JOURNAL ARTICLE

Robust Pupil Detection using Rank Order Filter and Cross-Correlation

Kyung-Shik JangSung-Dae Park

Year: 2013 Journal:   The Journal of the Korean Institute of Information and Communication Engineering Vol: 17 (7)Pages: 1564-1570

Abstract

이 논문에서는 rank order 필터와 상호상관을 이용하여 강인하게 눈동자를 찾는 방법을 제안한다. rank order 필터를 사용하여 얼굴 영상에서 눈동자 후보점을 찾는다. 임계치를 변화하며 눈 영역을 이진화하여 눈썹 위치를 구한 후 눈썹 영역의 눈동자 후보점을 제거한다. 눈동자 위치를 보정한 후 두 눈동자 후보점을 기하학적인 제약조건을 기반으로 쌍으로 묶는다. 각 쌍의 두 눈에 대한 유사도를 상호상관을 이용하여 측정하여 가장 큰 값을 갖는 쌍을 최종 눈동자로 결정한다. BioID 얼굴 데이터베이스의 얼굴 영상 500개에 대한 실험 결과 96.8%의 높은 눈동자 검출율을 보였으며 기존 방법보다 약 11.6% 개선된 결과를 얻었다. In this paper, we propose a robust pupil detection method using rank order filter and cross-correlation. Potential pupil candidates are detected using rank order filter. Eye region is binarized using variable threshold to find eyebrow, and pupil candidates at the eyebrow are removed. The positions of pupil candidates are corrected, the pupil candidates are grouped into pairs based on geometric constraints. A similarity measure is obtained for two eye of each pair using cross-correlation, we select a pair with the largest similarity measure as a final pupil. The experiments have been performed for 500 images of the BioID face database. The results show that it achieves the high detection rate of 96.8% and improves about 11.6% than existing method.

Keywords:
Pupil Correlation Rank (graph theory) Cross-correlation Order (exchange) Filter (signal processing) Computer science Mathematics Statistics Artificial intelligence Pattern recognition (psychology) Computer vision Optics Physics Combinatorics Economics Geometry

Metrics

0
Cited By
0.00
FWCI (Field Weighted Citation Impact)
11
Refs
0.08
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Topics

Gaze Tracking and Assistive Technology
Physical Sciences →  Computer Science →  Human-Computer Interaction
Glaucoma and retinal disorders
Health Sciences →  Medicine →  Ophthalmology
Ocular Surface and Contact Lens
Health Sciences →  Medicine →  Public Health, Environmental and Occupational Health

Related Documents

JOURNAL ARTICLE

Robust Pupil Detection using Rank Order Filter and Pixel Difference

Kyung-Shik Jang

Journal:   The Journal of the Korean Institute of Information and Communication Engineering Year: 2012 Vol: 16 (7)Pages: 1383-1390
JOURNAL ARTICLE

Pupil Detection using Hybrid Projection Function and Rank Order Filter

Kyung-Shik Jang

Journal:   Journal of the Korea Society of Computer and Information Year: 2014 Vol: 19 (8)Pages: 27-34
JOURNAL ARTICLE

Interest point detection using rank order LoG filter

Zhenwei MiaoXudong Jiang

Journal:   Pattern Recognition Year: 2013 Vol: 46 (11)Pages: 2890-2901
JOURNAL ARTICLE

Eye detection based on rank order filter

Jianfeng RenXudong Jiang

Year: 2009 Vol: 4 Pages: 1-4
JOURNAL ARTICLE

Efficient Edge Detection in Noisy Images using Robust Rank-Order Test

Dong-Hoon Lim

Journal:   Korean Journal of Applied Statistics Year: 2007 Vol: 20 (1)Pages: 147-157
© 2026 ScienceGate Book Chapters — All rights reserved.