WO2020253304A1 - Dispositif de reconnaissance faciale et procédé de traitement d'image, modèle d'extraction de caractéristique et support de stockage - Google Patents

Dispositif de reconnaissance faciale et procédé de traitement d'image, modèle d'extraction de caractéristique et support de stockage Download PDF

Info

Publication number
WO2020253304A1
WO2020253304A1 PCT/CN2020/081757 CN2020081757W WO2020253304A1 WO 2020253304 A1 WO2020253304 A1 WO 2020253304A1 CN 2020081757 W CN2020081757 W CN 2020081757W WO 2020253304 A1 WO2020253304 A1 WO 2020253304A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
feature
target
face
target face
Prior art date
Application number
PCT/CN2020/081757
Other languages
English (en)
Chinese (zh)
Inventor
赖长明
徐永泽
薛凯文
Original Assignee
深圳Tcl新技术有限公司
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 深圳Tcl新技术有限公司 filed Critical 深圳Tcl新技术有限公司
Publication of WO2020253304A1 publication Critical patent/WO2020253304A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the target scale and target direction of the Gabor filter are selected according to the prior knowledge of the face.
  • the present application also provides a face recognition device, the face recognition device comprising: a memory, a processor, and a face recognition stored on the memory and running on the processor A program, when the face recognition program is executed by the processor, the steps of the face recognition method as described in any one of the above are implemented.
  • the 1*1 convolutional layer in the Inception module can specifically include 4, one is set to generate the above-mentioned first group of first sub-feature images, and two 1*1 volumes
  • the build-up layer is set to 3*3 convolutional layer and 5*5 convolutional layer before convolution operation on the target face image to reduce the image data input to the 3*3 convolutional layer and 5*5 convolutional layer Data dimension
  • the data dimension of the obtained face feature image can be the same as the dimension of the feature image data output by the preset module in the deep convolutional neural network, so that the face feature image data can be followed in the deep convolutional neural network.
  • processing there is no need to modify the network architecture of the original deep convolutional neural network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

La présente invention concerne un procédé de traitement d'image, ledit procédé de traitement d'image comprenant les étapes suivantes consistant à : obtenir une image faciale cible ; utiliser un filtre de Gabor pour traiter l'image faciale cible au moyen d'un traitement de filtre de Gabor pour obtenir une première image de caractéristique ; utiliser un module prédéfini dans un réseau neuronal convolutif profond pour effectuer un traitement de convolution et de regroupement sur l'image faciale cible pour obtenir une seconde image de caractéristique ; en fonction de la première image de caractéristique et de la seconde image de caractéristique, générer une image de caractéristique faciale correspondant à l'image faciale cible. La présente invention concerne également un modèle d'extraction de caractéristique faciale, un dispositif de reconnaissance faciale et un support de stockage lisible.
PCT/CN2020/081757 2019-06-17 2020-03-27 Dispositif de reconnaissance faciale et procédé de traitement d'image, modèle d'extraction de caractéristique et support de stockage WO2020253304A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910525542.3A CN110245621B (zh) 2019-06-17 2019-06-17 人脸识别装置及图像处理方法、特征提取模型、存储介质
CN201910525542.3 2019-06-17

Publications (1)

Publication Number Publication Date
WO2020253304A1 true WO2020253304A1 (fr) 2020-12-24

Family

ID=67887805

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/081757 WO2020253304A1 (fr) 2019-06-17 2020-03-27 Dispositif de reconnaissance faciale et procédé de traitement d'image, modèle d'extraction de caractéristique et support de stockage

Country Status (2)

Country Link
CN (1) CN110245621B (fr)
WO (1) WO2020253304A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113705361A (zh) * 2021-08-03 2021-11-26 北京百度网讯科技有限公司 活体检测模型的方法、装置及电子设备

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110245621B (zh) * 2019-06-17 2023-10-17 深圳Tcl新技术有限公司 人脸识别装置及图像处理方法、特征提取模型、存储介质
CN112200169B (zh) * 2020-12-07 2021-04-30 北京沃东天骏信息技术有限公司 用于训练模型的方法、装置、设备以及存储介质
CN112633099B (zh) * 2020-12-15 2023-06-20 中国人民解放军战略支援部队信息工程大学 基于Gabornet的大脑低级视觉区信号处理方法及***
CN113903094A (zh) * 2021-10-22 2022-01-07 兰州乐智教育科技有限责任公司 一种宿舍签到的安全认证方法、装置、设备以及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6826300B2 (en) * 2001-05-31 2004-11-30 George Mason University Feature based classification
CN105718889A (zh) * 2016-01-21 2016-06-29 江南大学 基于GB(2D)2PCANet深度卷积模型的人脸身份识别方法
CN107392183A (zh) * 2017-08-22 2017-11-24 深圳Tcl新技术有限公司 人脸分类识别方法、装置及可读存储介质
CN107437081A (zh) * 2017-08-07 2017-12-05 北京中星微电子有限公司 基于深度卷神经网络的人脸识别方法、装置和存储介质
CN108090409A (zh) * 2017-11-06 2018-05-29 深圳大学 人脸识别方法、装置和存储介质
CN108345818A (zh) * 2017-01-23 2018-07-31 北京中科奥森数据科技有限公司 一种人脸活体检测方法及装置
CN109886209A (zh) * 2019-02-25 2019-06-14 成都旷视金智科技有限公司 异常行为检测方法及装置、车载设备
CN110245621A (zh) * 2019-06-17 2019-09-17 深圳Tcl新技术有限公司 人脸识别装置及图像处理方法、特征提取模型、存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108388830B (zh) * 2018-01-09 2020-08-14 中国农业大学 基于卷积神经网的动物体形检测方法及装置
CN109190622A (zh) * 2018-09-11 2019-01-11 深圳辉煌耀强科技有限公司 基于强特征和神经网络的上皮细胞分类***和方法
CN109446980A (zh) * 2018-10-25 2019-03-08 华中师范大学 表情识别方法及装置
CN109859091B (zh) * 2018-12-24 2023-05-16 中国人民解放军国防科技大学 基于Gabor滤波和卷积神经网络的图像隐写检测方法
CN109753938B (zh) * 2019-01-10 2021-11-05 京东方科技集团股份有限公司 图像识别方法和设备及应用、神经网络的训练方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6826300B2 (en) * 2001-05-31 2004-11-30 George Mason University Feature based classification
CN105718889A (zh) * 2016-01-21 2016-06-29 江南大学 基于GB(2D)2PCANet深度卷积模型的人脸身份识别方法
CN108345818A (zh) * 2017-01-23 2018-07-31 北京中科奥森数据科技有限公司 一种人脸活体检测方法及装置
CN107437081A (zh) * 2017-08-07 2017-12-05 北京中星微电子有限公司 基于深度卷神经网络的人脸识别方法、装置和存储介质
CN107392183A (zh) * 2017-08-22 2017-11-24 深圳Tcl新技术有限公司 人脸分类识别方法、装置及可读存储介质
CN108090409A (zh) * 2017-11-06 2018-05-29 深圳大学 人脸识别方法、装置和存储介质
CN109886209A (zh) * 2019-02-25 2019-06-14 成都旷视金智科技有限公司 异常行为检测方法及装置、车载设备
CN110245621A (zh) * 2019-06-17 2019-09-17 深圳Tcl新技术有限公司 人脸识别装置及图像处理方法、特征提取模型、存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113705361A (zh) * 2021-08-03 2021-11-26 北京百度网讯科技有限公司 活体检测模型的方法、装置及电子设备

Also Published As

Publication number Publication date
CN110245621A (zh) 2019-09-17
CN110245621B (zh) 2023-10-17

Similar Documents

Publication Publication Date Title
WO2020253304A1 (fr) Dispositif de reconnaissance faciale et procédé de traitement d'image, modèle d'extraction de caractéristique et support de stockage
Rao et al. Deep convolutional neural networks for sign language recognition
CN109416727B (zh) 一种人脸图像中眼镜去除方法及装置
WO2019100724A1 (fr) Procédé et dispositif d'apprentissage de modèle de classification à étiquettes multiples
CN109902548B (zh) 一种对象属性识别方法、装置、计算设备及***
WO2021012494A1 (fr) Procédé et appareil de reconnaissance faciale basée sur l'apprentissage profond, et support de stockage lisible par ordinateur
CN110660037A (zh) 图像间脸部交换的方法、装置、***和计算机程序产品
US11816880B2 (en) Face recognition method and apparatus, computer device, and storage medium
JP2015513754A (ja) 顔認識方法及びデバイス
CN110222718B (zh) 图像处理的方法及装置
CN110569756A (zh) 人脸识别模型构建方法、识别方法、设备和存储介质
CN112084917A (zh) 一种活体检测方法及装置
WO2022042043A1 (fr) Procédé et appareil de formation d'un modèle d'apprentissage machine et dispositif électronique
CN111914748B (zh) 人脸识别方法、装置、电子设备及计算机可读存储介质
CN111695462A (zh) 一种人脸识别方法、装置、存储介质和服务器
CN112001285B (zh) 一种美颜图像的处理方法、装置、终端和介质
CN113298158A (zh) 数据检测方法、装置、设备及存储介质
CN114863539A (zh) 一种基于特征融合的人像关键点检测方法及***
CN110826534B (zh) 一种基于局部主成分分析的人脸关键点检测方法及***
CN111126250A (zh) 一种基于ptgan的行人重识别方法及装置
Zhang et al. Landmark‐Guided Local Deep Neural Networks for Age and Gender Classification
WO2021217919A1 (fr) Procédé et appareil de reconnaissance d'unité d'action faciale, dispositif électronique et support de stockage
CN116386105A (zh) 人脸表情识别方法、电子设备及存储介质
Shukla et al. Deep Learning Model to Identify Hide Images using CNN Algorithm
JP7270304B2 (ja) ユーザのバイオメトリック特性を有する画像中の物体を識別することにより当該ユーザのｉｄを検証するための方法、及び当該方法を実施するためのモバイル装置

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: 20826767

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20826767

Country of ref document: EP

Kind code of ref document: A1