CN108229427B - A kind of identity security verification method and system based on identity document and face recognition - Google Patents
A kind of identity security verification method and system based on identity document and face recognitionDownload PDFInfo
- Publication number
- CN108229427B CN108229427BCN201810085256.5ACN201810085256ACN108229427BCN 108229427 BCN108229427 BCN 108229427BCN 201810085256 ACN201810085256 ACN 201810085256ACN 108229427 BCN108229427 BCN 108229427B
- Authority
- CN
- China
- Prior art keywords
- image
- face
- verification
- features
- unit
- 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.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/446—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering using Haar-like filters, e.g. using integral image techniques
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Collating Specific Patterns (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明属于生物特征识别的安全认证领域，更具体地，涉及一种基于身份证件和人脸识别的身份安全验证方法及系统。The invention belongs to the security authentication field of biometric identification, and more particularly relates to an identity security authentication method and system based on identity documents and face recognition.
背景技术Background technique
身份安全验证在银行、海关、机场、火车站等场景中应用广泛，随着身份证件中非接触式智能芯片的普及和人脸识别技术的高速发展，越来越多的场合对于身份验证系统的简易性、高效性、准确性提出了更高的要求。Identity security verification is widely used in banks, customs, airports, railway stations and other scenarios. With the popularization of non-contact smart chips in identity documents and the rapid development of face recognition technology, more and more occasions have Simplicity, efficiency and accuracy put forward higher requirements.
身份安全验证一方面需要验证证件的真伪，另一方面需要验证持证人与证件所有者是否一致。目前，对于前者，主要是利用证件本身的防伪点进行识别，或者人工判断芯片读取照片与证件表面印刷照片是否一致。而对于后者，则通常需要工作人员进行人工核验，不仅耗费大量时间，且验证的可靠性强依赖于工作人员的经验和能力，使得整个系统的安全性显著降低。On the one hand, identity security verification needs to verify the authenticity of the certificate, and on the other hand, it needs to verify whether the certificate holder is the same as the certificate owner. At present, for the former, the identification is mainly carried out by using the anti-counterfeiting points of the document itself, or it is manually judged whether the photo read by the chip is consistent with the photo printed on the surface of the document. For the latter, it usually requires staff to perform manual verification, which not only consumes a lot of time, but also the reliability of verification is strongly dependent on the experience and ability of the staff, which significantly reduces the security of the entire system.
目前已存在一些基于二代身份证和人脸识别技术的身份安全验证系统，为了解决芯片存储照片像素极低无法应用图像处理技术的问题，部分系统采取联网获得证件原始照片再与现场照片进行比对的方法，联网的要求导致应用范围严重受限。At present, there are some identity security verification systems based on the second-generation ID card and face recognition technology. In order to solve the problem that the image processing technology cannot be applied due to the extremely low pixels of the photos stored in the chip, some systems use the Internet to obtain the original photo of the ID card and compare it with the on-site photo. For the method, the requirement of networking leads to a serious limitation of the scope of application.
申请号为CN102902959A，名称为“基于二代身份证存储证件照的人脸识别方法及系统”的专利文献提出的方案无需接入身份证数据中心，但该方案需要对芯片照片采取大量复杂的预处理步骤，且判定决策仍依赖于人脸训练库。The solution proposed in the patent document with application number CN102902959A and titled "Face Recognition Method and System for Storing ID Photos Based on Second-Generation ID Cards" does not require access to the ID card data center, but this solution requires a large number of complex pre-processing steps for chip photos. processing steps, and the decision-making still relies on the face training library.
申请号为CN102129555A，名称为“基于第二代身份证进行身份验证的方法及系统”的专利文献，通过比对身份证表面扫描照片和实时照片完成对持证人身份的验证，但由于扫描获得的照片存在硬件导致的无法归一化的噪声影响，使得提取的特征无法准确表达图像信息，从而系统识别正确率较低，无法满足安检场景中的严格要求。The patent document with the application number CN102129555A and the title of "Method and System for Identity Verification Based on the Second Generation ID Card", completes the verification of the identity of the holder by comparing the scanned photo on the surface of the ID card and the real-time photo, but the result is obtained by scanning. There is a noise effect that cannot be normalized due to hardware, so that the extracted features cannot accurately express the image information, so the system has a low recognition accuracy and cannot meet the strict requirements in the security inspection scene.
另外，国内目前尚无可以处理港澳通行证和护照等身份证件的身份安全验证系统，无法满足海关或国际大型活动安检场景的需求。In addition, there is currently no identity security verification system in China that can handle identity documents such as Hong Kong and Macau passes and passports, which cannot meet the needs of customs or large-scale international event security inspection scenarios.
发明内容SUMMARY OF THE INVENTION
针对现有技术的缺陷和改进需求，本发明提供了一种基于身份证件和人脸识别的身份安全验证方法及系统，其目的在于，不依赖于外部数据库，可直接验证持证人和证件所有者的一致性，从而提高验证的效率和准确率，同时随着验证系统的应用逐步扩充后台数据库，以实现基于第二代居民身份证、港澳通行证、护照等多种身份证件的综合认证，进一步保障公共安全。Aiming at the defects and improvement requirements of the prior art, the present invention provides an identity security verification method and system based on identity documents and face recognition. At the same time, with the application of the verification system, the background database is gradually expanded to realize the comprehensive authentication based on the second-generation resident ID card, Hong Kong and Macao pass, passport and other ID documents, and further Protect public safety.
为实现上述目的，按照本发明的一个方面，提供了一种基于身份证件和人脸识别的身份安全验证方法，包括如下步骤：In order to achieve the above object, according to one aspect of the present invention, a kind of identity security verification method based on identity document and face recognition is provided, comprising the following steps:
(1)系统注册步骤：获取用户身份证件的证件信息作为注册信息，并采集用户正面免冠清晰的人脸图像作为注册图像，然后将注册信息和注册图像存入数据库；身份证件可以包括但不限于第二代居民身份证、港澳通行证、护照；身份证件的证件信息包括证件号和持证人的姓名；(1) System registration steps: obtain the certificate information of the user's identity certificate as the registration information, and collect the clear face image of the user's front without a hat as the registration image, and then store the registration information and registration image in the database; the identity certificate may include but not limited to The second-generation resident ID card, Hong Kong and Macau pass, and passport; the ID information of the ID card includes the ID number and the name of the holder;
(2)信息采集步骤：获取用户身份证件的证件信息、芯片内图像以及证件表面印刷照片的扫描图像，并采集实时人脸图像；根据证件信息查询数据库，若查询到相关条目，则从查询结果中提取注册图像；若查询不到相关条目，则在数据库中根据证件信息创建一个新条目，所创建的新条目中注册图像为空；(2) Information collection step: obtain the ID information of the user's ID card, the image in the chip and the scanned image of the printed photo on the surface of the ID card, and collect the real-time face image; query the database according to the ID information, if the relevant item is queried, the query result will be retrieved from the query result Extract the registered image from the database; if no relevant entry is found, a new entry will be created in the database according to the certificate information, and the registered image in the created new entry will be empty;
(3)证件鉴伪步骤：分别提取由步骤(2)获取到的芯片内图像和扫描图像的浅层特征，并进行一致性判定；若芯片内图像和扫描图像一致，则转入步骤(4)；若芯片内图像和扫描图像不一致，则验证不通过，验证终止；(3) Document authentication step: extract the shallow features of the in-chip image and the scanned image obtained by step (2) respectively, and carry out consistency judgment; if the in-chip image and the scanned image are consistent, go to step (4) ); if the image in the chip is inconsistent with the scanned image, the verification fails and the verification terminates;
(4)图像预处理步骤：若步骤(2)中，获取到注册图像，则对实时人脸图像进行人脸检测和预处理，得到第一对比图像，并对注册图像进行人脸检测和预处理，得到第二对比图像；若步骤(2)中，未获取到注册图像，则对实时人脸图像进行人脸检测和预处理，得到第一对比图像，并对芯片内图像和扫描图像中图像质量较高的图像进行人脸检测和预处理，得到第二对比图像；通过对图像进行人脸检测和预处理，能够提高人脸验证的效率和精确度；(4) Image preprocessing step: if the registered image is obtained in step (2), face detection and preprocessing are performed on the real-time face image to obtain a first contrast image, and face detection and preprocessing are performed on the registered image. processing to obtain a second contrast image; if in step (2), the registration image is not obtained, face detection and preprocessing are performed on the real-time face image to obtain the first contrast image, and the in-chip image and the scanned image are analyzed. The image with higher image quality is subjected to face detection and preprocessing to obtain a second contrast image; by performing face detection and preprocessing on the image, the efficiency and accuracy of face verification can be improved;
(5)人脸验证步骤：分别提取由步骤(4)获取到的第一对比图像和第二对比图像的深层特征，并计算二者的匹配度；若匹配度高于第一阈值，则转入步骤(6)；否则，验证不通过，验证终止；(5) Face verification step: extract the deep features of the first contrast image and the second contrast image obtained in step (4) respectively, and calculate the matching degree of the two; if the matching degree is higher than the first threshold, transfer the Enter step (6); otherwise, the verification fails, and the verification terminates;
(6)数据库更新步骤：若步骤(2)中，未获取到注册图像，则将本次采集的实时人脸图像作为注册图像，存入数据库对应的条目中，并转入步骤(7)；若步骤(2)中，获取到注册图像，并且当前验证时间距离上次数据库更新时间的时间间隔超过第二阈值，则将本次采集的实时人脸图像作为注册图像，更新数据库中对应的条目，并转入步骤(7)；若步骤(2)中，获取到注册图像，并且当前验证时间距离上次数据库更新时间的时间间隔未超过第二阈值，则转入步骤(7)；(6) database update step: if in step (2), the registered image is not obtained, then the real-time face image collected this time is used as the registered image, stored in the corresponding entry of the database, and transferred to step (7); If in step (2), the registered image is obtained, and the time interval between the current verification time and the last database update time exceeds the second threshold, then the real-time face image collected this time is used as the registered image, and the corresponding entry in the database is updated , and go to step (7); If in step (2), obtain the registration image, and the time interval of the current verification time from the last database update time does not exceed the second threshold, then go to step (7);
(7)验证通过，验证结束。(7) The verification is passed, and the verification ends.
进一步地，步骤(5)中用于判定人脸验证是否通过的第一阈值根据经验设定；第一阈值越大，则人脸验证的计算复杂度越低，但人脸验证的精确度越低；相反地，第一阈值越小，则人脸验证的精确度越高，但人脸验证的计算复杂度越高。Further, in step (5), the first threshold for determining whether the face verification passes is set according to experience; the larger the first threshold is, the lower the computational complexity of face verification is, but the more accurate the face verification is. Low; on the contrary, the smaller the first threshold, the higher the accuracy of face verification, but the higher the computational complexity of face verification.
进一步地，步骤(5)中，第一对比图像的深层特征和第二对比图像的深层特征之间的匹配度为二者的余弦距离。Further, in step (5), the matching degree between the deep feature of the first contrast image and the deep feature of the second contrast image is the cosine distance of the two.
进一步地，步骤(6)中判定是否更新注册图像的第二阈值根据实际应用场景设定；第二阈值越小，则注册图像更新越频繁，人脸验证的精确度越高，但更新开销较大；相反地，第二阈值越小，则注册图像更新越不频繁，更新开销较小，但人脸验证的精确度也较小。Further, in step (6), the second threshold for determining whether to update the registered image is set according to the actual application scenario; the smaller the second threshold is, the more frequently the registered image is updated, and the accuracy of face verification is higher, but the update cost is relatively high. On the contrary, the smaller the second threshold is, the less frequently the registered image is updated, and the update overhead is smaller, but the accuracy of face verification is also smaller.
进一步地，步骤(3)中提取的浅层特征为SURF特征、直方图水平投影特征、直方图垂直投影特征以及梯度特征组合而成的特征；以降低计算复杂度，同时提高提取速度。Further, the shallow features extracted in step (3) are features composed of SURF features, histogram horizontal projection features, histogram vertical projection features, and gradient features, so as to reduce computational complexity and improve extraction speed.
进一步地，步骤(3)中，一致性判定的方法包括：计算所提取的浅层特征之间的欧式距离；若欧式距离大于第三阈值，则判定芯片内图像和扫描图像一致；否则，判定芯片内图像和扫描图像不一致。Further, in step (3), the method for consistency determination includes: calculating the Euclidean distance between the extracted shallow features; if the Euclidean distance is greater than the third threshold, it is determined that the in-chip image is consistent with the scanned image; otherwise, it is determined that The in-chip image and the scanned image are inconsistent.
更进一步地，第三阈值根据经验设定；随着系统投入使用，数据库会动态扩张，系统将得到定期更新，第三阈值将更为精确。Furthermore, the third threshold is set based on experience; as the system is put into use, the database will expand dynamically, the system will be updated regularly, and the third threshold will be more precise.
进一步地，步骤(4)中可采用Haar特征和Adaboost分类器进行人脸检测；Further, in step (4), Haar feature and Adaboost classifier can be used for face detection;
进一步地，步骤(4)中，对图像的预处理包括：直方图均衡、高斯滤波去噪以及图像大小归一化；Further, in step (4), the preprocessing of the image includes: histogram equalization, Gaussian filter denoising, and image size normalization;
进一步地，步骤(4)中，比较芯片内图像和扫描图像的图像质量的方法包括：比较芯片内图像和扫描图像的图像文件的大小，图像文件越大，则图像质量越高；对于第二代居民身份证，扫描图像的图像质量较高；对于护照，芯片内图像的图像质量较高。Further, in step (4), the method for comparing the image quality of the in-chip image and the scanned image includes: comparing the size of the image file of the in-chip image and the scanned image, the larger the image file, the higher the image quality; for the second For resident ID cards, the image quality of the scanned image is higher; for passports, the image quality of the image inside the chip is higher.
进一步地，步骤(5)中，提取图像深层特征的方法包括：得到图像的高维卷积特征，再对高维卷积特征进行降维处理，得到适于计算的低维特征；将低维特征作为用于人脸验证的深层特征；用于得到图像高维卷积特征的方法包括但不限于深度卷积神经网络；用于对高维卷积特征进行降维处理的方法包括但不限于主成分分析算法。Further, in step (5), the method for extracting deep image features includes: obtaining high-dimensional convolution features of the image, and then performing dimension reduction processing on the high-dimensional convolution features to obtain low-dimensional features suitable for calculation; Features are used as deep features for face verification; methods for obtaining high-dimensional convolutional features of images include but are not limited to deep convolutional neural networks; methods for dimensionality reduction processing on high-dimensional convolutional features include but are not limited to Principal Component Analysis algorithm.
按照本发明的另一方面，本发明还提供了一种用于实现本发明所提供的基于身份证件和人脸识别的身份安全验证方法的系统，包括：视频流图像单元、证件信息采集单元、图像预处理单元、人脸验证单元以及数据库管理单元；According to another aspect of the present invention, the present invention also provides a system for realizing the identity security verification method based on the ID card and face recognition provided by the present invention, comprising: a video stream image unit, a certificate information collection unit, Image preprocessing unit, face verification unit and database management unit;
视频流图像单元用于在系统注册时采集用户正面免冠清晰的人脸图像作为注册图像；视频流图像单元还用于在信息采集时采集实时人脸图像；The video stream image unit is used to collect a clear face image of the user's front without a hat as a registration image when the system is registered; the video stream image unit is also used to collect real-time face images during information collection;
证件信息采集单元用于在系统注册时录入证件信息作为注册信息；证件信息采集单元还用于在信息采集时读取身份证件的证件信息及芯片内图像，并对身份证件进行扫描以获取证件表面印刷照片的扫描图像；The certificate information collection unit is used to enter the certificate information as registration information during system registration; the certificate information collection unit is also used to read the certificate information and the image in the chip of the ID card during information collection, and scan the ID card to obtain the surface of the certificate Scanned images of printed photographs;
图像预处理单元用于在图像预处理时对图像进行人脸检测和预处理，以提高人脸验证的精确度；The image preprocessing unit is used to perform face detection and preprocessing on the image during image preprocessing, so as to improve the accuracy of face verification;
人脸验证单元用于在证件鉴伪时提取由证件信息采集单元获取的芯片内图像和扫描图像，然后分别提取二者的浅层特征并进行一致性判定；人脸验证单元还用于在人脸验证时提取由图像预处理单元获取第一对比图像和第二对比图像，然后分别提取第一对比图像和第二对比图像的深层特征并计算二者的匹配度；The face verification unit is used to extract the in-chip image and the scanned image acquired by the document information collection unit when the certificate is authenticated, and then extract the shallow features of the two and perform consistency determination; the face verification unit is also used for During face verification, extract the first contrast image and the second contrast image by the image preprocessing unit, then extract the deep features of the first contrast image and the second contrast image respectively and calculate the matching degree of the two;
数据库管理单元用于在系统注册时从证件信息采集单元获取注册信息，并从视频流图像单元获取注册图像，然后将获取到的注册信息和注册图像存入数据库；数据库管理单元还用于在信息采集时从信息采集单元获取证件信息，并根据获取到的证件信息查询数据库；数据库管理单元还用于在数据库更新时从视频流图像单元获取实时人脸图像作为注册图像，并将获取到的注册图像存入或者更新到数据库中。The database management unit is used to obtain registration information from the certificate information collection unit when the system is registered, and obtain the registration image from the video stream image unit, and then store the obtained registration information and registration image in the database; Obtain the certificate information from the information collection unit during collection, and query the database according to the obtained certificate information; the database management unit is also used to obtain the real-time face image from the video stream image unit as the registration image when the database is updated, and use the obtained registration image Images are stored or updated in the database.
进一步地，视频流图像单元为摄像头。Further, the video stream image unit is a camera.
进一步地，证件信息采集单元包括：CIS(Contact Image Sensor，接触式图像传感器)图像采集模块和芯片读卡器；CIS图像采集模块用于扫描证件以获取身份证件表面印刷照片的扫描图像，芯片读卡器用于读取身份证件的证件信息及芯片内图像。Further, the certificate information acquisition unit includes: a CIS (Contact Image Sensor, contact image sensor) image acquisition module and a chip card reader; the CIS image acquisition module is used to scan the certificate to obtain the scanned image of the photo printed on the surface of the identity certificate, and the chip reads the scanned image. The card reader is used to read the ID information and the image in the chip of the ID document.
进一步地，人脸验证单元从图像提取的浅层特征为SURF特征、直方图水平投影特征、直方图垂直投影特征以及梯度特征组合而成的特征，以降低计算复杂度，同时提高提取速度。Further, the shallow features extracted from the image by the face verification unit are features composed of SURF features, histogram horizontal projection features, histogram vertical projection features and gradient features to reduce computational complexity and improve extraction speed.
进一步地，人脸验证单元从图像提取深层特征的方法包括：得到图像的高维卷积特征，再对高维卷积特征进行降维处理，得到适于计算的低维特征；将低维特征作为用于人脸验证的深层特征。Further, the method for extracting deep features from the image by the face verification unit includes: obtaining high-dimensional convolution features of the image, and then performing dimension reduction processing on the high-dimensional convolution features to obtain low-dimensional features suitable for calculation; as deep features for face verification.
总体而言，通过本发明所构思的以上技术方案，能够取得以下有益效果：In general, through the above technical solutions conceived by the present invention, the following beneficial effects can be achieved:
(1)建立了用于存储身份证件信息和注册图像的数据库，并定期对注册图像进行更新，一方面不依赖于外部数据库，可以提高身份安全验证的效率；另一方面，用于人脸验证的对比图像为用户近期的人脸图像及采集的实时人脸图像，能够显著提高人脸验证的正确率，并且在此基础上，人脸验证不强依赖于人工操作，可以显著提高人脸验证的验证速度；(1) A database for storing ID information and registered images is established, and the registered images are regularly updated. On the one hand, it does not rely on external databases, which can improve the efficiency of identity security verification; on the other hand, it is used for face verification. The comparison images of the user's recent face images and the collected real-time face images can significantly improve the correct rate of face verification. On this basis, face verification is not strongly dependent on manual operations, which can significantly improve face verification. verification speed;
(2)在证件鉴伪时，通过提取身份证件的芯片内图像和证件表面印刷照片的扫描图像的浅层特征完成证件真伪的鉴定，不再依赖于人工鉴别，可以提高证件鉴伪的效率和准确度；并且提取的浅层特征为SURF特征、直方图水平投影特征、直方图垂直投影特征以及梯度特征组合而成的特征，以降低计算复杂度，同时提高提取速度；(2) In the process of document authentication, the authenticity of the document is authenticated by extracting the shallow features of the image in the chip of the ID document and the scanned image of the printed photo on the surface of the document, which no longer relies on manual authentication, which can improve the efficiency of document authentication. and accuracy; and the extracted shallow features are SURF features, histogram horizontal projection features, histogram vertical projection features and gradient features combined to reduce computational complexity and improve extraction speed;
(3)可针对第二代居民身份证、港澳通行证、护照等多种证件完成身份安全验证，能够适用于多种身份安全验证场景；同时，随着系统的应用，数据库中将存储用户的多种证件信息，能够实现对多种身份证件的综合验证；(3) Identity security verification can be completed for various documents such as second-generation resident ID cards, Hong Kong and Macao passes, passports, etc., which can be applied to a variety of identity security verification scenarios; at the same time, with the application of the system, the database will store many users' data. It can realize comprehensive verification of various ID documents;
(4)在获取不到注册图像时，会选取身份证件的芯片内图像和证件表面印刷照片的扫描图像中图像质量较高的图像作为人脸验证的对比图像之一，因而能够保证人脸验证的准确度。(4) When the registered image cannot be obtained, the image with higher image quality in the image in the chip of the ID card and the scanned image of the printed photo on the surface of the certificate will be selected as one of the comparison images for face verification, thus ensuring the accuracy of face verification. Accuracy.
附图说明Description of drawings
图1为本发明提供的基于身份证件和人脸识别的身份安全验证方法的流程图；Fig. 1 is the flow chart of the identity security verification method based on identity document and face recognition provided by the present invention;
图2为本发明实施例提供的基于身份证件和人脸识别的身份安全验证系统的结构框图；FIG. 2 is a structural block diagram of an identity security verification system based on an ID card and face recognition provided by an embodiment of the present invention;
图3为本发明所提供的身份安全验证方法的第一实施例；Fig. 3 is the first embodiment of the identity security verification method provided by the present invention;
图4为本发明所提供的身份安全验证方法的第二实施例。FIG. 4 is a second embodiment of the identity security verification method provided by the present invention.
具体实施方式Detailed ways
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。此外，下面所描述的本发明各个实施方式中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
本发明提供的基于身份证件和人脸识别的身份安全验证方法，如图1所示，包括如下步骤：The identity security verification method based on identity documents and face recognition provided by the present invention, as shown in Figure 1, includes the following steps:
(1)系统注册步骤：获取用户身份证件的证件信息作为注册信息，并采集用户的人脸图像作为注册图像，然后将用注册信息和注册图像存入数据库；身份证件的证件信息包括证件号和持证人的姓名；(1) System registration steps: obtain the certificate information of the user's identity certificate as the registration information, and collect the user's face image as the registration image, and then store the registration information and the registered image into the database; the certificate information of the identity certificate includes the certificate number and the name of the holder;
(2)信息采集步骤：获取用户身份证件的证件信息、芯片内图像以及证件表面印刷照片的扫描图像，并采集实时人脸图像；根据证件信息查询数据库，若查询到相关条目，则从查询结果中提取注册图像；若查询不到相关条目，则在数据库中根据证件信息创建一个新条目，所创建的新条目中注册图像为空；(2) Information collection step: obtain the ID information of the user's ID card, the image in the chip and the scanned image of the printed photo on the surface of the ID card, and collect the real-time face image; query the database according to the ID information, if the relevant item is queried, the query result will be retrieved from the query result Extract the registered image from the database; if no relevant entry is found, a new entry will be created in the database according to the certificate information, and the registered image in the created new entry will be empty;
(3)证件鉴伪步骤：分别提取芯片内图像和扫描图像的浅层特征，并进行一致性判定；若芯片内图像和扫描图像一致，则转入步骤(4)；若芯片内图像和扫描图像不一致，则验证不通过，验证终止；(3) Document authentication step: extract the shallow features of the image in the chip and the scanned image respectively, and determine the consistency; if the image in the chip and the scanned image are consistent, go to step (4); if the image in the chip and the scanned image are consistent If the images are inconsistent, the verification fails and the verification terminates;
(4)图像预处理步骤：若步骤(2)中，获取到注册图像，则对实时人脸图像进行人脸检测和预处理，得到第一对比图像，并对注册图像进行人脸检测和预处理，得到第二对比图像；若步骤(2)中，未获取到注册图像，则对实时人脸图像进行人脸检测和预处理，得到第一对比图像，并对芯片内图像和扫描图像中图像质量较高的图像进行人脸检测和预处理，得到第二对比图像；通过对图像进行人脸检测和预处理，能够提高人脸验证的效率和精确度；(4) Image preprocessing step: if the registered image is obtained in step (2), face detection and preprocessing are performed on the real-time face image to obtain a first contrast image, and face detection and preprocessing are performed on the registered image. processing to obtain a second contrast image; if in step (2), the registration image is not obtained, face detection and preprocessing are performed on the real-time face image to obtain the first contrast image, and the in-chip image and the scanned image are analyzed. The image with higher image quality is subjected to face detection and preprocessing to obtain a second contrast image; by performing face detection and preprocessing on the image, the efficiency and accuracy of face verification can be improved;
(5)人脸验证步骤：分别提取第一对比图像和第二对比图像的深层特征，并计算二者的匹配度；若匹配度高于第一阈值，则转入步骤(6)；否则，验证不通过，验证终止；(5) face verification step: extract the deep features of the first contrast image and the second contrast image respectively, and calculate the matching degree of the two; if the matching degree is higher than the first threshold, then go to step (6); otherwise, If the verification fails, the verification is terminated;
(6)数据库更新步骤：若步骤(2)中，未获取到注册图像，则将实时人脸图像作为注册图像，存入数据库对应的条目中，并转入步骤(7)；若步骤(2)中，获取到注册图像，并且当前验证时间距离上次数据库更新时间的时间间隔超过第二阈值，则将实时人脸图像作为注册图像，更新数据库中对应的条目，并转入步骤(7)；若步骤(2)中，获取到注册图像，并且当前验证时间距离上次数据库更新时间的时间间隔未超过第二阈值，则转入步骤(7)；(6) database update step: if in step (2), the registered image is not obtained, then the real-time face image is taken as the registered image, stored in the corresponding entry of the database, and transferred to step (7); if step (2) ) in, obtain the registered image, and the time interval of the current verification time from the last database update time exceeds the second threshold, then take the real-time face image as the registered image, update the corresponding entry in the database, and go to step (7) If in step (2), obtain the registered image, and the time interval of the current verification time from the last database update time does not exceed the second threshold, then go to step (7);
(7)验证通过，验证结束。(7) The verification is passed, and the verification ends.
结合图1所示的身份安全验证方法，本发明实施例提供了一种用于实现该方法的系统，如图2所示，包括：视频流图像单元、证件信息采集单元、图像预处理单元、人脸验证单元以及数据库管理单元；With reference to the identity security verification method shown in FIG. 1, an embodiment of the present invention provides a system for implementing the method, as shown in FIG. 2, including: a video stream image unit, a certificate information collection unit, an image preprocessing unit, Face verification unit and database management unit;
视频流图像单元用于在系统注册时采集用户正面免冠清晰的人脸图像作为注册图像；视频流图像单元还用于在信息采集时采集实时人脸图像；在本实施例中，视频流图像单元为可实时采集人脸图像的摄像头；The video stream image unit is used to collect a clear face image of the user's front without a hat as a registration image when the system is registered; the video stream image unit is also used to collect real-time face images during information collection; in this embodiment, the video stream image unit It is a camera that can collect face images in real time;
证件信息采集单元用于在系统注册时录入证件信息作为注册信息；证件信息采集单元还用于在信息采集时读取身份证件的证件信息及芯片内图像，并对身份证件进行扫描以获取证件表面印刷照片的扫描图像；在本实施例中，证件信息采集单元包括基于CIS的证件扫描仪和芯片读卡器；基于CIS的图像扫描仪用于扫描证件以获取证件表面印刷照片的扫描图像；芯片读卡器用于读取身份证件的证件信息和芯片内图像；证件信息采集单元还包括支持手动输入的设备，如鼠标、键盘等；The certificate information collection unit is used to enter the certificate information as registration information during system registration; the certificate information collection unit is also used to read the certificate information and the image in the chip of the ID card during information collection, and scan the ID card to obtain the surface of the certificate The scanned image of the printed photo; in this embodiment, the document information collection unit includes a CIS-based document scanner and a chip card reader; the CIS-based image scanner is used to scan the document to obtain a scanned image of the printed photo on the document surface; a chip The card reader is used to read the document information and the image in the chip of the ID document; the document information collection unit also includes devices that support manual input, such as mouse, keyboard, etc.;
图像预处理单元用于在图像预处理时对图像进行人脸检测和预处理，以提高人脸验证的精确度；The image preprocessing unit is used to perform face detection and preprocessing on the image during image preprocessing, so as to improve the accuracy of face verification;
人脸验证单元用于在证件鉴伪时从证件信息采集单元获取芯片内图像和扫描图像，然后分别提取二者的特征并进行一致性判定；人脸验证单元还用于在人脸验证时从图像预处理单元获取第一对比图像和第二对比图像，然后分别提取第一对比图像和第二对比图像的深层特征并计算二者的匹配度；The face verification unit is used to obtain the in-chip image and the scanned image from the document information collection unit when the certificate is authenticated, and then extract the features of the two and perform consistency determination; The image preprocessing unit obtains the first contrast image and the second contrast image, and then extracts the deep features of the first contrast image and the second contrast image respectively and calculates the matching degree of the two;
数据库管理单元用于在系统注册时从证件信息采集单元获取注册信息，并从视频流图像单元获取注册图像，然后将获取到的注册信息和注册图像存入数据库；数据库管理单元还用于在信息采集时从信息采集单元获取证件信息，并根据获取到的证件信息查询数据库；数据库管理单元还用于在数据库更新时从视频流图像单元获取实时人脸图像作为注册图像，并将获取到的注册图像存入或者更新到数据库中。The database management unit is used to obtain registration information from the certificate information collection unit when the system is registered, and obtain the registration image from the video stream image unit, and then store the obtained registration information and registration image in the database; Obtain the certificate information from the information collection unit during collection, and query the database according to the obtained certificate information; the database management unit is also used to obtain the real-time face image from the video stream image unit as the registration image when the database is updated, and use the obtained registration image Images are stored or updated in the database.
人脸验证单元从图像提取的浅层特征为SURF特征、直方图水平投影特征、直方图垂直投影特征以及梯度特征组合而成的特征，以降低计算复杂度，同时提高提取速度；人脸验证单元从图像提取深层特征的方法包括：得到图像的高维卷积特征，再对高维卷积特征进行降维处理，得到适于计算的低维特征；将低维特征作为用于人脸验证的深层特征。The shallow features extracted from the image by the face verification unit are the combination of SURF features, histogram horizontal projection features, histogram vertical projection features and gradient features to reduce computational complexity and improve extraction speed at the same time; face verification unit The method of extracting deep features from an image includes: obtaining high-dimensional convolution features of the image, and then performing dimensionality reduction processing on the high-dimensional convolution features to obtain low-dimensional features suitable for calculation; deep features.
在第一应用场景中，用户已基于第二代居民身份证完成系统注册步骤，因此数据库中已存储用户身份证件的证件信息及注册图像。In the first application scenario, the user has completed the system registration steps based on the second-generation resident ID card, so the certificate information and registration image of the user's ID card have been stored in the database.
在第一应用场景下，如图3所示，本发明所提供的身份安全验证方法的具体包括如下步骤：In the first application scenario, as shown in Figure 3, the identity security verification method provided by the present invention specifically includes the following steps:
(11)信息采集步骤：读取用户第二代居民身份证的证件信息、芯片内图像，并对用户第二代居民身份证进行扫描以获取证件表面印刷照片的扫描图像，同时采集实时人脸图像；根据读取的证件信息查询数据库，提取数据库中存储的注册图像；(11) Information collection step: read the certificate information and the image in the chip of the user's second-generation resident ID card, scan the user's second-generation resident ID card to obtain the scanned image of the printed photo on the surface of the certificate, and collect real-time face at the same time Image; query the database according to the read certificate information, and extract the registered image stored in the database;
(12)证件鉴伪步骤：分别提取芯片内图像和扫描图像的浅层特征，并进行一致性判定；若芯片内图像和扫描图像一致，则转入步骤(13)；若芯片内图像和扫描图像不一致，则验证不通过，验证终止；在本实施例中，一致性判定的方法包括：分别提取芯片内图像和扫描图像的浅层特征；提取的浅层特征为SURF特征、直方图水平投影特征、直方图垂直投影特征以及梯度特征组合而成的特征；以降低计算复杂度，同时提高提取速度；计算所提取的浅层特征之间的欧式距离；若欧式距离大于第三阈值，则判定芯片内图像和扫描图像一致；否则，判定芯片内图像和扫描图像不一致；第三阈值根据经验设定；随着系统投入使用，数据库会动态扩张，系统将得到定期更新，第三阈值将更为精确；(12) Document authentication step: extract the shallow features of the image in the chip and the scanned image respectively, and make a consistency judgment; if the image in the chip and the scanned image are consistent, go to step (13); if the image in the chip and the scanned image are consistent If the images are inconsistent, the verification fails and the verification terminates; in this embodiment, the method for consistency determination includes: extracting the shallow features of the in-chip image and the scanned image respectively; the extracted shallow features are SURF features, histogram horizontal projection feature, histogram vertical projection feature and gradient feature combination; to reduce computational complexity and improve extraction speed; calculate the Euclidean distance between the extracted shallow features; if the Euclidean distance is greater than the third threshold, determine The in-chip image is consistent with the scanned image; otherwise, it is determined that the in-chip image and the scanned image are inconsistent; the third threshold is set based on experience; as the system is put into use, the database will expand dynamically, the system will be updated regularly, and the third threshold will be more accurate;
(13)图像预处理步骤：对实时人脸图像进行人脸检测和预处理，得到第一对比图像，并对查询数据库提取到的注册图像进行人脸检测和预处理，得到第二对比图像；在本实施例中，采用Haar特征和Adaboost分类器进行人脸检测；预处理包括：直方图均衡、高斯滤波去噪以及图像大小归一化；(13) Image preprocessing step: performing face detection and preprocessing on the real-time face image to obtain a first comparison image, and performing face detection and preprocessing on the registered image extracted from the query database to obtain a second comparison image; In this embodiment, the Haar feature and the Adaboost classifier are used for face detection; the preprocessing includes: histogram equalization, Gaussian filter denoising, and image size normalization;
(14)人脸验证步骤：分别提取第一对比图像和第二对比图像的深层特征，并计算二者的余弦距离作为匹配度；若匹配度高于第一阈值，则转入步骤(15)；否则，验证不通过，验证终止；在本实施例中，提取图像深层特征的方法包括：通过深度卷积神经网络得到图像的高维卷积特征，再通过主成分分析算法对高维卷积特征进行降维处理，得到适于计算的低维特征；将低维特征作为用于人脸验证的深层特征；(14) face verification step: extract the deep features of the first contrast image and the second contrast image respectively, and calculate the cosine distance of the two as the matching degree; if the matching degree is higher than the first threshold, then go to step (15) Otherwise, the verification is not passed, and the verification is terminated; In this embodiment, the method for extracting the deep features of the image includes: obtaining the high-dimensional convolution features of the image through a deep convolutional neural network, and then passing the principal component analysis algorithm to the high-dimensional convolution. The features are subjected to dimensionality reduction processing to obtain low-dimensional features suitable for calculation; the low-dimensional features are used as deep features for face verification;
(15)数据库更新步骤：若当前验证时间距离上次数据库更新时间的时间间隔超过第二阈值，则将实时人脸图像作为注册图像，更新数据库中对应的条目，并转入步骤(16)；否则，转入步骤(16)；第二阈值根据经验设定；(15) database update step: if the time interval of the current verification time from the last database update time exceeds the second threshold, then the real-time face image is used as the registered image, the corresponding entry in the update database, and go to step (16); Otherwise, go to step (16); the second threshold is set according to experience;
(16)验证通过，验证结束。(16) The verification is passed, and the verification ends.
在第二应用场景中，用户所持证件为护照，并且尚未完成系统注册步骤，因此数据库中不存在该用户身份证件的证件信息及注册图像。In the second application scenario, the certificate held by the user is a passport, and the system registration steps have not been completed, so the certificate information and registered image of the user's identity certificate do not exist in the database.
在第一应用场景下，如图4所示，本发明所提供的身份安全验证方法的具体包括如下步骤：In the first application scenario, as shown in FIG. 4 , the identity security verification method provided by the present invention specifically includes the following steps:
(21)信息采集步骤：读取用户护照的证件信息、芯片内图像，并对用户护照进行扫描以获取证件表面印刷照片的扫描图像，同时采集实时人脸图像；根据读取的证件信息查询数据库，查询结果为空，在数据库中根据证件信息创建一个新条目，新条目所对应的注册图像为空；(21) Information collection step: read the certificate information and the image in the chip of the user's passport, scan the user's passport to obtain the scanned image of the printed photo on the surface of the certificate, and collect the real-time face image at the same time; query the database according to the read certificate information , the query result is empty, a new entry is created in the database according to the certificate information, and the registered image corresponding to the new entry is empty;
(22)证件鉴伪步骤：分别提取芯片内图像和扫描图像的浅层特征，并进行一致性判定；若芯片内图像和扫描图像一致，则转入步骤(23)；若芯片内图像和扫描图像不一致，则验证不通过，验证终止；在本实施例中，一致性判定的方法包括：分别提取芯片内图像和扫描图像的浅层特征；提取的浅层特征为SURF特征、直方图水平投影特征、直方图垂直投影特征以及梯度特征组合而成的特征；以降低计算复杂度，同时提高提取速度；计算所提取的浅层特征之间的欧式距离；若欧式距离大于第三阈值，则判定芯片内图像和扫描图像一致；否则，判定芯片内图像和扫描图像不一致；第三阈值根据经验设定；随着系统投入使用，数据库会动态扩张，系统将得到定期更新，第三阈值将更为精确；(22) Document authentication step: extract the shallow features of the image in the chip and the scanned image respectively, and determine the consistency; if the image in the chip and the scanned image are consistent, go to step (23); if the image in the chip and the scanned image are consistent If the images are inconsistent, the verification fails and the verification terminates; in this embodiment, the method for consistency determination includes: extracting the shallow features of the in-chip image and the scanned image respectively; the extracted shallow features are SURF features, histogram horizontal projection feature, histogram vertical projection feature and gradient feature combination; to reduce computational complexity and improve extraction speed; calculate the Euclidean distance between the extracted shallow features; if the Euclidean distance is greater than the third threshold, determine The in-chip image is consistent with the scanned image; otherwise, it is determined that the in-chip image and the scanned image are inconsistent; the third threshold is set based on experience; as the system is put into use, the database will expand dynamically, the system will be updated regularly, and the third threshold will be more accurate;
(23)图像预处理步骤：对采集到的人脸图像进行人脸检测和预处理，得到第一对比图像，并对护照的芯片内图像进行人脸检测和预处理，得到第二对比图像；在本实施例中，采用Haar特征和Adaboost分类器进行人脸检测；预处理包括：直方图均衡、高斯滤波去噪以及图像大小归一化；(23) image preprocessing step: performing face detection and preprocessing on the collected face image to obtain a first contrast image, and performing face detection and preprocessing on the in-chip image of the passport to obtain a second contrast image; In this embodiment, the Haar feature and the Adaboost classifier are used for face detection; the preprocessing includes: histogram equalization, Gaussian filter denoising, and image size normalization;
(24)人脸验证步骤：分别提取第一对比图像和第二对比图像的深层特征，并计算二者的余弦距离作为匹配度；若匹配度高于第一阈值，则转入步骤(25)；否则，验证不通过，验证终止；在本实施例中，提取图像深层特征的方法包括：通过深度卷积神经网络得到图像的高维卷积特征，再通过主成分分析算法对高维卷积特征进行降维处理，得到适于计算的低维特征；将低维特征作为用于人脸验证的深层特征；(24) face verification step: extract the deep features of the first contrast image and the second contrast image respectively, and calculate the cosine distance of the two as the matching degree; if the matching degree is higher than the first threshold, then go to step (25) Otherwise, the verification is not passed, and the verification is terminated; In this embodiment, the method for extracting the deep features of the image includes: obtaining the high-dimensional convolution features of the image through a deep convolutional neural network, and then passing the principal component analysis algorithm to the high-dimensional convolution. The features are subjected to dimensionality reduction processing to obtain low-dimensional features suitable for calculation; the low-dimensional features are used as deep features for face verification;
(25)数据库更新步骤：将采集到的实时人脸图像作为注册图像，存入数据库对应的条目中，并转入步骤(26)；(25) database update step: take the collected real-time face image as a registered image, store it in the entry corresponding to the database, and transfer to step (26);
(26)验证通过，验证结束。(26) The verification is passed, and the verification ends.
本领域的技术人员容易理解，以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。Those skilled in the art can easily understand that the above are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention, etc., All should be included within the protection scope of the present invention.
Claims (5)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085256.5ACN108229427B (en) | 2018-01-29 | 2018-01-29 | A kind of identity security verification method and system based on identity document and face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085256.5ACN108229427B (en) | 2018-01-29 | 2018-01-29 | A kind of identity security verification method and system based on identity document and face recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108229427A CN108229427A (en) | 2018-06-29 |
| CN108229427Btrue CN108229427B (en) | 2020-07-10 |
Family
ID=62669090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810085256.5AActiveCN108229427B (en) | 2018-01-29 | 2018-01-29 | A kind of identity security verification method and system based on identity document and face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108229427B (en) |
Families Citing this family (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7073967B2 (en)* | 2018-07-30 | 2022-05-24 | 大日本印刷株式会社 | Certification device, issuing device, issuing system, issuing method, program |
| GB2576521A (en)* | 2018-08-21 | 2020-02-26 | Shufti Pro Ltd | Systems and methods for remotely verifying user identities |
| TWI671685B (en)* | 2018-09-19 | 2019-09-11 | 和碩聯合科技股份有限公司 | Face recognition method and electronic device using the same |
| CN111144164A (en)* | 2018-11-02 | 2020-05-12 | 上海迦叶网络科技有限公司 | Intelligent recognition system based on body scars |
| CN109376725B (en)* | 2018-12-21 | 2022-09-23 | 北京无线电计量测试研究所 | Identity verification method and device based on iris recognition |
| CN109522881A (en)* | 2018-12-25 | 2019-03-26 | 华南理工大学 | A kind of examinee information checking method based on recognition of face |
| CN109711339A (en)* | 2018-12-26 | 2019-05-03 | 天地融科技股份有限公司 | Passport identification method, control device and device |
| CN110011812A (en)* | 2019-04-10 | 2019-07-12 | 民航成都电子技术有限责任公司 | A kind of card method for anti-counterfeit suitable for airport security |
| CN110147740B (en)* | 2019-04-30 | 2021-07-09 | 北京迈格威科技有限公司 | Face recognition method, device, equipment and storage medium |
| CN110164007B (en)* | 2019-05-21 | 2022-02-01 | 一石数字技术成都有限公司 | Access control system based on identity evidence and face image incidence relation |
| CN112016925A (en)* | 2019-05-29 | 2020-12-01 | 福州云豆网络科技有限公司 | Bank account security verification face recognition method based on encryption algorithm |
| CN110414358B (en)* | 2019-06-28 | 2022-11-25 | 平安科技（深圳）有限公司 | Information output method and device based on intelligent face recognition and storage medium |
| CN110555926B (en)* | 2019-07-26 | 2021-01-22 | 华中科技大学 | A kind of access control method and corresponding device based on multi-document identification |
| CN110569718B (en)* | 2019-07-26 | 2021-11-05 | 华中科技大学 | A certificate-based test taker identity verification method and device |
| CN110414454A (en)* | 2019-07-31 | 2019-11-05 | 南充折衍智能光电科技有限公司 | A kind of testimony of a witness unification identifying system based on machine vision |
| CN110705350B (en)* | 2019-08-27 | 2020-08-25 | 阿里巴巴集团控股有限公司 | Document recognition method and device |
| CN111222887B (en)* | 2020-01-08 | 2024-04-16 | 中钞科堡现金处理技术（北京）有限公司 | Intelligent identity recognition system and method and intelligent teller machine |
| CN112598836A (en)* | 2020-12-14 | 2021-04-02 | 天时地理(深圳)智能科技有限公司 | Face recognition comparison system and method based on deep learning |
| CN113094677B (en)* | 2021-06-10 | 2021-10-01 | 天聚地合(苏州)数据股份有限公司 | Identity authentication method, identity authentication device, storage medium and equipment |
| CN113486727A (en)* | 2021-06-11 | 2021-10-08 | 福建数博讯信息科技有限公司 | Face recognition optimization method based on certificate photo as data source |
| CN113672964B (en)* | 2021-08-31 | 2024-01-23 | 大连市公安局 | Certificate checking method based on standard sample feature database |
| CN115147898B (en)* | 2022-06-28 | 2025-06-27 | 浙江宇视科技有限公司 | Person-ID verification method, device, electronic device and storage medium |
| CN115496500B (en)* | 2022-11-22 | 2023-02-10 | 天津郡阳科技发展有限公司 | Information collection method and system based on big data |
| CN116959064B (en)* | 2023-06-25 | 2024-04-26 | 上海腾桥信息技术有限公司 | Certificate verification method and device, computer equipment and storage medium |
| CN117854191A (en)* | 2024-01-10 | 2024-04-09 | 北京中航智信建设工程有限公司 | Airport isolation remote self-help checking system and method |
| CN118570883B (en)* | 2024-07-01 | 2024-12-20 | 北京诺君安信息技术股份有限公司 | Verification method of license verification device |
| CN119814477B (en)* | 2025-03-14 | 2025-05-09 | 北京芯盾时代科技有限公司 | Identity information safety management system and method based on artificial intelligence |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004318409A (en)* | 2003-04-15 | 2004-11-11 | Nec Soft Ltd | Personal authentication system |
| CN102970207A (en)* | 2011-09-01 | 2013-03-13 | 腾讯科技（深圳）有限公司 | Instant communication method, client device and instant communication system |
| CN103279764A (en)* | 2013-06-27 | 2013-09-04 | 苏州福丰科技有限公司 | Real-name network authentication system based on face identification |
| CN103426016A (en)* | 2013-08-14 | 2013-12-04 | 湖北微模式科技发展有限公司 | Method and device for authenticating second-generation identity card |
| CN204155293U (en)* | 2014-09-01 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | A kind of demo plant based on recognition of face and verification system |
| CN104504321A (en)* | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
| CN105005779A (en)* | 2015-08-25 | 2015-10-28 | 湖北文理学院 | Face verification anti-counterfeit recognition method and system thereof based on interactive action |
| CN105160321A (en)* | 2015-09-05 | 2015-12-16 | 深圳市飞思未来云媒体科技有限公司 | Vision-and-wireless-positioning-based mobile terminal identity verification method |
| CN105550638A (en)* | 2015-12-07 | 2016-05-04 | 深圳市安网通信有限公司 | Intelligent self-service identity card customs control system and intelligent self-service identity card customs control method |
| CN106339673A (en)* | 2016-08-19 | 2017-01-18 | 中山大学 | ATM identity authentication method based on face recognition |
| CN106529258A (en)* | 2016-11-30 | 2017-03-22 | 赵云龙 | Security management method and system for mobile equipment |
| CN106650560A (en)* | 2015-11-04 | 2017-05-10 | 上海市公安局刑事侦查总队 | Identity authentication method based on identity card and identity authentication processor and system thereof |
- 2018
- 2018-01-29CNCN201810085256.5Apatent/CN108229427B/enactiveActive
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004318409A (en)* | 2003-04-15 | 2004-11-11 | Nec Soft Ltd | Personal authentication system |
| CN102970207A (en)* | 2011-09-01 | 2013-03-13 | 腾讯科技（深圳）有限公司 | Instant communication method, client device and instant communication system |
| CN103279764A (en)* | 2013-06-27 | 2013-09-04 | 苏州福丰科技有限公司 | Real-name network authentication system based on face identification |
| CN103426016A (en)* | 2013-08-14 | 2013-12-04 | 湖北微模式科技发展有限公司 | Method and device for authenticating second-generation identity card |
| CN204155293U (en)* | 2014-09-01 | 2015-02-11 | 上海智达商投资管理合伙企业(有限合伙) | A kind of demo plant based on recognition of face and verification system |
| CN104504321A (en)* | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
| CN105005779A (en)* | 2015-08-25 | 2015-10-28 | 湖北文理学院 | Face verification anti-counterfeit recognition method and system thereof based on interactive action |
| CN105160321A (en)* | 2015-09-05 | 2015-12-16 | 深圳市飞思未来云媒体科技有限公司 | Vision-and-wireless-positioning-based mobile terminal identity verification method |
| CN106650560A (en)* | 2015-11-04 | 2017-05-10 | 上海市公安局刑事侦查总队 | Identity authentication method based on identity card and identity authentication processor and system thereof |
| CN105550638A (en)* | 2015-12-07 | 2016-05-04 | 深圳市安网通信有限公司 | Intelligent self-service identity card customs control system and intelligent self-service identity card customs control method |
| CN106339673A (en)* | 2016-08-19 | 2017-01-18 | 中山大学 | ATM identity authentication method based on face recognition |
| CN106529258A (en)* | 2016-11-30 | 2017-03-22 | 赵云龙 | Security management method and system for mobile equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108229427A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229427B (en) | A kind of identity security verification method and system based on identity document and face recognition | |
| CN105956578B (en) | A kind of face verification method of identity-based certificate information | |
| Hemalatha | A systematic review on Fingerprint based Biometric Authentication System | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| CN109684987B (en) | Identity verification system and method based on certificate | |
| CN112200136B (en) | Method, device, computer-readable medium, and electronic device for identifying authenticity of certificate | |
| CN100458832C (en) | Palm grain identification method based on direction character | |
| CN110008909B (en) | An AI-based real-name business real-time audit system | |
| CN105243357A (en) | Identity document-based face recognition method and face recognition device | |
| CN105930709A (en) | Method and apparatus for applying human face identification technology to witness testimony consistency check | |
| CN103426016A (en) | Method and device for authenticating second-generation identity card | |
| CN103914686A (en) | Face comparison authentication method and system based on identification photo and collected photo | |
| CN110570549A (en) | An intelligent unlocking method and corresponding device | |
| CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
| Ilankumaran et al. | Multi-biometric authentication system using finger vein and iris in cloud computing | |
| Laadjel et al. | Combining Fisher locality preserving projections and passband DCT for efficient palmprint recognition | |
| CN111460435A (en) | User registration method, verification method and registration device | |
| CN114694161A (en) | A text recognition method, device and storage medium for a specific format certificate | |
| CN112101296A (en) | Face registration method, face verification method, device and system | |
| Karki et al. | Multimodal Biometrics at Feature Level Fusion using Texture | |
| WO2023028947A1 (en) | Palm vein non-contact three-dimensional modeling method and apparatus, and authentication method | |
| Kour et al. | Palmprint recognition system | |
| Ma | Finger vein identification based on 2DPCA | |
| CN112801034A (en) | Finger vein recognition device | |
| Patel et al. | Fingerprint matching using two methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | Address after:430000 room 04, floor 3, building 3, phase III, international enterprise center, No. 1, Guanggu Avenue, Donghu New Technology Development Zone, Wuhan, Hubei 3602 (Wuhan area of free trade zone) Patentee after:Wuhan Huake heding Information Technology Co.,Ltd. Patentee after:HUAZHONG University OF SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE SHENZHEN Address before:210000 No. 99-74, Taizhong Road, Zijin (Pukou) science and technology entrepreneurship special community, Pukou District, Nanjing, Jiangsu Province Patentee before:NANJING HUAKE HEDING INFORMATION TECHNOLOGY Co.,Ltd. Patentee before:HUAZHONG University OF SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE SHENZHEN | |
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address | Address after:214100 Jiangsu Province, Wuxi City, Xinwu District, Xing'an Street, Lihhu Avenue 228, Tianan Smart City, Building 35, 3rd Floor and 4th Floor Patentee after:Wuxi Huake Heding Information Technology Co.,Ltd. Country or region after:China Patentee after:HUAZHONG University OF SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE SHENZHEN Address before:430000 room 04, floor 3, building 3, phase III, international enterprise center, No. 1, Guanggu Avenue, Donghu New Technology Development Zone, Wuhan, Hubei 3602 (Wuhan area of free trade zone) Patentee before:Wuhan Huake heding Information Technology Co.,Ltd. Country or region before:China Patentee before:HUAZHONG University OF SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE SHENZHEN | |
| CP03 | Change of name, title or address |