org/10.1117/12.2182881

Hardware implementation of fast pupil segmentation using region properties. / Khan, Taiq M.; Kong, Yinan; Khan, Muhammad A.U.
Twelfth International Conference on Quality Control by Artificial Vision: Proceedings of SPIE. ed. / Fabrice Meriaudeau; Olivier Aubreton. Vol. 9534 Bellingham, WA: SPIE, 2015. p. 1-10 95340F.

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

TY - GEN

T1 - Hardware implementation of fast pupil segmentation using region properties

AU - Khan, Taiq M.

AU - Kong, Yinan

AU - Khan, Muhammad A.U.

PY - 2015

Y1 - 2015

N2 - This paper presents a novel approach for automatic pupil segmentation. The proposed algorithm uses local histogram-based threshold, area and eccentricity that looks for the region that has the highest probability of having the pupil. Proposed algorithm is implemented on FPGA using a non-iterative scheme along with hardware optimized median filter and connected component logic algorithm. The proposed algorithm is tested on two public databases namely: CASIA v1.0 and MMU v1.0. Experimental results show that the proposed method has satisfying performance and good robustness against the reflection in the pupil.

AB - This paper presents a novel approach for automatic pupil segmentation. The proposed algorithm uses local histogram-based threshold, area and eccentricity that looks for the region that has the highest probability of having the pupil. Proposed algorithm is implemented on FPGA using a non-iterative scheme along with hardware optimized median filter and connected component logic algorithm. The proposed algorithm is tested on two public databases namely: CASIA v1.0 and MMU v1.0. Experimental results show that the proposed method has satisfying performance and good robustness against the reflection in the pupil.

UR - http://www.scopus.com/inward/record.url?scp=84931326216&partnerID=8YFLogxK

U2 - 10.1117/12.2182881

DO - 10.1117/12.2182881

M3 - Conference proceeding contribution

AN - SCOPUS:84931326216

VL - 9534

SP - 1

EP - 10

BT - Twelfth International Conference on Quality Control by Artificial Vision

A2 - Meriaudeau, Fabrice

A2 - Aubreton, Olivier

PB - SPIE

CY - Bellingham, WA

T2 - 12th International Conference on Quality Control by Artificial Vision

Y2 - 3 June 2015 through 5 June 2015

ER -

Hardware implementation of fast pupil segmentation using region properties

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this