WO2017173640A1 - Method and apparatus for recognizing individuals based on multi-mode biological recognition information - Google Patents

Abstract

A method, an apparatus and a program for recognizing an individual, the method comprising: determining, from a database, a set of candidates for whom a matching degree regarding a first biological feature is greater than a first critical threshold (A2); determining, from the set of candidates, a candidate for whom a matching degree regarding the first biological feature is greater than a first threshold (A1), to be an individual, and exiting the recognition; if it is impossible for a first determination part to determine a candidate when all the matching degrees regarding the first biological feature for the set of candidates are not greater than the first threshold (A1), then determining, from the set of candidates, a candidate for whom a matching degree regarding a second biological feature is greater than a second critical threshold (B2), to be the individual, and exiting the recognition; and if the set of candidates is empty, determining, from the database, a candidate for whom a matching degree regarding the second biological feature is greater than a second threshold (B1), to be the individual, and exiting the recognition; wherein the first threshold (A1) is greater than the first critical threshold (A2), and the second threshold (B1) is greater than the second critical threshold (B2). The method and apparatus have both a high pass rate and high accuracy of facial recognition and the anti-counterfeiting capability of palm recognition, ensuring accuracy while reducing matching time, and improving recognition efficiency.

Description

Translated fromChinese

一种基于多模式生物识别信息的个人识别方法和装置Personal identification method and device based on multi-mode biometric information技术领域Technical field

本申请涉及生物识别领域，特别地，涉及一种基于多模式生物识别信息的个人识别方法、装置和程序。The present application relates to the field of biometrics, and in particular to a personal identification method, apparatus and program based on multi-modal biometric information.

背景技术Background technique

生物识别技术及相关产品已经广泛地用于用户标识和验证/鉴权，例如考勤机，安防行业的智能锁、门禁机、梯控，出入口控制的通道产品、停车场产品、视频监控产品，都可以引入这种生物特征身份识别方式，达到时间管理、出入口安全控制、人流统计等目的。生物识别技术还可以集成应用于大型软件、项目，具体这些产品可以应用于银行、企事业单位、监狱、家庭、学校等等任何需要出入口控制、安全控制的环境，甚至可以建立集成生物特征的身份证，建立数据库，用于寻找走失、拐卖儿童。Biometric technology and related products have been widely used for user identification and verification/authentication, such as attendance machines, smart locks for security industry, access control, ladder control, access control, access control products, parking products, video surveillance products, This biometric identification method can be introduced to achieve time management, entrance and exit security control, and flow statistics. Biometrics can also be integrated into large-scale software and projects. These products can be applied to any environment that requires access control and security control in banks, enterprises, prisons, homes, schools, etc., and even establish integrated biometric identity. Proof, establish a database for finding lost and abducting children.

传统的生物识别技术中，指纹、面部、指静脉、掌纹、掌静脉、虹膜等作为单一生物特征用于身份识别，相应技术已经较为成熟。但是其通过率与误判率、准确率与通过率一直相互制约，不能完全满足市场需求。此外，由于指纹、面部易于仿制造假，使身份验证的可靠性存在隐患。例如，使用人造的指纹膜、指纹硅胶膜以假冒真通过验证、或者直接使用照片做面部识别等。因此，虹膜、指静脉、掌静脉这些生物特征比较隐蔽、难以仿制的生物识别特征的应用应运而生，但是这3种识别方式的生物特征也相对难以获取，且识别准确率也相对有限，需要用面部这种比较成熟的识别方式予以弥补，提高安全级别。In the traditional biometric identification technology, fingerprints, faces, finger veins, palm prints, palm veins, irises, etc. are used as single biometrics for identification, and the corresponding technologies are relatively mature. However, its pass rate and false positive rate, accuracy rate and pass rate have always been mutually constrained and cannot fully meet market demand. In addition, since the fingerprint and the face are easy to be faked, the reliability of the authentication is hidden. For example, using an artificial fingerprint film, a fingerprint silicone film to verify the fake, or directly using a photo for facial recognition. Therefore, the application of biometric features such as iris, finger vein and palm vein, which are relatively concealed and difficult to imitate, has emerged, but the biometrics of these three recognition methods are relatively difficult to obtain, and the recognition accuracy is relatively limited. Use the more mature recognition method of the face to make up for the safety level.

目前，两个及以上的复合认证方式已经越来越得到用户的认可，如指纹与面部复合识别、指纹与指静脉复合识别，但是，现有的混合识别技术是分别单一识别成功后的组合识别。例如，指纹与指静脉的组合识别，实际的识别过程就是单独指纹识别得到识别结果，单独指静脉识别得到识别结果，之后对指纹和指静脉的识别结果进行不同的逻辑组合(如与、或等)得到最终的识别结果。在这种识别模式下，每一次识别都需要将待识别个人的生物特征数据与相应的数据库中的全部数据进行匹配，当同一个数据库中的待识别用户数目很多时，这种组合识别的模式使得单次验证耗费的时间大幅增加。At present, two or more composite authentication methods have been more and more recognized by users, such as fingerprint and facial composite recognition, fingerprint and finger vein composite recognition, but the existing hybrid recognition technology is combined recognition after successful single recognition. . For example, the combination of fingerprint and finger vein identification, the actual recognition process is the identification of individual fingerprint recognition, the identification of the vein is recognized separately, and then the logical combination of fingerprint and finger vein recognition results.(such as and/or etc.) to get the final recognition result. In this recognition mode, each identification needs to match the biometric data of the individual to be identified with all the data in the corresponding database. When the number of users to be identified in the same database is large, the mode of combined recognition The time it takes to make a single verification has increased dramatically.

因此，亟需提出一种新的基于多模式生物识别信息的复合认证方式来解决上述问题。Therefore, it is urgent to propose a new composite authentication method based on multi-modal biometric information to solve the above problems.

发明内容Summary of the invention

本发明提供一种基于多模式生物识别信息的个人识别方法、装置和程序。The present invention provides a personal identification method, apparatus and program based on multi-modal biometric information.

在一个实施例中公开了一种用于识别个人的装置，包括：In one embodiment, an apparatus for identifying an individual is disclosed, comprising:

第一识别部分，用于将数据库中关于第一生物特征的匹配度高于第一临界阈值的候选确定为候选合集；第一判断部分，用于将所述候选合集中关于第一生物特征的匹配度高于第一阈值的候选确定为该个人，并退出识别；第二判断部分，用于当所述候选合集中关于第一生物特征的匹配度都不高于第一阈值，第一判断部分无法确定候选时，将所述候选合集中关于第二生物特征的匹配度高于第二临界阈值的候选确认为该个人，并退出识别；以及第二识别部分，用于当所述候选合集为空时，将数据库中关于第二生物特征的匹配度高于第二阈值的候选确定为该个人，并退出识别；其中，第一阈值高于第一临界阈值，第二阈值高于第二临界阈值。a first identifying part, configured to determine a candidate in the database that the matching degree of the first biometric is higher than the first critical threshold as a candidate collection; the first determining part is configured to use the candidate collection as to the first biometric The candidate whose matching degree is higher than the first threshold is determined as the individual, and exits the identification; the second determining part is configured to: when the matching degree of the candidate bio-features with respect to the first biometric feature is not higher than the first threshold, the first judgment When the candidate cannot be determined in part, the candidate of the candidate collection with respect to the second biometric with the matching degree higher than the second critical threshold is confirmed as the individual, and the identification is exited; and the second identifying portion is used when the candidate is collected When it is empty, the candidate in the database that the matching degree of the second biometric is higher than the second threshold is determined as the individual, and the identification is exited; wherein, the first threshold is higher than the first critical threshold, and the second threshold is higher than the second Critical threshold.

根据本发明的其中一个方面，所述第一生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。According to one aspect of the invention, the first biometric feature is one of a face, a palm, a fingerprint, a finger vessel, and an iris.

根据本发明的其中一个方面，所述第一生物特征为面部图像。According to one aspect of the invention, the first biometric is a facial image.

根据本发明的其中一个方面，所述装置还包括：面部特征采集部分，用于获取待识别个人的面部图像。According to an aspect of the invention, the apparatus further includes: a facial feature collecting portion for acquiring a facial image of the individual to be identified.

根据本发明的其中一个方面，所述第一识别部分包括：面部图像处理单元，用于基于采集到的面部图像生成面部特征；以及基于面部的匹配单元，用于对所述面部特征和存储在第一数据库中的多个候选面部特征进行比对，确定所述候选合集。According to an aspect of the invention, the first identification portion includes: a face image processing unit configured to generate a facial feature based on the collected face image; and a face-based matching unit configured to store and store the facial feature Multiple candidate faces in the first databaseThe features are compared and the candidate collection is determined.

根据本发明的其中一个方面，所述第二生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。According to one aspect of the invention, the second biometric is one of a face, a palm, a fingerprint, a finger vessel, and an iris.

根据本发明的其中一个方面，所述第二生物特征为手掌。According to one aspect of the invention, the second biometric is a palm.

根据本发明的其中一个方面，所述第二生物特征为手掌掌纹信息、手掌血管信息、手掌形状信息中的一种或几种的组合。According to one aspect of the invention, the second biometric is a combination of one or more of palm palm print information, palm blood vessel information, and palm shape information.

根据本发明的其中一个方面，所述装置还包括：手掌图像采集部分，用于采集待识别个人的手掌图像。According to one aspect of the invention, the apparatus further includes: a palm image acquisition portion for collecting a palm image of the individual to be identified.

根据本发明的其中一个方面，所述第二识别部分包括：According to one aspect of the invention, the second identifying portion comprises:

手掌图像处理单元，用于基于采集到的手掌图像生成手掌特征图像；以及a palm image processing unit for generating a palm feature image based on the acquired palm image;

基于手掌的匹配单元，用于对所述手掌特征图像和存储在第二数据库中的多个候选手掌特征图像中的每一个进行比对，根据比对结果确定该个人。The palm-based matching unit is configured to compare each of the palm feature image and the plurality of candidate palm feature images stored in the second database, and determine the individual according to the comparison result.

根据本发明的其中一个方面，所述第二判断部分包括：According to an aspect of the invention, the second determining portion comprises:

手掌图像处理单元，用于基于采集到的手掌图像生成手掌特征图像；以及a palm image processing unit for generating a palm feature image based on the acquired palm image;

基于手掌的匹配单元，用于对所述手掌特征图像和所述候选合集中的候选所对应的手掌特征图像中进行比对，根据比对结果确定该个人。The palm-based matching unit is configured to compare the palm feature image and the palm feature image corresponding to the candidate of the candidate collection, and determine the individual according to the comparison result.

相应的，本发明还提供了一种识别个人的方法，包括：Correspondingly, the present invention also provides a method for identifying an individual, comprising:

将数据库中关于第一生物特征的匹配度高于第一临界阈值的候选确定为所述候选合集；Determining, in the database, candidates for matching the first biometric with the first critical threshold as the candidate collection;

将所述候选合集中关于第一生物特征的匹配度高于第一阈值(A1)的候选确定为该个人，并退出识别；Determining, in the candidate collection, that the degree of matching of the first biometric is higher than the first threshold (A1) is the individual, and exiting the identification;

当第一判断部分无法确定候选时，将所述候选合集中关于第二生物特征的匹配度高于第二临界阈值的候选确认为该个人，并退出识别；以及When the first determining portion cannot determine the candidate, the candidate of the candidate collection with respect to the second biometric with the matching degree higher than the second critical threshold is confirmed as the individual, and exits the identification;

当所述候选合集为空时，将数据库中关于第二生物特征的匹配度高于第二阈值的候选确定为该个人，并退出识别；When the candidate collection is empty, the candidate in the database that the matching degree of the second biometric is higher than the second threshold is determined as the individual, and the identification is exited;

其中，第一阈值高于第一临界阈值，第二阈值高于第二临界阈值。The first threshold is higher than the first critical threshold, and the second threshold is higher than the second critical threshold.

根据本发明的其中一个方面，所述第一生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。According to one aspect of the invention, the first biometric feature is one of a face, a palm, a fingerprint, a finger vessel, and an iris.

根据本发明的其中一个方面，所述第一生物特征为面部特征。According to one aspect of the invention, the first biometric is a facial feature.

根据本发明的其中一个方面，基于个人的面部特征确定所述候选合集的方法包括：According to one aspect of the present invention, a method for determining the candidate collection based on facial features of an individual includes:

接收到从个人获取的待识别面部图像；Receiving a facial image to be recognized obtained from an individual;

基于待识别面部图像生成待识别面部特征；Generating a facial feature to be recognized based on the facial image to be recognized;

将待识别面部特征与存储在数据库中的多个候选面部特征的每一个进行比对，从而得到候选面部特征的每一个与待识别面部特征的匹配度；Comparing the facial features to be identified with each of the plurality of candidate facial features stored in the database, thereby obtaining a matching degree of each of the candidate facial features and the facial features to be recognized;

基于所述匹配度选择一个或多个匹配候选。One or more matching candidates are selected based on the matching degree.

根据本发明的其中一个方面，所述第二生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。According to one aspect of the invention, the second biometric is one of a face, a palm, a fingerprint, a finger vessel, and an iris.

根据本发明的其中一个方面，所述第二生物特征为手掌。According to one aspect of the invention, the second biometric is a palm.

根据本发明的其中一个方面，所述第二生物特征为手掌掌纹信息、手掌血管信息、手掌形状信息中的一种或几种的组合。According to one aspect of the invention, the second biometric is a combination of one or more of palm palm print information, palm blood vessel information, and palm shape information.

根据本发明的其中一个方面，基于个人的手掌特征确定该个人的方法包括：According to one aspect of the invention, a method for determining the individual based on an individual's palm characteristics includes:

接收到从个人获取的待识别手掌图像；Receiving an image of the palm to be recognized obtained from the individual;

基于待识别手掌图像生成待识别手掌特征图像；Generating a palm feature image to be recognized based on the palm image to be recognized;

将待识别手掌特征图像与所述候选合集中的候选对应的手掌特征的每一个进行比对，得到相应的匹配度；Comparing each of the palm feature images corresponding to the candidate of the candidate collection to the palm feature image to be recognized, and obtaining a corresponding matching degree;

基于所述匹配度确定该个人。The individual is determined based on the matching degree.

本发明提供了一种新的基于多种生物信息的个人识别方法和装置，具体的，提供了一种基于面部图像和手掌图像的融合识别方法，同时具有面部识别所具有的高通过率以及高精确度的特点以及手掌识别所具有的防伪能力，有效解决了现有技术中单一生物信息识别的缺陷。The invention provides a new personal identification method and device based on multiple biological information, in particular, a fusion recognition method based on facial image and palm image, and has high pass rate and high face recognition. The characteristics of accuracy and the anti-counterfeiting ability of palm recognition effectively solve the defects of single bio-information recognition in the prior art.

本发明还提供了一种新的基于多种生物信息的识别方法，首先通过第一生物特征确定候选合集，再通过第二生物特征从所述候选合集中确定待识别个人的身份。相比于现有技术中根据第一生物特征确定第一候选合集，根据第二生物特征确认第二候选合集，再将第一、第二候选合集进行与、或等逻辑运算得到待识别个人的方法，本发明有效的在确保识别准确度的同时减少了两次匹配过程中的匹配数量，提高了识别效率。The invention also provides a new identification method based on multiple biological information, firstlyThe candidate set is determined by the first biometric, and the identity of the individual to be identified is determined from the candidate set by the second biometric. Compared with determining the first candidate collection according to the first biometric in the prior art, confirming the second candidate collection according to the second biometric, and then performing the logical operation of the first and second candidate collections to obtain the individual to be identified. The method effectively reduces the number of matches in the two matching processes while improving the recognition accuracy, and improves the recognition efficiency.

此外，由于面部、手掌图像采集均是通过非接触实现采集与比对，图像获取的过程更加清洁方便，用户体验好。In addition, since the image acquisition of the face and the palm is achieved through non-contact acquisition and comparison, the process of image acquisition is more clean and convenient, and the user experience is good.

本领域普通技术人员将了解，虽然下面的详细说明将参考图示实施例、附图进行，但本申请并不仅限于这些实施例。而是，本申请的范围是广泛的，且意在仅通过后附的权利要求限定本申请的范围。Those skilled in the art will appreciate that although the following detailed description is made with reference to the illustrated embodiments and drawings, the application is not limited to these embodiments. Rather, the scope of the present application is broadly defined and the scope of the application is defined by the appended claims.

附图说明DRAWINGS

通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：Other features, objects, and advantages of the present application will become more apparent from the detailed description of the accompanying drawings.

图1为本发明中一个实施例中基于多种生物信息的个人识别方法流程图；1 is a flow chart of a personal identification method based on multiple biological information in an embodiment of the present invention;

图2为本发明中一个实施例中基于多种生物信息的个人识别装置的示意图；2 is a schematic diagram of a personal identification device based on multiple biological information in an embodiment of the present invention;

图3描绘了其上可以实施本教导的通用计算机架构。FIG. 3 depicts a general purpose computer architecture upon which the present teachings may be implemented.

附图中相同或相似的附图标记代表相同或相似的部件。The same or similar reference numerals in the drawings denote the same or similar components.

具体实施方式detailed description

在下面详细的描述中，作为示例列举出了多个特定的细节从而提供对于相关教导的全面理解。然而，对于本领域的技术人员来说明显的是本教导可以无需这些细节或者连同附加特征来实践。在其他的例子中，在相对高的层面上无有细节地对公知的方法、进程、系统、组件和/或电路进行描述，从而避免对本教导的方面造成不必要的模糊化。In the following detailed description, numerous specific details are set forth It will be apparent to those skilled in the art, however, that the present teachings may be practiced without these details or additional features. In other instances, well-known methods, processes, systems, components, and/or circuits are described in detail at a relatively high level to avoid unnecessary obscuring aspects of the present teachings.

在更加详细地讨论示例性实施例之前应当提到的是，一些示例性实施例被描述成作为流程图描绘的处理或方法。虽然流程图将各项操作描述成顺序的处理，但是其中的许多操作可以被并行地、并发地或者同时实施。此外，各项操作的顺序可以被重新安排。当其操作完成时所述处理可以被终止，但是还可以具有未包括在附图中的附加步骤。所述处理可以对应于方法、函数、规程、子例程、子程序等等。Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as a process or method depicted as a flowchart. Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. In addition, the order of operations can be rearranged. The process may be terminated when its operation is completed, but may also have additional steps not included in the figures. The processing may correspond to methods, functions, procedures, subroutines, subroutines, and the like.

后面所讨论的方法(其中一些通过流程图示出)可以通过硬件、软件、固件、中间件、微代码、硬件描述语言或者其任意组合来实施。当用软件、固件、中间件或微代码来实施时，用以实施必要任务的程序代码或代码段可以被存储在机器或计算机可读介质(比如存储介质)中。(一个或多个)处理器可以实施必要的任务。The methods discussed below, some of which are illustrated by flowcharts, can be implemented in hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to carry out the necessary tasks can be stored in a machine or computer readable medium, such as a storage medium. The processor(s) can perform the necessary tasks.

这里所公开的具体结构和功能细节仅仅是代表性的，并且是用于描述本申请的示例性实施例的目的。但是本申请可以通过许多替换形式来具体实现，并且不应当被解释成仅仅受限于这里所阐述的实施例。The specific structural and functional details disclosed herein are merely representative and are for the purpose of describing exemplary embodiments of the present application. The present application, however, may be embodied in many alternative forms and should not be construed as being limited to the embodiments set forth herein.

应当理解的是，虽然在这里可能使用了术语“第一”、“第二”等等来描述各个单元，但是这些单元不应当受这些术语限制。使用这些术语仅仅是为了将一个单元与另一个单元进行区分。举例来说，在不背离示例性实施例的范围的情况下，第一单元可以被称为第二单元，并且类似地第二单元可以被称为第一单元。这里所使用的术语“和/或”包括其中一个或更多所列出的相关联项目的任意和所有组合。It should be understood that although the terms "first," "second," etc. may be used herein to describe the various elements, these elements should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, a first unit could be termed a second unit, and similarly a second unit could be termed a first unit, without departing from the scope of the exemplary embodiments. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items.

这里所使用的术语仅仅是为了描述具体实施例而不意图限制示例性实施例。除非上下文明确地另有所指，否则这里所使用的单数形式“一个”、“一项”还意图包括复数。还应当理解的是，这里所使用的术语“包括”和/或“包含”规定所陈述的特征、整数、步骤、操作、单元和/或组件的存在，而不排除存在或添加一个或更多其他特征、整数、步骤、操作、单元、组件和/或其组合。The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It is also to be understood that the terms "comprising" and """ Other features, integers, steps, operations, units, components, and/or combinations thereof.

还应当提到的是，在一些替换实现方式中，所提到的功能/动作可以按照不同于附图中标示的顺序发生。举例来说，取决于所涉及的功能/动作，相继示出的两幅图实际上可以基本上同时执行或者有时可以按照相反的顺序来执行。It should also be noted that, in some alternative implementations, the functions/acts noted may occur in a different order than that illustrated in the drawings. For example, two figures shown in succession may in fact be executed substantially concurrently or sometimes in reverse order, depending on the function/acts involved.To execute.

下面将结合附图对本发明的实施例进行详细描述。Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

如图1所示，本发明提供了一种基于多种生物信息的个人识别装置，该装置包括：第一识别部分、第一判断部分、第二判断部分以及第二识别部分。相应的，本发明还提供了识别个人的方法，包括：As shown in FIG. 1, the present invention provides a personal identification device based on a plurality of biological information, the device comprising: a first identification portion, a first determination portion, a second determination portion, and a second identification portion. Correspondingly, the present invention also provides a method for identifying an individual, comprising:

将数据库中关于第一生物特征的匹配度高于第一临界阈值A2的候选确定为候选合集；Determining, in the database, candidates for matching the first biometric with the first critical threshold A2 as a candidate collection;

将候选合集中关于第一生物特征的匹配度高于第一阈值A1的候选确定为该个人，并退出识别；Determining, in the candidate collection, that the degree of matching of the first biometric is higher than the first threshold A1 is the individual, and exiting the identification;

当所述候选合集中关于第一生物特征的匹配度都不高于第一阈值A1时第一判断部分无法确定候选，则将候选合集中关于第二生物特征的匹配度高于第二临界阈值B2的候选确认为该个人，并退出识别；以及When the matching degree of the candidate biometrics is not higher than the first threshold A1, the first judging portion cannot determine the candidate, and the matching degree of the candidate folio with respect to the second biometric is higher than the second critical threshold. The candidate for B2 is confirmed as the individual and exits the identification;

当候选合集为空时，将数据库中关于第二生物特征的匹配度高于第二阈值B1的候选确定为该个人，并退出识别；When the candidate collection is empty, the candidate in the database that the matching degree of the second biometric is higher than the second threshold B1 is determined as the individual, and the identification is exited;

其中，第一阈值A1高于第一临界阈值A2，第二阈值B1高于第二临界阈值B2。The first threshold A1 is higher than the first critical threshold A2, and the second threshold B1 is higher than the second critical threshold B2.

下面将结合具体的应用实施例对以上各部分及其工作流程进行说明。The above various parts and their workflows will be described below in conjunction with specific application embodiments.

需要说明的是，本发明中共涉及四个阈值，分别为关于第一生物特征的第一阈值A1和第一临界阈值A2，以及关于第二生物特征的第二阈值B1和第二临界阈值B2。其中，所述阈值为待识别个人与数据库中的候选关于第一或第二生物特征的匹配度，假设匹配度的范围为[0，100]，匹配度的数值越大，则说明待识别个人与候选为同一个人的概率越高。以第一阈值A1和第一临界阈值A2为例进行说明。第一阈值A1的确定原则为：可以将匹配度高于A1的候选直接确定为待识别个人，在这种条件下，第一阈值A1通常是一个比较高的数值，以最大值为100为例，第一阈值A1的值通常大于90。第一临界阈值A2的确定原则为：匹配度高于A2的候选有较大的几率为该识别个人，但有一定的几率存在误差，以最大值为100为例，第一阈值A1的值通常大于70。明显的，第一阈值A1确定的候选准确率高，相应的通过率低，而第一临界阈值A2确定的候选准确率低，相应的通过率较高。同样的，第二阈值B1和第二临界阈值B2的大小和确定原则也满足上述规律。在实际应用的，所述四个阈值的值都可以通过根据需要自主设定，例如，第一阈值A1的值可以为90～98中的任意一个自然数，如92、95、96以及93.5、94.5等，第一临界阈值A2的值可以为60～85中的任意一个自然数，如65、75、70以及63.5、74.5等。以上数据只能解释为对本发明的说明，而不能解释为对本发明的限制。It should be noted that the present invention relates to four thresholds, namely a first threshold A1 and a first critical threshold A2 regarding the first biometric, and a second threshold B1 and a second critical threshold B2 regarding the second biometric. The threshold is a degree of matching between the candidate to be identified and the candidate in the database regarding the first or second biometric, and the range of the matching degree is assumed to be [0, 100], and the greater the matching degree, the individual to be identified The higher the probability of being the same person as the candidate. The first threshold A1 and the first critical threshold A2 are taken as an example for description. The first threshold A1 is determined according to the principle that the candidate whose matching degree is higher than A1 can be directly determined as the individual to be identified. Under this condition, the first threshold A1 is usually a relatively high value, and the maximum value is 100. The value of the first threshold A1 is typically greater than 90. The first critical threshold A2 is determined according to the principle that the candidate whose matching degree is higher than A2 has a larger probability of the identified individual, but there is a certain probability that there is an error. The maximum value is 100, and the value of the first threshold A1 is usually More than 70. Obviously, the first thresholdThe candidate accuracy rate determined by A1 is high, and the corresponding pass rate is low, and the candidate accuracy rate determined by the first critical threshold A2 is low, and the corresponding pass rate is high. Similarly, the magnitude and determination principle of the second threshold B1 and the second critical threshold B2 also satisfy the above rule. In practice, the values of the four thresholds can be set autonomously according to requirements. For example, the value of the first threshold A1 can be any natural number from 90 to 98, such as 92, 95, 96, and 93.5, 94.5. Etc., the value of the first critical threshold A2 may be any one of 60 to 85, such as 65, 75, 70, and 63.5, 74.5, and the like. The above data is only to be construed as illustrative of the invention and is not to be construed as limiting.

所述第一识别部分用于将数据库中关于第一生物特征的匹配度高于第一临界阈值A2的候选确定为候选合集。其中，所述数据库中存储了一定数量的个人身份信息以及该个人的第一和\或第二生物特征，当待识别个人的第一和\或第二生物特征与数据库中存储的某个第一和\或第二特征相匹配时，则判定所述待识别个人的身份为数据库中与该待识别个人相匹配的生物特征所对应的个人的身份。若匹配失败，则说明数据库中不存在所述待识别个人的信息。数据库中存储的个人信息可以通过采集设备和控制系统进行更新，例如增加或删除用户信息，对用户信息对应的生物特征进行更新等。对数据库中的数据进行管理和编辑的方法为本领域中的常用技术，在此不再赘述。The first identifying portion is configured to determine a candidate in the database that the matching degree of the first biometric is higher than the first critical threshold A2 as a candidate collection. Wherein the database stores a certain amount of personally identifiable information and the first and/or second biometrics of the individual, when the first and/or second biometrics of the individual to be identified and a certain number stored in the database When the first and/or the second feature match, the identity of the person to be identified is determined to be the identity of the individual corresponding to the biometric in the database that matches the person to be identified. If the match fails, it means that the information of the person to be identified does not exist in the database. The personal information stored in the database can be updated by the collection device and the control system, such as adding or deleting user information, updating biometrics corresponding to the user information, and the like. The method for managing and editing data in the database is a common technique in the art, and will not be described herein.

所述第一生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。例如，在本发明实施例中，所述第一生物特征为面部图像。如前所述，在本实施例中，设定所述第一临界阈值A2的值为70。所述第一识别部分的目的在于将所有可能是待识别个人的候选从数据库中筛选出来形成候选合集，以缩小下一次匹配识别过程中的样本数量，从而缩短匹配时间。其中，所述数据库中预先存储有不同用户的身份信息和第一、第二生物特征信息。The first biometric feature is one of a face, a palm, a fingerprint, a finger blood vessel, and an iris. For example, in an embodiment of the invention, the first biometric is a facial image. As described above, in the present embodiment, the value of the first critical threshold A2 is set to 70. The purpose of the first identifying part is to filter all candidates who may be individuals to be identified from the database to form a candidate collection to reduce the number of samples in the next matching identification process, thereby shortening the matching time. The identity information of the different users and the first and second biometric information are pre-stored in the database.

具体的，所述待识别个人的面部图像通过面部特征采集部分获取。图2示出了本发明一个实施例中基于多种生物信息的个人识别装置的示意图，如图所示，该装置包括面部图像采集单元210，用于采集待识别个人的面部图像，具体的，该单元包括第一红外灯和第一红外摄像头，通过红外摄像头采集被待识别对象的面部反射的红外线生成待识别对象的面部图像。相应的，当所述第一生物特征为手掌、指纹、手指血管、虹膜时，所述采集单元的结构也相应的发生改变以获取相应的生物特征。具体的采集原理为本领域的公知常识，在此不再赘述。Specifically, the facial image of the person to be identified is acquired by the facial feature collecting portion. 2 is a schematic diagram of a personal identification device based on a plurality of biological information in an embodiment of the present invention. As shown, the device includes a facialimage capturing unit 210 for collecting facial images of an individual to be identified, specifically, The unit includes a first infrared light and a first infrared camera, through the infraredThe camera collects infrared rays reflected by the face of the object to be identified to generate a face image of the object to be recognized. Correspondingly, when the first biometric is a palm, a fingerprint, a finger blood vessel, and an iris, the structure of the collecting unit is correspondingly changed to acquire a corresponding biometric. The specific collection principle is common knowledge in the art and will not be described here.

具体的，所述第一识别部分包括：面部图像处理单元，用于基于采集到的面部图像生成面部特征；以及基于面部的匹配单元，用于对所述面部特征和存储在第一数据库中的多个候选面部特征进行比对，得到每一个候选与待识别个人的面部图像的匹配度，并将匹配度大于第一临界阈值A2，即70，的候选筛选出来，形成候选合集以缩小下一次匹配识别过程中的样本数量，从而缩短匹配时间。例如，在一个实施例中，针对待识别个人X，第一识别部分筛选出的候选合集中包括匹配度为75的候选X1，匹配度为80的候选X2，匹配度为96的候选X3。Specifically, the first identifying portion includes: a face image processing unit configured to generate a facial feature based on the collected facial image; and a face-based matching unit configured to store the facial feature and the first facial feature in the first database Aligning a plurality of candidate facial features, obtaining a matching degree of each candidate and a facial image of the individual to be identified, and screening the candidates whose matching degree is greater than the first critical threshold A2, that is, 70, to form a candidate collection to narrow the next time Match the number of samples in the recognition process to shorten the matching time. For example, in one embodiment, for the individual X to be identified, the candidate collection selected by the first identification portion includes a candidate X1 with a matching degree of 75, a candidate X2 with a matching degree of 80, and a candidate X3 with a matching degree of 96.

接下来，由第一判断部分对候选合集中的候选进行匹配判断，将候选合集中关于第一生物特征的匹配度高于第一阈值A1的候选确定为该个人，并退出识别。如前所述，在本实施例中，设定所述第一阈值A1的值为95。匹配度大于第一阈值的候选可以直接确认为该个人，而不用再进行关于第二生物特征的判断，在保证准确性的同时有效节省了时间。例如，在关于待识别个人X的实施例中，第一判断部分判断出，候选合集中存在匹配度大于95的候选X3，因此将X3直接判断为该待识别个人，识别完成。Next, the candidate of the candidate collection is judged by the first determination part, and the candidate of the candidate collection with respect to the first biometric with the matching degree higher than the first threshold A1 is determined as the individual, and the recognition is exited. As described above, in the present embodiment, the value of the first threshold A1 is set to 95. A candidate whose matching degree is greater than the first threshold may be directly confirmed as the individual without further judgment on the second biometric, which effectively saves time while ensuring accuracy. For example, in the embodiment regarding the individual X to be identified, the first judging portion judges that there is a candidate X3 whose matching degree is greater than 95 in the candidate collection, and thus X3 is directly judged as the individual to be identified, and the recognition is completed.

在其他实施例中，若所述候选合集中不存在匹配度大于第一阈值A1的候选，即无法通过第一判断部分确定待识别个人的身份时，由第二判断部分将候选合集中关于第二生物特征的匹配度高于第二临界阈值B2的候选确认为该个人，并退出识别。In other embodiments, if there is no candidate in the candidate collection that has a matching degree greater than the first threshold A1, that is, the identity of the to-be-identified person cannot be determined by the first determining portion, the second determining portion selects the candidate collection. The candidate whose matching degree of the second biometric is higher than the second critical threshold B2 is confirmed as the individual and exits the identification.

所述第二生物特征为面部、手掌、指纹、手指血管、虹膜中的一种，其中，所述第二生物特征与所述第一生物特征为不同的生物特征。例如，在本发明实施例中，所述第一生物特征为面部图像，则所述第二生物特征可以为手掌、指纹、手指血管、虹膜中的一种，优选的，在本实施例中，所述第二生物特征为手掌图像，优选的，为了进一步具有防伪功能，所述第二生物特征为手掌血管图像。The second biometric is one of a face, a palm, a fingerprint, a finger blood vessel, and an iris, wherein the second biometric is different from the first biometric. For example, in the embodiment of the present invention, the first biometric feature is a facial image, and the second biometric feature may be one of a palm, a fingerprint, a finger blood vessel, and an iris. Preferably, in the embodiment, The second biometric is a palm image, preferably, for further protectionA pseudo-function, the second biometric is a palm blood vessel image.

所述第二判断部分包括：手掌图像处理单元，用于基于采集到的手掌图像生成手掌特征图像；以及基于手掌的匹配单元，用于对所述手掌特征图像和存储在第二数据库中的多个候选手掌特征图像中的每一个进行比对，根据比对结果确定该个人。在其他实施例中，也可以采用虹膜作为第二生物特征，相关的采集方法和装置为本领域的常用技术手段，在此不再赘述。The second determining portion includes: a palm image processing unit configured to generate a palm feature image based on the collected palm image; and a palm-based matching unit for the palm feature image and the plurality of stored in the second database Each of the candidate palm feature images is compared, and the individual is determined based on the comparison result. In other embodiments, the iris can also be used as the second biological feature. The related collection methods and devices are common technical means in the art, and are not described herein again.

如前所述，在本实施例中，设定所述第二临界阈值B2的值为70。由于候选合集中的候选与待识别个人关于面部图像的匹配度大于第一临界阈值A2，因此在通过手掌血管图像判断待识别个人的身份时，只需其匹配度大于第二临界阈值，即可将该候选确认为所述待识别个人。以前文中的候选人X为例，第一识别部分筛选出的候选合集中包括匹配度为75的候选X1，匹配度为80的候选X2，匹配度为87的候选X4，由于候选合集中不存在匹配度大于95的候选，因此第一判断部分识别失败。As described above, in the present embodiment, the value of the second critical threshold B2 is set to 70. Since the matching degree between the candidate of the candidate collection and the person to be identified is greater than the first critical threshold A2, when the identity of the individual to be identified is determined by the palm blood vessel image, only the matching degree is greater than the second critical threshold. The candidate is confirmed as the person to be identified. The candidate X in the previous example is taken as an example. The candidate collection selected by the first identification part includes the candidate X1 with the matching degree of 75, the candidate X2 with the matching degree of 80, and the candidate X4 with the matching degree of 87, because the candidate collection does not exist. The candidate whose matching degree is greater than 95, therefore the first judgment part identification fails.

接下来，由第二判断部分将待识别个人的手掌血管图像分别与候选X1、X2、X4的手掌血管图像进行对比，得到候选X1与待识别个人关于手掌血管图像的匹配度为3，候选X2与待识别个人关于手掌血管图像的匹配度为10，候选X4与待识别个人关于手掌血管图像的匹配度为78，则可判断候选X4为所述待识别个人。在此实施例中，通过第二生物特征确定待识别个人的身份时，仅需对候选合集中的三个候选与待识别个人进行匹配，而无需对数据库中的所有候选均进行一一匹配，有效节约了匹配时间，且不影响识别的准确性。Next, the palm blood vessel image of the individual to be identified is compared with the palm blood vessel images of the candidates X1, X2, and X4 by the second determining portion, and the matching degree between the candidate X1 and the person to be identified regarding the palm blood vessel image is obtained as 3, candidate X2. The matching degree of the palm blood vessel image with the person to be identified is 10, and the matching degree of the candidate X4 with the person to be identified regarding the palm blood vessel image is 78, and then the candidate X4 can be judged as the individual to be identified. In this embodiment, when determining the identity of the person to be identified by the second biometric, only three candidates in the candidate collection need to be matched with the individual to be identified, without one-to-one matching for all candidates in the database. The matching time is effectively saved without affecting the accuracy of the recognition.

在其他实施例中，若所述候选合集为空，即不存在关于第一生物特征与待识别个人匹配的候选时，由第二识别部分将数据库中关于第二生物特征的匹配度高于第二阈值B1的候选确定为该个人，并退出识别。在实际中的情况为，对于待识别个人Y，数据库中不存在关于面部图像的匹配度大于70的候选，此时，通过第二识别部分将候选Y的手掌图像与数据库中的全部候选的手掌图像进行匹配，并将匹配度高于第二阈值B1，即95，的候选确认为该个人。若不存在匹配度高于第二阈值B1的候选，则说明数据库中不存在所述待识别个人的信息，识别失败。In other embodiments, if the candidate collection is empty, that is, there is no candidate for matching the first biometric with the individual to be identified, the matching degree of the second biometric in the database is higher by the second identification portion. The candidate for the second threshold B1 is determined to be the individual and exits the identification. In practice, in the case of the person Y to be identified, there is no candidate in the database for the matching degree of the face image greater than 70. At this time, the palm image of the candidate Y and the palm of all candidates in the database are obtained by the second identifying portion. The image is matched, and the candidate whose matching degree is higher than the second threshold B1, that is, 95, is confirmed as the individual. If there is no matching degree higher than the second threshold B1The candidate indicates that the information of the person to be identified does not exist in the database, and the identification fails.

本发明提供了一种新的基于多种生物信息的个人识别方法和装置，具体的，提供了一种基于面部图像和手掌图像的融合识别方法，同时具有面部识别所具有的高通过率以及高精确度的特点以及手掌识别所具有的防伪能力，有效解决了现有技术中单一生物信息识别的缺陷。The invention provides a new personal identification method and device based on multiple biological information, in particular, a fusion recognition method based on facial image and palm image, and has high pass rate and high face recognition. The characteristics of accuracy and the anti-counterfeiting ability of palm recognition effectively solve the defects of single bio-information recognition in the prior art.

本发明还提供了一种新的基于多种生物信息的识别方法，首先通过第一生物特征确定候选合集，再通过第二生物特征从所述候选合集中确定待识别个人的身份。相比于现有技术中根据第一生物特征确定第一候选合集，根据第二生物特征确认第二候选合集，再将第一、第二候选合集进行与、或等逻辑运算得到待识别个人的方法，本发明有效的在确保识别准确度的同时减少了两次匹配过程中的匹配数量，提高了识别效率。The present invention also provides a new multi-biological information-based identification method, which first determines a candidate collection by a first biometric, and then determines an identity of the individual to be identified from the candidate collection by a second biometric. Compared with determining the first candidate collection according to the first biometric in the prior art, confirming the second candidate collection according to the second biometric, and then performing the logical operation of the first and second candidate collections to obtain the individual to be identified. The method effectively reduces the number of matches in the two matching processes while improving the recognition accuracy, and improves the recognition efficiency.

此外，由于面部、手掌图像采集均是通过非接触实现采集与比对，图像获取的过程更加清洁方便，用户体验好。In addition, since the image acquisition of the face and the palm is achieved through non-contact acquisition and comparison, the process of image acquisition is more clean and convenient, and the user experience is good.

图3描绘了其上可以实施本教导的通用计算机架构并且具有包括用户接口元素的计算机硬件平台的功能性框图描述。计算机可以是通用目的的计算机或者专用目的计算机。这个计算机300可以用于实施这里所描述的用户识别架构的任何组件。例如图1和图2所描绘的系统的不同组件全部可以经由其硬件、软件程序、固件或其组合而实施在例如计算机300的一个或多个计算机上。虽然为了方便仅仅示出了一个这种计算机，但是关于用户识别的计算机功能可以以分布的方式实施在多个相似的平台上，从而分布过程负载。3 depicts a functional block diagram depiction of a general purpose computer architecture on which the present teachings may be implemented and having a computer hardware platform including user interface elements. The computer can be a general purpose computer or a special purpose computer. Thiscomputer 300 can be used to implement any of the components of the user identification architecture described herein. For example, various components of the system depicted in Figures 1 and 2 can all be implemented on one or more computers, such ascomputer 300, via their hardware, software programs, firmware, or a combination thereof. Although only one such computer is shown for convenience, the computer functions for user identification can be implemented in a distributed manner on a plurality of similar platforms, thereby distributing the process load.

计算机300，例如包括连接到并且连接自连接到此从而有助于数据通信的网络的COM端口302。计算机300还包括CPU304，其形式为用于执行程序指令的一个或多个处理器。示例性的计算机平台包括内部通信总线306、具有不同形式的程序贮存设备和数据贮存设备，例如碟308、只读存储器(ROM)310、或者随机存储存储器(RAM)312，用于将被计算机处理并且/或者通信的各种数据文件，以及将被CPU304执行的可能的程序指令。计算机300还包括I/O组件314，支持在计算机和其中诸如用户接口元素316的其他组件之间的输入/输出流。计算机300还可以经由网络通信接收程序和数据。Computer 300, for example, includes aCOM port 302 that is connected to and connected to a network that is connected thereto to facilitate data communication.Computer 300 also includes aCPU 304 in the form of one or more processors for executing program instructions. An exemplary computer platform includes aninternal communication bus 306, program storage devices having different forms, and data storage devices, such as adisk 308, a read only memory (ROM) 310, or a random access memory (RAM) 312 for processing by a computer And/or various data files for communication, as well as possible program instructions to be executed by theCPU 304.Computer 300 also includes an I/O groupPiece 314 supports input/output streams between the computer and other components such asuser interface element 316.Computer 300 can also receive programs and data via network communications.

因此，如上面所勾勒出的用户识别方法的各个方面可以在程序中实施。技术的程序方面可以被认为是典型地形式为被承载或者实施在机器可读介质类型上的可执行代码和/或相关联数据的“产品”或“制造件”。有形的永久“贮存”类型介质包括任何或者所有的存储器或其他用于计算机、处理器或类似的存储器或其相关联模块，诸如各种半导体存储器、带驱动、盘驱动或类似，其可以在任何时候提供用于软件程序的贮存。Thus, various aspects of the user identification method as outlined above can be implemented in the program. A procedural aspect of the technology may be considered a "product" or "manufactured piece" typically in the form of executable code and/or associated data that is carried or implemented on a machine readable medium type. A tangible permanent "storage" type of media includes any or all of the memory or other memory for a computer, processor or similar or its associated modules, such as various semiconductor memories, tape drives, disk drives or the like, which may be in any Provide storage for software programs.

软件的所有或者部分可以不时地通过诸如因特网或各种其他电信网络的网络进行通信。这种通信例如可以实现软件从一个计算机或处理器加载进入另一个中。由此，可以承载软件元素的其他类型的介质包括光学、电气、以及电磁波，例如通过有线和光学陆地线网络以及通过各种空中链路而跨域本地设备之间的物理接口所使用的。承载这种波的物理元素，例如有限或无线链路、光学链路或者类似同样可以被视为承载软件的介质。正如在这里所使用的，除非限制于有形的“贮存”介质，例如计算机或机器“可读”的术语指的是任何参与了提供指令到处理器用于执行的介质。All or part of the software may communicate from time to time over a network such as the Internet or various other telecommunications networks. Such communication may, for example, enable software to be loaded from one computer or processor into another. Thus, other types of media that can carry software elements include optical, electrical, and electromagnetic waves, such as those used by wired and optical landline networks, and through physical interfaces between domain devices across various air links. Physical elements that carry such waves, such as limited or wireless links, optical links, or the like, can also be considered as a medium carrying software. As used herein, unless restricted to a tangible "storage" medium, the term "computer- or machine-readable" refers to any medium that participates in providing instructions to a processor for execution.

因此，机器可读介质可以采用许多形式，包括但不限于有形贮存介质、载波介质或物理传输介质。非易失性贮存介质例如包括诸如在任何计算机或类似中的任何贮存设备的光盘或磁盘，其可以用于实施系统或其任何组件，如图所示出。易失性贮存介质包括动态存储器，例如这种计算机平台的主存储器。有形传输介质包括同轴线缆、铜线和光纤，包括形成计算机系统内的总线的线路。载波传输介质可以采用电子或电磁信号的形式，或者声波或光波，例如这些在射频(RF)和红外(IR)数据通信中生成的。计算机可读介质的通用形式因此包括例如软盘、柔性盘、硬盘、磁盘、任何其他磁性介质、CD-ROM、DVD或DVD-ROM、任何其他光学介质、打孔卡片纸带、任何其他具有孔图案的物理贮存介质、RAM、PROM和EPROM、FLASH-EPROM、任何其他存储器芯片或卡盘、传送数据或指令的载波、传送这种载波的线缆或链路、或者计算机可以从其读取程序代码和/或数据的任何其他介质。许多这些形式的计算机可读介质可以涉及运载一个或多个指令的一个或多个序列到处理器用于执行。Thus, a machine-readable medium can take many forms, including but not limited to, a tangible storage medium, a carrier wave medium, or a physical transmission medium. Non-volatile storage media include, for example, optical disks or magnetic disks, such as any storage device in any computer or the like, which can be used to implement a system or any component thereof, as illustrated. Volatile storage media include dynamic storage, such as main memory of such computer platforms. Tangible transmission media include coaxial cables, copper wire and fiber optics, including the circuitry that forms the bus within the computer system. The carrier transmission medium can take the form of an electronic or electromagnetic signal, or acoustic or optical waves, such as those generated in radio frequency (RF) and infrared (IR) data communications. General forms of computer readable media thus include, for example, floppy disks, flexible disks, hard disks, magnetic disks, any other magnetic media, CD-ROM, DVD or DVD-ROM, any other optical media, perforated card stock, any other aperture pattern Physical storage medium, RAM, PROMAnd EPROM, FLASH-EPROM, any other memory chip or chuck, carrier carrying data or instructions, cable or link transmitting such carrier, or any other medium from which the computer can read program code and/or data . Many of these forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.

需要注意的是，本申请可在软件和/或软件与硬件的组合体中被实施，例如，可采用专用集成电路(ASIC)、通用目的计算机或任何其他类似硬件设备来实现。在一个实施例中，本申请的软件程序可以通过处理器执行以实现上文所述步骤或功能。同样地，本申请的软件程序(包括相关的数据结构)可以被存储到计算机可读记录介质中，例如，RAM存储器，磁或光驱动器或软磁盘及类似设备。另外，本申请的一些步骤或功能可采用硬件来实现，例如，作为与处理器配合从而执行各个步骤或功能的电路。It should be noted that the present application can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Likewise, the software programs (including related data structures) of the present application can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some of the steps or functions of the present application may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

另外，本申请的一部分可被应用为计算机程序产品，例如计算机程序指令，当其被计算机执行时，通过该计算机的操作，可以调用或提供根据本申请的方法和/或技术方案。而调用本申请的方法的程序指令，可能被存储在固定的或可移动的记录介质中，和/或通过广播或其他信号承载媒体中的数据流而被传输，和/或被存储在根据所述程序指令运行的计算机设备的工作存储器中。在此，根据本申请的一个实施例包括一个装置，该装置包括用于存储计算机程序指令的存储器和用于执行程序指令的处理器，其中，当该计算机程序指令被该处理器执行时，触发该装置运行基于前述根据本申请的多个实施例的方法和/或技术方案。In addition, a portion of the present application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or technical solution in accordance with the present application. The program instructions for invoking the method of the present application may be stored in a fixed or removable recording medium, and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in a The working memory of the computer device in which the program instructions are run. Herein, an embodiment in accordance with the present application includes a device including a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, triggering The apparatus operates based on the aforementioned methods and/or technical solutions in accordance with various embodiments of the present application.

对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一，第二等词语用来表示名称，而并不表示任何特定的顺序。It is obvious to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is defined by the appended claims instead All changes in the meaning and scope of equivalent elements are included in this application. Any reference signs in the claims should not be construed as limiting the claim. Moreover, it is obvious that the word "including" does not exclude other elements or steps.The singular does not exclude the plural. A plurality of units or devices recited in the system claims can also be implemented by a unit or device by software or hardware. The first, second, etc. words are used to denote names and do not denote any particular order.

Claims (19)

Translated fromChinese

一种用于识别个人的装置，包括：A device for identifying an individual, comprising:第一识别部分，用于将数据库中关于第一生物特征的匹配度高于第一临界阈值(A2)的候选确定为候选合集；a first identifying part, configured to determine, in the database, a candidate that the matching degree of the first biometric is higher than the first critical threshold (A2) as a candidate collection;第一判断部分，用于将所述候选合集中关于第一生物特征的匹配度高于第一阈值(A1)的候选确定为该个人，并退出识别；a first determining portion, configured to determine, as the individual, a candidate of the candidate collection with respect to the first biometric with a matching degree higher than the first threshold (A1), and exit the identification;第二判断部分，用于当所述候选合集中关于第一生物特征的匹配度都不高于第一阈值(A1)第一判断部分无法确定候选时，将所述候选合集中关于第二生物特征的匹配度高于第二临界阈值(B2)的候选确认为该个人，并退出识别；以及a second determining portion, configured to: when the matching degree of the candidate bio-features with respect to the first biometric is not higher than the first threshold (A1), the first judging portion cannot determine the candidate, and the candidate collection is related to the second biometric A candidate whose feature is higher than the second critical threshold (B2) is confirmed as the individual and exits the recognition;第二识别部分，用于当所述候选合集为空时，将数据库中关于第二生物特征的匹配度高于第二阈值(B1)的候选确定为该个人，并退出识别；a second identifying part, configured to determine, when the candidate collection is empty, a candidate in the database that the matching degree of the second biometric is higher than the second threshold (B1) as the individual, and exit the identification;其中，第一阈值(A1)高于第一临界阈值(A2)，第二阈值(B1)高于第二临界阈值(B2)。The first threshold (A1) is higher than the first critical threshold (A2), and the second threshold (B1) is higher than the second critical threshold (B2).根据权利要求1的装置，其特征在于，所述第一生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。The device according to claim 1, wherein said first biometric feature is one of a face, a palm, a fingerprint, a finger blood vessel, and an iris.根据权利要求2的装置，其特征在于，所述第一生物特征为面部图像。The apparatus of claim 2 wherein said first biometric is a facial image.根据权利要求3的装置，其特征在于，所述装置还包括：面部特征采集部分，用于获取待识别个人的面部图像。The apparatus according to claim 3, characterized in that said apparatus further comprises: a facial feature collecting section for acquiring a facial image of the individual to be identified.根据权利要求4的装置，其特征在于，所述第一识别部分包括：The apparatus according to claim 4, wherein said first identifying portion comprises:面部图像处理单元，用于基于采集到的面部图像生成面部特征；以及a facial image processing unit for generating a facial feature based on the acquired facial image;基于面部的匹配单元，用于对所述面部特征和存储在第一数据库中的多个候选面部特征进行比对，确定所述候选合集。The face-based matching unit is configured to compare the facial features with a plurality of candidate facial features stored in the first database to determine the candidate collection.根据权利要求1的装置，其特征在于，所述第二生物特征为面部、手掌、指纹、手指血管、虹膜中的一种，其中，所述第二生物特征与所述第一生物特征为不同的生物特征。The device according to claim 1, wherein said second biometric is one of a face, a palm, a fingerprint, a finger vessel, and an iris, wherein said second biometric is different from said first biometric Biological characteristics.根据权利要求6的装置，其特征在于，所述第二生物特征为手掌。The device of claim 6 wherein said second biometric feature is a palm.根据权利要求7的装置，其特征在于，所述第二生物特征为手掌掌纹信息、手掌血管信息、手掌形状信息中的一种或几种的组合。The apparatus according to claim 7, wherein said second biometric is a combination of one or more of palm palm print information, palm blood vessel information, and palm shape information.根据权利要求7的装置，其特征在于，所述装置还包括：手掌图像采集部分，用于采集待识别个人的手掌图像。The apparatus according to claim 7, wherein said apparatus further comprises: a palm image capturing section for collecting a palm image of the individual to be identified.根据权利要求9的装置，其特征在于，所述第二识别部分包括：The apparatus according to claim 9, wherein said second identifying portion comprises:手掌图像处理单元，用于基于采集到的手掌图像生成手掌特征图像；以及a palm image processing unit for generating a palm feature image based on the acquired palm image;基于手掌的匹配单元，用于对所述手掌特征图像和存储在第二数据库中的多个候选手掌特征图像中的每一个进行比对，根据比对结果确定该个人。The palm-based matching unit is configured to compare each of the palm feature image and the plurality of candidate palm feature images stored in the second database, and determine the individual according to the comparison result.根据权利要求9的装置，其特征在于，所述第二判断部分包括：The apparatus according to claim 9, wherein said second determining portion comprises:手掌图像处理单元，用于基于采集到的手掌图像生成手掌特征图像；以及a palm image processing unit, configured to generate a palm feature image based on the collected palm image;as well as基于手掌的匹配单元，用于对所述手掌特征图像和所述候选合集中的候选所对应的手掌特征图像中进行比对，根据比对结果确定该个人。The palm-based matching unit is configured to compare the palm feature image and the palm feature image corresponding to the candidate of the candidate collection, and determine the individual according to the comparison result.一种在具有至少一个处理器和存储器的机器上实现的用于识别个人的方法，包括：A method for identifying an individual implemented on a machine having at least one processor and memory, comprising:将数据库中关于第一生物特征的匹配度高于第一临界阈值(A2)的候选确定为候选合集；Determining, in the database, candidates for matching the first biometric with respect to the first critical threshold (A2) as candidate collections;将所述候选合集中关于第一生物特征的匹配度高于第一阈值(A1)的候选确定为该个人，并退出识别；Determining, in the candidate collection, that the degree of matching of the first biometric is higher than the first threshold (A1) is the individual, and exiting the identification;当所述候选合集中关于第一生物特征的匹配度都不高于第一阈值(A1)时第一判断部分无法确定候选，则将所述候选合集中关于第二生物特征的匹配度高于第二临界阈值(B2)的候选确认为该个人，并退出识别；以及When the matching degree of the candidate biometrics is not higher than the first threshold (A1), the first judging portion cannot determine the candidate, and the matching degree of the candidate folio with respect to the second biometric is higher than A candidate for the second critical threshold (B2) is identified as the individual and exits the identification;当所述候选合集为空时，将数据库中关于第二生物特征的匹配度高于第二阈值(B1)的候选确定为该个人，并退出识别；When the candidate collection is empty, the candidate in the database that the matching degree of the second biometric is higher than the second threshold (B1) is determined as the individual, and the identification is exited;其中，第一阈值(A1)高于第一临界阈值(A2)，第二阈值(B1)高于第二临界阈值(B2)。The first threshold (A1) is higher than the first critical threshold (A2), and the second threshold (B1) is higher than the second critical threshold (B2).根据权利要求12的方法，其特征在于，所述第一生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。The method of claim 12 wherein said first biometric feature is one of a face, a palm, a fingerprint, a finger vessel, and an iris.根据权利要求13的方法，其特征在于，所述第一生物特征为面部特征。The method of claim 13 wherein said first biometric feature is a facial feature.根据权利要求14的方法，其特征在于，基于个人的面部特征确定所述候选合集的方法包括：The method of claim 14 wherein the facial features of the individual are determinedThe method for determining the candidate collection includes:接收到从个人获取的待识别面部图像；Receiving a facial image to be recognized obtained from an individual;基于待识别面部图像生成待识别面部特征；Generating a facial feature to be recognized based on the facial image to be recognized;将待识别面部特征与存储在数据库中的多个候选面部特征的每一个进行比对，从而得到候选面部特征的每一个与待识别面部特征的匹配度；Comparing the facial features to be identified with each of the plurality of candidate facial features stored in the database, thereby obtaining a matching degree of each of the candidate facial features and the facial features to be recognized;基于所述匹配度选择一个或多个匹配候选。One or more matching candidates are selected based on the matching degree.根据权利要求12的方法，其特征在于，所述第二生物特征为面部、手掌、指纹、手指血管、虹膜中的一种。The method of claim 12 wherein said second biometric feature is one of a face, a palm, a fingerprint, a finger vessel, and an iris.根据权利要求16的方法，其特征在于，所述第二生物特征为手掌。The method of claim 16 wherein said second biometric feature is a palm.根据权利要求17的方法，其特征在于，所述第二生物特征为手掌掌纹信息、手掌血管信息、手掌形状信息中的一种或几种的组合。The method of claim 17, wherein said second biometric is a combination of one or more of palm palm print information, palm blood vessel information, and palm shape information.根据权利要求17的方法，其特征在于，基于个人的手掌特征确定该个人的方法包括：The method of claim 17 wherein the method of determining the individual based on an individual's palm characteristics comprises:接收到从个人获取的待识别手掌图像；Receiving an image of the palm to be recognized obtained from the individual;基于待识别手掌图像生成待识别手掌特征图像；Generating a palm feature image to be recognized based on the palm image to be recognized;将待识别手掌特征图像与所述候选合集中的候选对应的手掌特征的每一个进行比对，得到相应的匹配度；Comparing each of the palm feature images corresponding to the candidate of the candidate collection to the palm feature image to be recognized, and obtaining a corresponding matching degree;基于所述匹配度确定该个人。The individual is determined based on the matching degree.

Images