Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021002556 - METHOD AND DEVICE FOR DETECTING, IN REAL TIME, PUPIL POSITION FOR LOW SPECIFICATION ENVIRONMENT SYSTEM

Publication Number WO/2021/002556
Publication Date 07.01.2021
International Application No. PCT/KR2020/001827
International Filing Date 10.02.2020
IPC
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/46 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
G06K 9/48 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
48by coding the contour of the pattern
Applicants
  • 계명대학교 산학협력단 INDUSTRY ACADEMIC COOPERATION FOUNDATION KEIMYUNG UNIVERSITY [KR]/[KR]
Inventors
  • 고병철 KO, Byoung Chul
  • 정미라 JUNG, Mi Ra
Agents
  • 김건우 KIM, Keon Woo
Priority Data
10-2019-007870101.07.2019KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) METHOD AND DEVICE FOR DETECTING, IN REAL TIME, PUPIL POSITION FOR LOW SPECIFICATION ENVIRONMENT SYSTEM
(FR) PROCÉDÉ ET DISPOSITIF DE DÉTECTION, EN TEMPS RÉEL, DE POSITION DE PUPILLE POUR UN SYSTÈME D'ENVIRONNEMENT À FAIBLES SPÉCIFICATIONS
(KO) 저사양 환경 시스템을 위한 실시간 동공 위치 검출 방법 및 장치
Abstract
(EN)
According to a method and a device for detecting, in real time, a pupil position for a low specification environment system, presented in the present invention, pupil candidate areas for left and right eyes are estimated by applying fast radial symmetry transform (FRST) in an input eye image for fast pupil detection, the pupil candidate areas include an incorrect area due to noise such as reflected light or eyelashes in an image so that spatiotemporal similarity between left and right pupils is extracted in order to effectively exclude the incorrect area and estimate an optimal pupil position, and optimal left and right eye pupil positions are determined using the similarity, thereby excluding algorithms such as deep learning in order to achieve high speed processing, and using an optimized image processing algorithm so as to accurately detect positions of pupils for various pupil positions, changes in lighting brightness, partial blocking and a subject wearing glasses.
(FR)
Selon un procédé et un dispositif de détection, en temps réel, d'une position de pupille pour un système d'environnement à faibles spécifications, présentés dans la présente invention, des zones candidates de pupille pour les yeux gauche et droit sont estimées par application d'une transformée de symétrie radiale rapide (FRST) dans une image d'oeil entrée pour une détection de pupille rapide; les zones candidates de pupille comprennent une zone incorrecte en raison du bruit tel que la lumière réfléchie ou les cils dans une image de façon à extraire la similarité spatio-temporelle entre les pupilles gauche et droite afin d'exclure efficacement la zone incorrecte et d'estimer une position de pupille optimale, et des positions optimales de pupille de l'oeil gauche et de l'oeil droit sont déterminées à l'aide de la similarité, ce qui exclut des algorithmes tels que l'apprentissage profond afin de réaliser un traitement à haute vitesse, et à l'aide d'un algorithme de traitement d'image optimisé de façon à détecter avec précision des positions de pupilles concernant diverses positions de pupille, des changements de luminosité d'éclairage, un blocage partiel et un sujet portant des lunettes.
(KO)
본 발명에서 제안하고 있는 저사양 환경 시스템을 위한 실시간 동공 위치 검출 방법 및 장치에 따르면, 빠른 동공 검출을 위해 입력된 눈 영상에서 고속 반경 대칭 변환(FRST, Fast radial symmetry transform)을 적용하여 좌우 눈에 대한 동공 후보 영역을 추정하고, 동공 후보 영역 중에는 영상에서의 반사광이나 속눈썹 등의 노이즈에 의해 잘못된 영역을 포함하므로 이러한 영역을 효과적으로 배제시키고 최적의 동공 위치를 추정하기 위해서, 좌우 동공에 대한 시공간적 유사도를 추출하고, 이를 이용하여 최적의 양안 동공 위치를 결정함으로써, 고속처리를 위해 딥러닝 등의 알고리즘을 배제하고 최적화된 영상처리 알고리즘만을 이용하여 다양한 동공의 위치, 조명 밝기 변화, 부분적인 가려짐 및 안경을 착용한 대상에 대해서도 정확하게 동공의 위치를 검출할 수 있다.
Latest bibliographic data on file with the International Bureau