[go: up one dir, main page]

WO2025050265A1 - Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré - Google Patents

Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré Download PDF

Info

Publication number
WO2025050265A1
WO2025050265A1 PCT/CN2023/116842 CN2023116842W WO2025050265A1 WO 2025050265 A1 WO2025050265 A1 WO 2025050265A1 CN 2023116842 W CN2023116842 W CN 2023116842W WO 2025050265 A1 WO2025050265 A1 WO 2025050265A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
light spot
spot
light
structured light
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2023/116842
Other languages
English (en)
Chinese (zh)
Inventor
王文锦
王志煜
单彩峰
徐永
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Ibaby Labs Inc
Southern University of Science and Technology
Original Assignee
Shenzhen Ibaby Labs Inc
Southern University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Ibaby Labs Inc, Southern University of Science and Technology filed Critical Shenzhen Ibaby Labs Inc
Priority to PCT/CN2023/116842 priority Critical patent/WO2025050265A1/fr
Publication of WO2025050265A1 publication Critical patent/WO2025050265A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40Spoof detection, e.g. liveness detection

Definitions

  • the present invention relates to the technical field of liveness detection, and in particular to a liveness detection method based on structured light spot gradient energy.
  • liveness detection based on structured light analysis. Specifically, this method first projects the speckle structured light image onto the detection target, and then uses a binocular camera or a monocular camera to detect the degree of deformation of the speckle structured light to determine the three-dimensional morphology of the object. This method can effectively detect printed photos or screen displays with planar structures, but it is difficult to deal with attacks from 3D masks or distorted photos.
  • the purpose of the present invention is to solve the technical deficiencies in the security of existing face recognition systems and to provide a liveness detection method based on the gradient energy of structured light spots.
  • the present invention performs clarity detection on each light spot in the structured light image, and utilizes the difference between the low clarity of the light spot in the living area and the high clarity of the light spot in the non-living area to innovate a liveness detection method based on structured light analysis.
  • the present invention provides the following technical solution: a method for detecting living bodies based on structured light spot gradient energy, characterized in that it comprises the following steps:
  • Locate all the light spots in the structured light image First, calculate the optimal pixel value threshold for distinguishing the light spots from the background. Then, binarize the image according to the threshold to obtain a mask highlighting the light spot area. Then, obtain the position information of all the light spots, including the center coordinates and the position of the smallest rectangle containing the corresponding area.
  • this embodiment uses a near-infrared industrial camera with a resolution of 2592 x 1944 to capture images of the detection object under structured light irradiation, significantly enhancing the clarity difference between the light spots in the living area and the light spots in the non-living area, and designs an algorithm based on this to detect the clarity and position of the light spots in the image. If there is a living body, it can be determined that there is a living body in the image and the position of the living body can be given.
  • Structured light spot detection module detects all spots with an area larger than 45 pixels in the structured light image and provides the location information of the spots.
  • Structured light spot image clarity module uses the energy gradient function modified by the present invention to calculate the clarity of the spot image.
  • Living area light spot detection module determines whether the light spot is in the living area based on the clarity of the light spot.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

La présente invention se rapporte au domaine technique de la détection de corps vivant. Est divulgué un procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré, qui comprend les étapes suivantes : S1, acquérir une image de lumière structurée : utiliser un dispositif d'imagerie optique pour acquérir une image de lumière structurée contenant une peau humaine ; S2, localiser tous les points lumineux dans l'image de lumière structurée, et acquérir des informations de position de tous les points lumineux ; S3, sélectionner les points lumineux situés dans la région de corps vivant, calculer la définition de chaque image de point lumineux au moyen d'une formule de fonction de gradient d'énergie, et s'il n'y a pas de point lumineux satisfaisant à une condition ou si le nombre de points lumineux satisfaisant à la condition n'est pas supérieur à dix, déterminer qu'il n'y a pas de corps vivant dans l'image, et marquer "aucun corps vivant n'est détecté dans l'image" sur la partie supérieure de l'image d'origine ; et S4, marquer un résultat de détection de corps vivant dans l'image de lumière structurée. La présente invention surmonte le défaut selon lequel une détection de corps vivant basée sur une analyse de lumière structurée est difficile à gérer avec des attaques de masque tridimensionnel, et permet également d'obtenir une localisation pour des régions de corps vivant dans des images de lumière structurée de granularité.
PCT/CN2023/116842 2023-09-04 2023-09-04 Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré Pending WO2025050265A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/116842 WO2025050265A1 (fr) 2023-09-04 2023-09-04 Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2023/116842 WO2025050265A1 (fr) 2023-09-04 2023-09-04 Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré

Publications (1)

Publication Number Publication Date
WO2025050265A1 true WO2025050265A1 (fr) 2025-03-13

Family

ID=94922738

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/116842 Pending WO2025050265A1 (fr) 2023-09-04 2023-09-04 Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré

Country Status (1)

Country Link
WO (1) WO2025050265A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170286788A1 (en) * 2016-04-01 2017-10-05 Beijing Kuangshi Technology Co., Ltd. Liveness detection method, liveness detection system, and computer program product
CN113255587A (zh) * 2021-06-24 2021-08-13 深圳市光鉴科技有限公司 基于深度相机的刷脸支付系统
CN113468920A (zh) * 2020-03-31 2021-10-01 深圳市光鉴科技有限公司 基于人脸光斑图像的活体检测方法、系统、设备及介质
WO2023060756A1 (fr) * 2021-10-13 2023-04-20 深圳前海微众银行股份有限公司 Procédé et dispositif de détection anti-usurpation de visage, et support de stockage lisible et produit-programme informatique
CN116188588A (zh) * 2022-11-11 2023-05-30 苏州全视智能光电有限公司 光斑中心定位方法及设备
CN116224531A (zh) * 2023-02-27 2023-06-06 上海航天控制技术研究所 一种快速智能化高精度红外成像镜头的调焦装置及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170286788A1 (en) * 2016-04-01 2017-10-05 Beijing Kuangshi Technology Co., Ltd. Liveness detection method, liveness detection system, and computer program product
CN113468920A (zh) * 2020-03-31 2021-10-01 深圳市光鉴科技有限公司 基于人脸光斑图像的活体检测方法、系统、设备及介质
CN113255587A (zh) * 2021-06-24 2021-08-13 深圳市光鉴科技有限公司 基于深度相机的刷脸支付系统
WO2023060756A1 (fr) * 2021-10-13 2023-04-20 深圳前海微众银行股份有限公司 Procédé et dispositif de détection anti-usurpation de visage, et support de stockage lisible et produit-programme informatique
CN116188588A (zh) * 2022-11-11 2023-05-30 苏州全视智能光电有限公司 光斑中心定位方法及设备
CN116224531A (zh) * 2023-02-27 2023-06-06 上海航天控制技术研究所 一种快速智能化高精度红外成像镜头的调焦装置及方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
BYTE CAT: "Clarity detection and enhancement algorithm", JIANSHU, XP009562143, Retrieved from the Internet <URL:https://www.jianshu.com/p/43b210425755> *
HAN YA-RONG, HUANG CHAO-BING, ZHONG JI-WEI, WANG XIANG: "A Method of Thresholding Segmentation and Spot Center Coordinates Calculation for Light Spot-Image", MODERN COMPUTER, 25 September 2011 (2011-09-25), CN, pages 13 - 16, XP093287259, ISSN: 2097-597X *

Similar Documents

Publication Publication Date Title
CN106446873B (zh) 人脸检测方法及装置
CN107705288B (zh) 伪目标运动强干扰下的危险气体泄漏红外视频检测方法
CA2867365C (fr) Procede et systeme d&#39;etalonnage de visage, et support de stockage informatique
JP4970195B2 (ja) 人物追跡システム、人物追跡装置および人物追跡プログラム
CN106530310B (zh) 一种基于人体头顶部识别的行人统计方法及装置
KR100480781B1 (ko) 치아영상으로부터 치아영역 추출방법 및 치아영상을이용한 신원확인방법 및 장치
TW202011733A (zh) 對影像進行目標取樣的方法及裝置
US20130243343A1 (en) Method and device for people group detection
CN101246544A (zh) 一种基于边界点搜索和susan边缘检测的虹膜定位方法
CN104574365B (zh) 障碍物检测装置及方法
US10650249B2 (en) Method and device for counting pedestrians based on identification of head top of human body
CN111739029B (zh) 基于深度学习卷积神经网络的电铲斗齿脱落检测方法
CN107657639A (zh) 一种快速定位目标的方法和装置
CN102096802A (zh) 人脸检测方法及装置
CN108921881A (zh) 一种基于单应性约束的跨摄像头目标跟踪方法
CN107967687A (zh) 一种获取目标物行走姿态的方法与系统
WO2021217764A1 (fr) Procédé de détection du caractère vivant d&#39;un visage humain basé sur l&#39;imagerie de polarisation
CN105574509A (zh) 一种基于光照的人脸识别系统回放攻击检测方法及应用
CN111582118A (zh) 一种人脸识别方法及装置
CN107067595A (zh) 一种指示灯的状态辨识方法、装置及电子设备
CN111222432A (zh) 人脸活体检测方法、系统、设备及可读存储介质
CN104915641B (zh) 基于android平台获取人脸图像光源方位的方法
WO2025050265A1 (fr) Procédé de détection de corps vivant basé sur une énergie de gradient de point lumineux structuré
CN119380042B (zh) 一种基于空间梯度方差最大化的事件特征提取方法
CN112926516B (zh) 一种鲁棒的手指静脉图像感兴趣区域提取方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23951094

Country of ref document: EP

Kind code of ref document: A1