WO2023159350A1 - Système de reconnaissance détectant des caractéristiques faciales - Google Patents
Système de reconnaissance détectant des caractéristiques faciales Download PDFInfo
- Publication number
- WO2023159350A1 WO2023159350A1 PCT/CN2022/077291 CN2022077291W WO2023159350A1 WO 2023159350 A1 WO2023159350 A1 WO 2023159350A1 CN 2022077291 W CN2022077291 W CN 2022077291W WO 2023159350 A1 WO2023159350 A1 WO 2023159350A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- facial
- determining
- eyebrow
- image
- individual
- Prior art date
Links
- 230000001815 facial effect Effects 0.000 title claims abstract description 207
- 238000000034 method Methods 0.000 claims abstract description 42
- 210000005069 ears Anatomy 0.000 claims abstract description 6
- 210000004709 eyebrow Anatomy 0.000 claims description 74
- 239000011148 porous material Substances 0.000 claims description 43
- 230000008901 benefit Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 210000000887 face Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 210000001142 back Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0861—Network architectures or network communication protocols for network security for authentication of entities using biometrical features, e.g. fingerprint, retina-scan
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
Definitions
- the disclosure relates to the biometric recognition technology, and particularly, relates to a facial recognition system for detecting facial features such as facial pores and eyebrow pores.
- biometric recognition technology is common for all spects of authentication applications. From the use of fingerprints, to the more recently facial recognition, the biometric recognition technology can be applied to unlock mobile devices (such as mobile phones) , log into an online account (such as bank account or e-mail account) , and gain access to a building or a restructed area.
- the selection of the biometric recognition method for authentication depends greatly on the level of secuity required. It is foreseeable that the biometric authentication will continue to play an important role in identifying a person, and to be used intentively and widely for various applications.
- the biometric authentication is generally complex and difficult to perform. It involves complex calculations and computations locally in the computer system or remotely on the cloud server. It is also required to run algorithms for checking the similarities to the stored authentication images. In some instances, a less sophisticated system is preferred. This may be used in applications where a lower security level of protection is required.
- a simple facial recognition system that can be performed quickly with less computation power.
- a facial recognition system can detect the facial pores and eyebrow pores of an individual, and determine the similarities with the stored images for granting or denying an access of the individual.
- the facial recognition method includes receiving a first image of an individual; detecting two or more facial landmarks and at least a facial feature of the individual from the first image; determining relative position of the facial feature from and the two or more facial landmarks, and a relative size of the facial feature with respect to the two or more facial landmarks; and determining whether the first image is associated with an authorized user based on the relative positions and the relative size of the facial feature.
- the facial landmark may be the eyes, nose, mouth, or ears of the individual.
- the facial recognition method is configured to grant an access when the first image is determined to be similar to a stored image of the authorized user.
- the at least a facial feature detected includes plural eyebrow pores of an eyebrow of the individual.
- the facial recognition method includes the step of receiving a second image of a magnified image of the eyebrow of the individual.
- the facial recognition method includes the step of determining an eyebrow contour having the plural eyebrow pores arranged on at least an outer arch, an inner arch, or both.
- the detecting of at least a facial feature of the individual from the first image comprises the step of detecting a first group of the plural eyebrow pores on the outer arch, a second group of the plural eyebrow pores on the inner arch, or both.
- the facial recognition method includes the step of selecting an eyebrow shape from a collection of eyebrow templates for the eyebrow of the individual for authentication without a need of an exact match.
- the facial feature is a facial pore.
- the determining of the relative position of the facial feature from the two or more facial landmarks includes the steps of determining a relative distance and an angle from each of the two or more facial landmarks to the facial feature; selecting at least two closest facial landmarks from the two or more facial landmarks based on the relative distance; and marking the relative distance and the angle from each of the at least two closest facial landmarks to the facial feature as positioning parameters of the relative positions.
- the determining of the relative size of the facial feature with respect to the two or more facial landmarks includes the steps of determining a first width of each of the two or more facial landmarks; determining a second width of the facial feature; and determining the relative size of the facial feature based on a ratio between the first width and the second width.
- the determining of the relative size of the facial feature with respect to the two or more facial landmarks includes the steps of determining a first height of each of the two or more facial landmarks; determining a second height of the facial feature; and determining the relative size of the facial feature based on a ratio between the first height and the second height.
- the facial recognition method includes the step of defining a similarity threshold for choosing a level of security.
- FIG. 1 shows an exemplary image of a facial image where facial recognition authentication is performed in accordance with certain embodiments of the present disclosure
- FIG. 2 shows the detection of facial landmarks in accordance with certain embodiments of the present disclosure
- FIG. 3 shows the detection of facial pores in accordance with certain embodiments of the present disclosure
- FIG. 4 shows the detection of eyebrow in accordance with certain embodiments of the present disclosure
- FIG. 5 shows the detection of eyebrow pores in accordance with certain embodiments of the present disclosure.
- FIG. 6 shows the recognition system of the present disclosure executed on a mobile device for performing authentication.
- a computer device may use a facial recognition system for various purposes.
- the computer device may perform according to a facial recognition method to authenticate an individual who attempts to gain access to one or more functionalities of the computer device, or one or more functionalities of other devices controlled by the computer device.
- the computer device having stored images of the faces of one or more authorized users, is configured to compare the image of the individual with the stored images to verify whether the individual attempting to gain access is in fact one of the one or more authorized users.
- the computer device may be a smartphone, a tablet, a computer, a doorbell security camera device, a security portal having one or more revolving doors or vestibules, elevator panel, and the like.
- the computer device may also be provided on the cloud server such that the authentication is executed remotely.
- the computer device has a camera device configured to capture an image of the individual for authentication.
- the image obtained by the camera device is then compared with the stored images of the faces of the one or more authorized users, wherein the stored images may not necessarily be stored in the computer device.
- the stored images are kept in a separated database or memory device locally or remotely.
- the present disclosure is directed to a facial recognition method implemented on a computer device for authenticating an individual who attempts to gain access to one or more functionalities.
- the facial recognition method may include other comparison and verification techniques, which are combined to provide a reliable, effective mean to authenticate the individual.
- the facial recognition method described herein may provide a number of advantages, such as reduced complexity in authentication for minimizing the computation time, and maximized overall accuracy when used in conjunction with other recognition algorithms.
- FIG. 1 provides an exemplary image showing a facial image of an individual 10 where facial recognition operation is performed in accordance with one or more aspects of the present disclosure.
- the facial image may be captured by one or more camera devices, a video recorder, a smartphone, or any appropriate image acquisition devices, and subsequently processed by a face recognition algorithm.
- the computer device may perform operations according to a facial recognition method to authenticate the individual 10.
- the facial recognition method is focused on the facial features, particularly the facial pores 30 and the eyebrow pores 20A (shown in FIG. 5) . This is unlike other conventional recognition system that perform facial recognition system based on the facial landmarks such as the eyes, nose, mouth, ears. Therefore, this is a relatively simple recognition system and can be performed easily.
- the computer device may include a processor, a computer-readable storage device such as memory, hard drive, flash drive, or the like.
- the computer device may include communication interface or network interface for connecting to a remote server or other network database.
- the computer-readable storage device stores a plurality of instructions that, when executed by the processor, performs according to the facial recognition method.
- a first image of the individual 10 is captured and received by the computer device.
- the first image may alternatively be selected and extracted from a video or live stream.
- the computer device subsequently detects two or more facial landmarks from the first image of the individual 10 captured.
- the facial landmark may be eyes 41, nose 42, mouth 43, or ears 44.
- the facial landmarks are not used for authenticating the individual 10 directly. Instead, the facial landmarks are used as the reference for determining the size and position of the facial features.
- the facial landmarks are detected by selected elements, such as iris, pupil, lips, ear helix, nose tip, nostril, dorsum, and so on.
- the computer device is further configured to detect at least a facial feature from the first image of the individual 10, for example, the facial pores 30 and the eyebrow pores 20A.
- the facial pores 30 are on the facial skin surface with a different color (represented as color components) than the facial skin surface.
- the facial pores 30 have darker colors, such as black, which are easily distinguishable.
- the two eyebrows 20 are located above the eyes 41, and one aspect of the present disclosure is related to the detection of plural eyebrow pores 20A after detecting the eyebrow 20, which will be discussed briefly below.
- the eyebrow 20 may be shaped according to a collection of eyebrow templates.
- the collection of eyebrow templates may include an arched shape, a rounded shape, a straight shape, an upward shape, an S-shape, a high arch shape, a curved shape, or other pre-defined shapes.
- the facial recognition method also selects an eyebrow shape from the collection of eyebrow templates for the eyebrow 20 of the individual 10 to confirm whether it matches with the authorized user. Instead of storing the exact shape and details of the eyebrow 20, the present facial recognition method uses the eyebrow templates to perform the comparison and matching. For example, if the authorized user is determined to have an eyebrow having an arched shape, the shape of the eyebrow of the individual 10 who is attempting to gain access will be checked and determined whether it has an arched shape. The level of security is not as high as an exact match, but the computation complexity is lower and the memory required to store the information of the eyebrows for all authorized users is minimized.
- the positions of the right eye 41A and the mouth 43 are used. It is apparent that other proximate facial landmarks may also be used, such as the nose 42, the left eye 41B, and so on.
- the two or more facial landmarks are used to determine the relative position of the facial feature.
- the computer device first determines a relative distance and an angle from each of the two or more facial landmarks to the facial feature, then at least two closest facial landmarks are selected from the two or more facial landmarks based on the relative distance. Using the two closest facial landmarks can improve the accuracy when determining the relative distance and the angle. In certain cases, more than two facial landmarks are used to further improve the accuracy but sacrificing the computation efficiency.
- the relative distance and the angle from each of the at least two closest facial landmarks are marked to the facial feature as positioning parameters of the relative positions.
- the next step is to determine the relative size of the facial feature with respect to the two or more facial landmarks.
- the facial pores 30 on the facial skin surface are generally represented with different color components than the facial skin surface of the individual 10.
- the area with different color components is identified and labelled as a facial pore 30, which is a kind of a facial feature.
- the size of such facial feature is determined by the steps of determining a first width of each of the two or more facial landmarks; determining a second width of the facial feature; and determining the relative size of the facial feature based on a ratio between the first width and the second width. Therefore, the size of the facial feature can be calculated as a factor in width the facial landmarks.
- the size of the facial feature can also be determined by the steps of determining a first height of each of the two or more facial landmarks; determining a second height of the facial feature; and determining the relative size of the facial feature based on a ratio between the first height and the second height. Therefore, the size of the facial feature can be calculated as a factor in height the facial landmarks.
- FIG. 4 shows the detection of eyebrow 20 for the purposes of facial recognition.
- the eyebrow 20 can be identified by the head 21, the outer arch 22, the inner arch 23, and the tail 24.
- the eyebrow contour of the eyebrow 20 can be determined by selecting an eyebrow shape from the collection of eyebrow templates based on the positions of the head 21, the outer arch 22, the inner arch 23, and the tail 24.
- the eyebrow 20 may have an arched shape, a rounded shape, a straight shape, an upward shape, an S-shape, a high arch shape, a curved shape, or other pre-defined shapes.
- the facial recognition method further includes the step of receiving, by the computer device, a second image of a magnified image of the eyebrow 20 of the individual 10.
- the camera device is configured to capture the magnified image by focusing on the eyebrow 20.
- the second image has a higher resolution of the eyebrow 20, which can help to determine the positions of the eyebrow pores 20A.
- the magnified image can show clear details of the eyebrow 20, including hair and pores.
- a machine learning algorithm may be used to detect the position of the pores and enhance the detection accuracy.
- the eyebrow contour as determined above has a plural eyebrow pores 20A arranged on at least an outer arch 22, an inner arch 23, or both.
- the eyebrow hair may only block either the eyebrow pores 20A on the other arch 22 or the eyebrow pores 20A on the inner arch 23, but not both generally.
- the magnified image has sufficient visual details for determining the locations of the eyebrow pores 20A for recognition purposes.
- the facial recognition method is configured to detect a first group 22A of the plural eyebrow pores on the outer arch 22, a second group 23A of the plural eyebrow pores on the inner arch 23, or both the first group 22A and the second group 23A.
- the location and size of each the eyebrow pores 20A are determined by referencing to the right eye 41A, the left eye 41B, or both.
- the location and size of each the eyebrow pores 20A are determined by referencing to the overall shape and size of the eyebrow 20 captured by the first image and the second image.
- the recognition system executed on a mobile device 50 for performing authentication is illustrated.
- a mobile phone is illustrated as the mobile device 50, it is apparent that the mobile device may be a tablet, a notebook computer, a smart watch, a wearable device, or other portable devices.
- the recognition system may also be executed on other non-portable devices.
- the recognition system may be part of the security system in a building, an infrastructure, a restricted area, a bank account, a military structure, a public or private transportation system, and so on. It is essential for the device to have a camera 51, which may be integrated or separately provided.
- the device may be provided with a monitor 52 for showing the image of the individual 10 who attempts to gain access.
- the device may also include a processor and a computer-readable storage device, such as memory device, for storing a plurality of instructions.
- a facial recognition method is performed to authenticate an individual 10 who attempts to gain access to one or more functionalities.
- the facial recognition is preferably executed locally by the computer device without connecting to the network or server computer, thereby it is not dependent on the network connectivity.
- the computer device is configured to determine whether the first image of the individual 10 captured by the camera 51 is associated with an authorized user based on the relative positions and the relative size of the facial feature.
- the facial recognition method is also configured to change to unlock state 54 and grant an access when the first image is determined to be similar to a stored image of the authorized user.
- the facial recognition also comprises the step of defining a similarity threshold for choosing a level of security.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
L'invention concerne un procédé de reconnaissance faciale permettant d'authentifier un individu qui tente d'accéder à une ou plusieurs fonctionnalités. Le procédé de reconnaissance faciale consiste à recevoir une première image d'un individu ; à détecter deux points de repère faciaux ou plus et au moins une caractéristique faciale de l'individu à partir de la première image ; à déterminer une position relative de la caractéristique faciale à partir des deux points de repère faciaux ou plus, et une taille relative de la caractéristique faciale par rapport aux deux points de repère faciaux ou plus ; et à déterminer si la première image est associée à un utilisateur autorisé sur la base des positions relatives et de la taille relative de la caractéristique faciale. Le point de repère facial peut être les yeux, le nez, la bouche ou les oreilles de l'individu. Le procédé de reconnaissance faciale est configuré pour accorder un accès lorsque la première image est déterminée comme étant similaire à une image stockée de l'utilisateur autorisé.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2022/077291 WO2023159350A1 (fr) | 2022-02-22 | 2022-02-22 | Système de reconnaissance détectant des caractéristiques faciales |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2022/077291 WO2023159350A1 (fr) | 2022-02-22 | 2022-02-22 | Système de reconnaissance détectant des caractéristiques faciales |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023159350A1 true WO2023159350A1 (fr) | 2023-08-31 |
Family
ID=87764308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/077291 WO2023159350A1 (fr) | 2022-02-22 | 2022-02-22 | Système de reconnaissance détectant des caractéristiques faciales |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2023159350A1 (fr) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120126939A1 (en) * | 2010-11-18 | 2012-05-24 | Hyundai Motor Company | System and method for managing entrance and exit using driver face identification within vehicle |
CN107403168A (zh) * | 2017-08-07 | 2017-11-28 | 青岛有锁智能科技有限公司 | 一种面部识别系统 |
CN108875484A (zh) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | 用于移动终端的人脸解锁方法、装置和系统及存储介质 |
US20190050546A1 (en) * | 2017-08-09 | 2019-02-14 | Jumio Corporation | Authentication Using Facial Image Comparison |
CN109690542A (zh) * | 2016-07-14 | 2019-04-26 | 金勇尚 | 使用面部识别的用户认证方法以及用于该方法的设备 |
EP3629232A1 (fr) * | 2018-09-26 | 2020-04-01 | Bundesdruckerei GmbH | Dispositif de détection d'une manipulation d'image dans une image de visage numérique de référence d'une personne |
CN111768543A (zh) * | 2020-06-29 | 2020-10-13 | 杭州翔毅科技有限公司 | 基于人脸识别的通行管理方法、设备、存储介质及装置 |
US20210326579A1 (en) * | 2020-04-20 | 2021-10-21 | Scott C. Harris | Mask aware biometric identification system |
-
2022
- 2022-02-22 WO PCT/CN2022/077291 patent/WO2023159350A1/fr unknown
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120126939A1 (en) * | 2010-11-18 | 2012-05-24 | Hyundai Motor Company | System and method for managing entrance and exit using driver face identification within vehicle |
CN109690542A (zh) * | 2016-07-14 | 2019-04-26 | 金勇尚 | 使用面部识别的用户认证方法以及用于该方法的设备 |
CN107403168A (zh) * | 2017-08-07 | 2017-11-28 | 青岛有锁智能科技有限公司 | 一种面部识别系统 |
US20190050546A1 (en) * | 2017-08-09 | 2019-02-14 | Jumio Corporation | Authentication Using Facial Image Comparison |
CN108875484A (zh) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | 用于移动终端的人脸解锁方法、装置和系统及存储介质 |
EP3629232A1 (fr) * | 2018-09-26 | 2020-04-01 | Bundesdruckerei GmbH | Dispositif de détection d'une manipulation d'image dans une image de visage numérique de référence d'une personne |
US20210326579A1 (en) * | 2020-04-20 | 2021-10-21 | Scott C. Harris | Mask aware biometric identification system |
CN111768543A (zh) * | 2020-06-29 | 2020-10-13 | 杭州翔毅科技有限公司 | 基于人脸识别的通行管理方法、设备、存储介质及装置 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101997371B1 (ko) | 신원 인증 방법 및 장치, 단말기 및 서버 | |
KR102299847B1 (ko) | 얼굴 인증 방법 및 장치 | |
US10032327B1 (en) | Access control system with facial recognition and unlocking method thereof | |
US9177130B2 (en) | Facial feature detection | |
US9036876B2 (en) | Method and system for authenticating biometric data | |
US9613428B2 (en) | Fingerprint authentication using stitch and cut | |
US20130227678A1 (en) | Method and system for authenticating user of a mobile device via hybrid biometics information | |
US20140165187A1 (en) | Method, Apparatus, and Computer-Readable Recording Medium for Authenticating a User | |
US10922399B2 (en) | Authentication verification using soft biometric traits | |
KR100905675B1 (ko) | 지문인식 장치 및 방법 | |
US11711215B2 (en) | Methods, systems, and media for secure authentication of users based on a biometric identifier and knowledge-based secondary information | |
KR100554129B1 (ko) | 인체의 열정보를 이용한 개인인증장치와 그 방법 | |
JP4899552B2 (ja) | 認証装置、認証方法、認証プログラム、これを記録したコンピュータ読み取り可能な記録媒体 | |
KR101266603B1 (ko) | 무인접수시스템의 사용자 인증을 위한 얼굴 인식 시스템 | |
EP3785166A1 (fr) | Inscriptions multiples dans une reconnaissance faciale | |
WO2023159350A1 (fr) | Système de reconnaissance détectant des caractéristiques faciales | |
EP3811254A1 (fr) | Procédé et dispositif électronique pour l'authentification d'un utilisateur | |
WO2022060578A1 (fr) | Temporisation intelligente avec détection de changement | |
JP2005275605A (ja) | 個人認証装置および個人認証方法 | |
JP6430987B2 (ja) | 参照点位置決定装置 | |
Patil et al. | Iris recognition using fuzzy system | |
KR100608307B1 (ko) | 얼굴 인식 방법 및 시스템 | |
Shih et al. | Ear detection based on arc-masking extraction and AdaBoost polling verification | |
Venkata Ramana et al. | Hybrid biometric based person identification using machine learning | |
Singh et al. | Biometric Methods of Face Recognition: A Mirror Review |
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: 22927646 Country of ref document: EP Kind code of ref document: A1 |