WO2021088640A1 - Technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique - Google Patents

Technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique Download PDF

Info

Publication number
WO2021088640A1
WO2021088640A1 PCT/CN2020/122249 CN2020122249W WO2021088640A1 WO 2021088640 A1 WO2021088640 A1 WO 2021088640A1 CN 2020122249 W CN2020122249 W CN 2020122249W WO 2021088640 A1 WO2021088640 A1 WO 2021088640A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
neural network
network model
image
facial
Prior art date
Application number
PCT/CN2020/122249
Other languages
English (en)
Chinese (zh)
Inventor
袁正午
查徐鹏
李林
梁星
Original Assignee
重庆邮电大学
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 重庆邮电大学 filed Critical 重庆邮电大学
Priority to KR1020217009596A priority Critical patent/KR102593835B1/ko
Publication of WO2021088640A1 publication Critical patent/WO2021088640A1/fr

Links

Images

Classifications

    • 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
    • G06V40/161—Detection; Localisation; Normalisation
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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

Definitions

  • the invention belongs to the field of image recognition technology, and in particular relates to a face recognition technology based on heuristic Gaussian cloud transformation.
  • Face recognition is a process of analyzing and comparing face images in the database based on digital image processing, computer vision and machine learning technologies, with the help of computer processing technology.
  • face recognition technology mainly uses the convolution training operation of deep convolutional neural networks to extract facial features. For two face images of the same person, the corresponding features belong to the same category; conversely, for two different persons The corresponding features of a face image belong to different categories, so in the face recognition model, a person corresponds to one category.
  • the Softmax classification was used directly to obtain the probability of each class, and the highest probability or the first few probabilities were selected as the recognition result.
  • this technique has low recognition accuracy due to the small training set and the large number of types.
  • the present invention provides a face recognition technology based on heuristic Gaussian cloud transformation, defines a new loss function for face recognition, instead of the softmax classification method, and no longer needs to consider the sample of the recognition object Problems such as a small number and a large number of classification categories have improved the accuracy.
  • the technical solution of the present invention is: a face recognition technology based on heuristic Gaussian cloud transformation, including the following steps:
  • Step 1) Use the camera to obtain the target face image
  • Step 2 Input the target face image into the MTCNN neural network model, and output a square face frame image with only facial features aligned with the face cut;
  • Step 3 Construct a neural network model based on the random_normal activation function, and define a new face recognition loss function
  • Step 4) Pre-train the constructed neural network model with the pre-processed face image data set CASIA-WebFace, and retain the structure and parameters of the trained model;
  • Step 5 Input the target face image and the face image in the face database into the neural network model, and then use the heuristic Gaussian cloud transform algorithm to obtain the ambiguity to judge the face recognition result.
  • the process of constructing a neural network model based on the random_normal activation function and defining a new face recognition loss function includes:
  • Step 3-1 Build a neural network model and set the activation function of each layer to random_nomal;
  • Step 3-2 define the loss function loss of the neural network model
  • the process of defining the loss function loss of the neural network model is as follows:
  • the loss function loss of face recognition is defined as:
  • step 5 the face image of the database is input into the trained neural network model, and the obtained face feature vector is overlaid on the original face image corresponding to the database, and finally, a face feature vector is obtained.
  • the database of faces is composed.
  • the target face feature vector is merged with the feature vector of the face image in the face database, and then the heuristic Gaussian cloud transform algorithm is used to finally obtain the similarity between the target image and the image in the face database degree.
  • the face recognition technology based on heuristic Gaussian cloud transformation disclosed in the present invention has the following beneficial effects:
  • the face database no longer uses face images to store personal face information, and converts the feature vector corresponding to the adult face image to store it. This not only protects the privacy of the user, but also reduces the storage space. It is necessary to judge the ambiguity of the feature vectors of the two groups of face images to obtain their similarity. This recognition method shortens the face recognition time.
  • FIG. 1 is a schematic diagram of the evaluation process of the loss function loss of the present invention.
  • the present invention discloses a face recognition technology based on heuristic Gaussian cloud transformation. The detailed steps are as follows:
  • Step 1) Use the camera to obtain the target face image
  • Step 2 Input the target face image into the MTCNN neural network model, and output a square face frame image with only facial features aligned with the face cut;
  • Step 3 Construct a neural network model based on the random_normal activation function, and add a new face recognition loss function
  • Step 4) Pre-train the constructed neural network model with the pre-processed face image data set CASIA-WebFace, and retain the structure and parameters of the trained model;
  • Step 5 Input the target face image and the face image in the face database into the neural network model, and then use the heuristic Gaussian cloud transform algorithm to obtain the ambiguity to judge the face recognition result.
  • Step 1) The target face image can be obtained by using a smart phone or other smart device, and the way to obtain a good face image is to perform a frontal, horizontal, horizontal, and Get close
  • the target face image is input into the MTCNN neural network model, and the process of outputting a square face frame image with only facial features aligned and cut includes:
  • Step 2-1 Use the P-Net network to obtain candidate frames and boundary regressors, and at the same time, the candidate frames are calibrated according to the bounding boxes, and then the NMS method is used to remove overlapping frames;
  • Step 2-2 Train the picture containing the candidate frame determined by the P-Net network in the R-Net network, use the bounding box vector to fine-tune the candidate frame, and then use the NMS method to remove the overlapping frames;
  • Step 2-3 Use the O-Net network to remove the candidate form and display the location of five key points of the face at the same time.
  • the target face image is processed to obtain a square face frame image after facial features aligned face cutting.
  • the process of constructing a neural network model based on the random_normal activation function in the step 3) and adding a new face recognition loss function includes:
  • Step 3-1 Build a neural network model and set the activation function of each layer to random_nomal, so that the output features of each layer present a normal distribution state;
  • Step 3-2 define the loss function loss of a new neural network model, so as to complete the construction of the neural network model
  • the loss function loss process of the neural network model is as follows:
  • the loss function loss of face recognition is defined as:
  • the neural network model is obtained.
  • step 4 pre-training the constructed neural network model with the pre-processed face image data set CASIA-WebFace, and saving the network model structure and parameters when the model no longer converges;
  • the feature vector of the target face image is merged with the feature vector of the face image in the face database, the number of concepts of the heuristic Gaussian cloud transform algorithm is set to 2, and the merged vector is used as the algorithm Input the data sample set of, get 2 mixing degrees CD 1 , CD 2 , and put The value of is used as the similarity between the target face image and the face image in the face database.
  • the threshold In the actual use process (such as attendance system, user verification system), set a threshold. If the similarity value obtained is higher than the threshold, it will be judged as a similar picture, and the verification is deemed to be passed. If it is lower than the threshold, it will be judged as a different picture. , Indicates that the authentication has failed; the threshold here can be set manually or according to the results of training.

Landscapes

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

Abstract

La présente invention appartient au domaine technique de la reconnaissance d'image et concerne en particulier une technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique. Le procédé consiste à : acquérir une image faciale cible à l'aide d'une caméra; entrer l'image faciale cible dans un modèle MTCNN et délivrer une image de trame faciale carrée obtenue après découpe de visage alignée par caractéristique faciale; construire un modèle de réseau neuronal sur la base d'une fonction d'activation aléatoire normale, et définir une nouvelle fonction de perte de reconnaissance faciale; pré-entraîner le modèle de réseau neuronal construit au moyen d'un ensemble de données d'image faciale prétraité CASIA-WebFace et conserver la structure et les paramètres du modèle entraîné; et entrer l'image faciale cible et les images faciales dans une base de données faciales dans le modèle de réseau neuronal, puis utiliser un algorithme de transformation de nuage gaussien heuristique pour obtenir un degré d'ambiguïté afin de déterminer un résultat de reconnaissance faciale. Selon la présente invention, la technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique est fournie, définit la nouvelle fonction de perte de reconnaissance faciale, remplace un procédé de classification softmax et élimine les problèmes liés au nombre insuffisant d'échantillons d'un objet de reconnaissance et au nombre excessif de catégories de classification, ce qui permet d'améliorer la précision.
PCT/CN2020/122249 2019-11-06 2020-10-20 Technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique WO2021088640A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020217009596A KR102593835B1 (ko) 2019-11-06 2020-10-20 휴리스틱 가우스 클라우드 변환에 기반하는 얼굴인식 기술

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911075387.6 2019-11-06
CN201911075387.6A CN111104852B (zh) 2019-11-06 2019-11-06 一种基于启发式高斯云变换的人脸识别技术

Publications (1)

Publication Number Publication Date
WO2021088640A1 true WO2021088640A1 (fr) 2021-05-14

Family

ID=70420664

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/122249 WO2021088640A1 (fr) 2019-11-06 2020-10-20 Technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique

Country Status (3)

Country Link
KR (1) KR102593835B1 (fr)
CN (1) CN111104852B (fr)
WO (1) WO2021088640A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113806578A (zh) * 2021-09-01 2021-12-17 浪潮卓数大数据产业发展有限公司 一种基于人工智能和大数据的遗失人员询查方法及系统
CN115880727A (zh) * 2023-03-01 2023-03-31 杭州海康威视数字技术股份有限公司 人体识别模型的训练方法和装置
CN117475091A (zh) * 2023-12-27 2024-01-30 浙江时光坐标科技股份有限公司 高精度3d模型生成方法和系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111104852B (zh) * 2019-11-06 2020-10-16 重庆邮电大学 一种基于启发式高斯云变换的人脸识别技术

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530866A (zh) * 2012-12-31 2014-01-22 刘玉超 一种基于高斯云变换的图像处理方法及装置
CN107341463A (zh) * 2017-06-28 2017-11-10 北京飞搜科技有限公司 一种结合图像质量分析与度量学习的人脸特征识别方法
CN107423690A (zh) * 2017-06-26 2017-12-01 广东工业大学 一种人脸识别方法及装置
US20180123797A1 (en) * 2016-10-31 2018-05-03 Electronics And Telecommunications Research Institute Method and apparatus for key generation based on face recognition using cnn and rnn
WO2019002602A1 (fr) * 2017-06-30 2019-01-03 Norwegian University Of Science And Technology (Ntnu) Détection d'images manipulées
CN109165566A (zh) * 2018-08-01 2019-01-08 中国计量大学 一种基于新型损失函数的人脸识别卷积神经网络训练方法
CN109447053A (zh) * 2019-01-09 2019-03-08 江苏星云网格信息技术有限公司 一种基于双重限制注意力神经网络模型的人脸识别方法
CN109543606A (zh) * 2018-11-22 2019-03-29 中山大学 一种加入注意力机制的人脸识别方法
CN111104852A (zh) * 2019-11-06 2020-05-05 重庆邮电大学 一种基于启发式高斯云变换的人脸识别技术

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10198626B2 (en) * 2016-10-19 2019-02-05 Snap Inc. Neural networks for facial modeling
CN107609459B (zh) * 2016-12-15 2018-09-11 平安科技（深圳）有限公司 一种基于深度学习的人脸识别方法及装置
KR102117050B1 (ko) * 2017-09-08 2020-05-29 삼성전자주식회사 이미지 내 휴먼 분리를 위한 전자 장치 및 방법
CN110135236A (zh) * 2019-03-21 2019-08-16 云南路普斯数据科技有限公司 一种基于小波变换及神经网络算法的视频人脸识别方法

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530866A (zh) * 2012-12-31 2014-01-22 刘玉超 一种基于高斯云变换的图像处理方法及装置
US20180123797A1 (en) * 2016-10-31 2018-05-03 Electronics And Telecommunications Research Institute Method and apparatus for key generation based on face recognition using cnn and rnn
CN107423690A (zh) * 2017-06-26 2017-12-01 广东工业大学 一种人脸识别方法及装置
CN107341463A (zh) * 2017-06-28 2017-11-10 北京飞搜科技有限公司 一种结合图像质量分析与度量学习的人脸特征识别方法
WO2019002602A1 (fr) * 2017-06-30 2019-01-03 Norwegian University Of Science And Technology (Ntnu) Détection d'images manipulées
CN109165566A (zh) * 2018-08-01 2019-01-08 中国计量大学 一种基于新型损失函数的人脸识别卷积神经网络训练方法
CN109543606A (zh) * 2018-11-22 2019-03-29 中山大学 一种加入注意力机制的人脸识别方法
CN109447053A (zh) * 2019-01-09 2019-03-08 江苏星云网格信息技术有限公司 一种基于双重限制注意力神经网络模型的人脸识别方法
CN111104852A (zh) * 2019-11-06 2020-05-05 重庆邮电大学 一种基于启发式高斯云变换的人脸识别技术

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113806578A (zh) * 2021-09-01 2021-12-17 浪潮卓数大数据产业发展有限公司 一种基于人工智能和大数据的遗失人员询查方法及系统
CN115880727A (zh) * 2023-03-01 2023-03-31 杭州海康威视数字技术股份有限公司 人体识别模型的训练方法和装置
CN117475091A (zh) * 2023-12-27 2024-01-30 浙江时光坐标科技股份有限公司 高精度3d模型生成方法和系统
CN117475091B (zh) * 2023-12-27 2024-03-22 浙江时光坐标科技股份有限公司 高精度3d模型生成方法和系统

Also Published As

Publication number Publication date
CN111104852A (zh) 2020-05-05
KR102593835B1 (ko) 2023-10-25
KR20210100592A (ko) 2021-08-17
CN111104852B (zh) 2020-10-16

Similar Documents

Publication Publication Date Title
WO2021088640A1 (fr) Technologie de reconnaissance faciale basée sur une transformation de nuage gaussien heuristique
WO2021077984A1 (fr) Procédé et appareil de reconnaissance d'objets, dispositif électronique et support de stockage lisible
CN108509862B (zh) 抗角度与遮挡干扰的快速人脸识别方法
Abozaid et al. Multimodal biometric scheme for human authentication technique based on voice and face recognition fusion
Goswami et al. MDLFace: Memorability augmented deep learning for video face recognition
WO2020114118A1 (fr) Procédé et dispositif d'identification d'attribut facial, support d'enregistrement et processeur
US20170262472A1 (en) Systems and methods for recognition of faces e.g. from mobile-device-generated images of faces
KR101254177B1 (ko) 방사형 기저 함수 신경회로망 알고리즘을 이용한 실시간 얼굴 인식 시스템
CN112101241A (zh) 一种基于深度学习的轻量级表情识别方法
CN110781829A (zh) 一种轻量级深度学习的智慧营业厅人脸识别方法
CN111191564A (zh) 基于多角度神经网络的多姿态人脸情绪识别方法及系统
CN112686191B (zh) 基于人脸三维信息的活体防伪方法、系统、终端及介质
CN113205002B (zh) 非受限视频监控的低清人脸识别方法、装置、设备及介质
CN108564040A (zh) 一种基于深度卷积特征的指纹活性检测方法
CN112395901A (zh) 一种改进型复杂环境下人脸检测定位识别方法
Jadhav et al. HDL-PI: hybrid DeepLearning technique for person identification using multimodal finger print, iris and face biometric features
CN113011307A (zh) 一种基于深度残差网络的人脸识别身份认证方法
Radu et al. A colour iris recognition system employing multiple classifier techniques
CN111191549A (zh) 一种两级人脸防伪检测方法
RU2768797C1 (ru) Способ и система для определения синтетически измененных изображений лиц на видео
Zuobin et al. Effective feature fusion for pattern classification based on intra-class and extra-class discriminative correlation analysis
Sivasangari et al. Facial recognition system using decision tree algorithm
Nguyen et al. User re-identification using clothing information for smartphones
Balraj et al. Fusion of Iris, Face, Fingerprint using Score Level Mechanism for Biometric Application
Gong Face Recognition: Representation, Intrinsic Dimensionality, Capacity, and Demographic Bias

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: 20885091

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: 20885091

Country of ref document: EP

Kind code of ref document: A1