WO2016197389A1 - 一种用于检测活体对象的方法、装置和移动终端 - Google Patents

一种用于检测活体对象的方法、装置和移动终端 Download PDF

Info

Publication number
WO2016197389A1
WO2016197389A1 PCT/CN2015/081345 CN2015081345W WO2016197389A1 WO 2016197389 A1 WO2016197389 A1 WO 2016197389A1 CN 2015081345 W CN2015081345 W CN 2015081345W WO 2016197389 A1 WO2016197389 A1 WO 2016197389A1
Authority
WO
WIPO (PCT)
Prior art keywords
display screen
brightness
eye
change
image
Prior art date
Application number
PCT/CN2015/081345
Other languages
English (en)
French (fr)
Inventor
王晓鹏
徐鹤菲
Original Assignee
北京释码大华科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京释码大华科技有限公司 filed Critical 北京释码大华科技有限公司
Priority to CN201580080750.7A priority Critical patent/CN107710221B/zh
Priority to PCT/CN2015/081345 priority patent/WO2016197389A1/zh
Publication of WO2016197389A1 publication Critical patent/WO2016197389A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition

Definitions

  • the present invention relates to the technical field of biometrics and information security, and more particularly to a technique for detecting a living object.
  • biometrics especially facial recognition technology
  • the field is widely used for identity authentication.
  • biometric-based authentication also has some drawbacks. For example, illegal users obtain images/videos of legitimate users by various means, such as through public web albums, resumes, pinhole cameras, etc., and then forge biometric spoofing. Identify the system, thus gaining legal rights, etc. Therefore, there is an urgent need for biometrics to require that the person being identified be a living, not a photo or a recorded video, that is, biometrics need to rely on live detection techniques.
  • the present invention provides a method, apparatus and mobile terminal for detecting a living subject in an effort to solve or at least alleviate at least one of the problems present above.
  • a method for detecting a living body object includes the steps of: generating a random sequence adapted to control a change in brightness of a display screen of the mobile terminal; and changing a display screen of the mobile terminal in a specific brightness change mode according to a random sequence Brightness; real-time acquisition of an eye image of the object to be detected facing the display screen; analysis of the eye image sequence to obtain an eye feature change mode; determining whether the eye feature change mode corresponds to a specific brightness change mode; if corresponding, Make sure the object is alive.
  • the random sequence comprises a first random sequence component adapted to control a change in display screen brightness amplitude and a second random sequence component adapted to control a temporal or frequency change of the display screen brightness;
  • the particular brightness change mode includes a change in the amplitude of the display screen brightness and a change in time or frequency.
  • the step of acquiring an eye image in real time comprises: acquiring a face image of the object to be detected in real time; and cropping the eye image from the face image.
  • the step of analyzing the sequence of ocular images comprises detecting pupils from a sequence of ocular images and extracting pupil edge scaling features.
  • the ocular features comprise the area and/or diameter of the pupil and/or the blink and/or pupil reflection bright spots.
  • the step of determining whether the eye feature change mode corresponds to the specific brightness change mode comprises: if the display brightness of the screen is increased in the specific brightness change mode, the eye feature change mode The pupil area and/or the diameter of the middle eye image is reduced; and in the period in which the screen brightness is reduced in the specific brightness change mode, the pupil area and/or the diameter of the eye image is enlarged in the eye feature change mode, and the eye is judged
  • the feature change pattern corresponds to the specific brightness change mode.
  • the method further comprises the steps of: pre-analysing the current eye feature of the object to be detected; and comparing the eye feature with a predetermined threshold, wherein the step of generating the random sequence comprises based on the current eye feature The pattern generates a first random sequence component, wherein if the eye is special The sign is greater than the predetermined threshold, and the first random sequence component increases the display screen brightness during the first period, otherwise the first random sequence component decreases the display screen brightness during the first period.
  • the method further includes prompting the object to be detected to look at the display screen by means of text, color or multimedia on the display screen.
  • an apparatus for detecting a living body object includes: a sequence generating unit adapted to generate a random sequence for controlling a brightness of a display screen of the mobile terminal to change in a specific brightness change mode; image acquisition a unit adapted to collect an eye image of the object to be detected facing the display screen in real time; a living body recognition unit adapted to analyze the collected eye image sequence to obtain an eye feature change mode; and a determining unit adapted to determine the eye Whether the feature change mode corresponds to a specific brightness change mode; if corresponding, it is determined that the object is a living body.
  • the random sequence comprises a first random sequence component adapted to control a change in display screen brightness amplitude and a second random sequence component adapted to control a temporal or frequency change of the display screen brightness;
  • the particular brightness change mode includes a change in the amplitude of the display screen brightness and a change in time or frequency.
  • the image acquisition unit is adapted to acquire a face image of the object to be detected facing the display screen in real time; and the image acquisition unit further comprises a positioning unit adapted to position the cropped eye from the face image Part image.
  • the living body recognition unit is further adapted to detect the pupil from the sequence of ocular images and to extract the pupil edge scaling feature.
  • the ocular features comprise the area and/or diameter of the pupil and/or the blink and/or pupil reflectes the bright spot.
  • the judging unit is configured to reduce the pupil area and/or the diameter of the eye image in the eye feature change mode in a period in which the display screen brightness is increased in the specific brightness change mode And a period in which the display screen brightness is reduced in the specific brightness change mode, the pupil area and/or the diameter of the eye image is enlarged in the eye feature change mode; determining the eye feature change mode and the specific brightness change mode correspond.
  • the image acquisition unit is further adapted to acquire an eye image of the object to be detected; and the sequence generation unit is further adapted to perform pre-analysis of the eye features of the object to be detected, Comparing the eye feature with a predetermined threshold, and generating a first random sequence component based on the current eye feature mode, wherein if the eye feature is greater than a predetermined threshold, the first random sequence component increases the display screen brightness in the first cycle, otherwise The first random sequence component reduces the display screen brightness during the first period.
  • the object to be detected is prompted to look at the display screen by means of text, color or multimedia on the display screen.
  • a mobile terminal comprising: a display screen adapted to prompt the gaze of the object to be detected by means of color, text or multimedia; and an imaging device adapted to collect an image including the face of the object to be detected in real time And a device for detecting a living subject as described above.
  • the detection is realized by utilizing the essential feature of the reaction of the physiological and physical functions of the human eye under the excitation of light, and it is possible to quickly and efficiently detect whether the eye image is acquired from the living object. Improves the reliability of living body detection.
  • the living body detection can be conveniently implemented by using a common mobile terminal without adding additional hardware or equipment, which contributes to cost reduction.
  • FIG. 1 is a block diagram showing the configuration of a mobile terminal 100 according to an embodiment of the present invention
  • FIG. 2 shows a flow chart of a method 200 of detecting a living object in accordance with one embodiment of the present invention
  • FIG. 3 illustrates a block diagram of an apparatus 300 for detecting a living object in accordance with one embodiment of the present invention.
  • FIG. 1 is a block diagram showing the configuration of a mobile terminal 100 according to an embodiment of the present invention.
  • the mobile terminal 100 includes a memory interface 102, one or more data processors, an image processor and/or a central processing unit 104, and a peripheral interface 106.
  • Memory interface 102, one or more processors 104, and/or peripheral interface 106 can be either discrete components or integrated into one or more integrated circuits.
  • various components may be coupled by one or more communication buses or signal lines.
  • Sensors, devices, and subsystems can be coupled to the peripheral interface 106 to help implement a variety of functions.
  • motion sensor 110 can be coupled to peripheral interface 106 to facilitate functions such as orientation, illumination, and ranging.
  • Other sensors 116 may also be coupled to peripheral interface 106, such as a positioning system (e.g., a GPS receiver), a temperature sensor, a biometric sensor, or other sensing device, thereby facilitating the implementation of related functions.
  • Camera subsystem 120 and optical sensor 122 may be used to facilitate implementation of camera functions such as recording photos and video clips, where the camera subsystem and optical sensor may be, for example, a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS) ) Optical sensor.
  • Communication functions may be facilitated by one or more wireless communication subsystems 124, which may include radio frequency receivers and transmitters and/or optical (e.g., infrared) receivers and transmitters.
  • the particular design and implementation of wireless communication subsystem 124 may depend on one or more communication networks supported by mobile terminal 100.
  • mobile terminal 100 may include communication subsystem 124 that is designed to support a GSM network, a GPRS network, an EDGE network, a Wi-Fi or WiMax network, and a BlueboothTM network.
  • the audio subsystem 126 can be coupled to the speaker 128 and the microphone 130 to assist in implementing voice-enabled functions such as voice recognition, voice replication, digital recording, and telephony functions.
  • I/O subsystem 140 may include touch screen controller 142 and/or one or more other input controllers 144.
  • Touch screen controller 142 can be coupled to touch screen 146.
  • the touch screen 146 and the touch screen controller 142 can detect contact and movement or pause with any of a variety of touch sensing technologies, including but not limited to capacitive, Resistive, infrared and surface acoustic wave technology.
  • One or more other input controllers 144 may be coupled to other input/control devices 148, such as one or more buttons, rocker switches, thumb wheels, infrared ports, USB ports, and/or pointing devices such as styluses .
  • the one or more buttons may include An up/down button for controlling the volume of the speaker 128 and/or the microphone 130.
  • Memory interface 102 can be coupled to memory 150.
  • the memory 150 can include high speed random access memory and/or nonvolatile memory, such as one or more magnetic disk storage devices, one or more optical storage devices, and/or flash memory (eg, NAND, NOR).
  • the memory 150 can store an operating system 152, such as an operating system such as Android, IOS, or Windows Phone.
  • the operating system 152 can include instructions for processing basic system services and performing hardware dependent tasks.
  • the memory 150 can also store the application 154. These applications, when operational, are loaded from the memory 150 onto the processor 104 and run on top of the operating system already run by the processor 104, and utilize the interface provided by the operating system and the underlying hardware to implement various user desired functions. Such as instant messaging, web browsing, photo management, and so on. Applications can be either independent of the operating system or native to the operating system.
  • an apparatus 300 for detecting a living object is provided that can be stored in the application 154 as an application.
  • step S210 a random sequence suitable for controlling the display of the screen brightness change of the mobile terminal is generated.
  • the first random sequence component is an amplitude random variable array, which is used to control the change of the display screen brightness amplitude
  • the second random sequence component is an array of frequency random variables, To control the time or frequency change of the display screen brightness.
  • the random sequence can be generated by any random number generation algorithm, and in any suitable form, as long as the screen brightness can be randomly varied.
  • the random sequence may be [(t 1 , A 1 ), (t 2 , A 2 ), (t 3 , A 3 )...], respectively controlling the luminance amplitude at different points in time.
  • the randomness of such a random sequence does not need to be completely random in the sense of randomness, that is, although each value has a certain randomness, the trend of the change may exhibit a certain regularity, such as increasing the amplitude first, then decreasing and then increasing.
  • step S220 the brightness of the display screen of the mobile terminal is changed in a specific brightness change mode according to the random sequence generated in the previous step. That is to say, the two sets of random sequence components are taken as input variables, and the brightness change of the display screen is controlled by software.
  • the specific brightness change mode includes the amplitude change of the display screen brightness and the change of time or frequency.
  • any one of an array, a curve, or a model may be used to record a particular brightness change pattern.
  • text, color, icons, patterns, multimedia, or any suitable content that may cause the subject to be detected to be gazing may be displayed on the display screen of the mobile terminal 100 at the time of detection.
  • the above content can be displayed conspicuously.
  • an eye image of the object to be detected facing the display screen is acquired in real time.
  • the face image of the object to be detected is first acquired in real time, and then the eye image is cropped from the face image.
  • a face image of any suitable format can be obtained by means of the camera subsystem 120 of the mobile terminal 100.
  • the facial image may also be one or more frames in the captured video.
  • the original image may undergo various pre-processing and/or format conversions for subsequent live object detection and/or facial recognition after being acquired.
  • any image/video recognition technology currently known or later developed may be used in conjunction with embodiments of the present invention, and the scope of the present invention is not limited in this respect.
  • step S240 the sequence of eye images acquired in the previous step is analyzed to obtain an eye feature change pattern.
  • it is required to acquire an eye image of an object to be detected in a luminance change period in real time, instead of a frame image, thereby forming an eye image sequence.
  • the pupil is detected from the sequence of eye images acquired in step S230, and then the processed image extracts pupil edge scaling features and information therefrom.
  • the ocular features include the area and/or diameter of the pupil and/or the blink and/or pupil reflection bright spots.
  • the ocular feature change pattern can be described, for example, in an arbitrary form such as an array, a curve, or a model.
  • an arbitrary form such as an array, a curve, or a model.
  • the same form is used to describe the specific brightness change mode and the eye feature change mode for subsequent determination.
  • step S250 it is judged whether or not the eye feature change mode corresponds to the specific brightness change mode.
  • the judging method includes: if the display screen brightness is increased in the period of the specific brightness change mode, the pupil area and/or the diameter of the eye image is reduced in the eye feature change mode; or, in the specific brightness change mode In the period in which the display screen brightness is reduced, the pupil area and/or the diameter of the eye image in the eye feature change mode is enlarged, and it is considered that the eye feature change pattern corresponds to the specific brightness change pattern.
  • step S260 if corresponding, it is determined that the object is a living body. On the contrary, think This object is not a living body.
  • the current eye feature of the object to be detected may be pre-analyzed before the random sequence is generated, and then the first random sequence component is generated based on the current eye feature pattern.
  • the eye feature of the current object is acquired, and then the eye feature is compared with a predetermined threshold. If the eye feature is greater than a predetermined threshold, the first random sequence component increases the brightness of the display screen in the first cycle, otherwise the first The random sequence component reduces the display screen brightness during the first period.
  • the first random sequence component is generated to control the display screen variable, thereby increasing the light energy received by the eye of the object to be detected. Large, stimulating the pupil to shrink, so that rapid biopsy can be performed.
  • the detection is realized by utilizing the essential feature of the reaction of the physiological and physical functions of the human eye under the excitation of light, and it is possible to quickly and efficiently detect whether the eye image is acquired from the living object. Improves the reliability of living body detection.
  • a hacker may attempt to use a printed eye photo to place a fraud in front of the camera.
  • the detection of the characteristics of the human eye in front of the screen of the mobile terminal can be utilized.
  • the screen light source when the human eye looks directly at the screen of the mobile terminal, the pupil light in the human eye image obtained by the camera of the mobile terminal may reflect light, and the main light source is concentrated at a certain point in the region, and the other pupils The area does not reflect the screen source for structural reasons.
  • the focus reflection effect does not occur under the illumination of the light. Therefore, the pupil reflection spot can be extracted as a basis for living body detection.
  • a blinking motion is detected, the living body can be judged. This detection of blink and/or pupillary reflections can be used alone or in combination with previous solutions that utilize screen brightness variations.
  • FIG. 3 illustrates a block diagram of an apparatus 300 for detecting a living object in accordance with one embodiment of the present invention.
  • the apparatus includes a sequence generation unit 310, an image acquisition unit 320, a living body recognition unit 330, and a determination unit 340.
  • the sequence generation unit 310 is adapted to generate a random sequence for controlling the display screen of the mobile terminal 100
  • the brightness changes in a particular brightness change mode.
  • the random sequence includes a first random sequence component adapted to control a change in display screen brightness magnitude and a second random sequence component adapted to control a temporal or frequency change in display screen brightness.
  • the specific brightness change mode includes a change in the amplitude of the display screen brightness and a change in time or frequency, and the specific brightness change pattern can be recorded in the form of an array, a curve, or a model.
  • the face image of the object to be detected facing the display screen is then acquired by the image acquisition unit 320 in real time, and the face image of any suitable format can be acquired by means of the camera subsystem 120 of the mobile terminal 100.
  • the camera subsystem 120 and the image acquisition unit 320 may be separate components in the mobile terminal 100, and the facial image may be acquired by the camera subsystem 120 and then transmitted to the image acquisition unit 320, or may be the same component, and the scope of the present invention is not Limited to this.
  • the original image may undergo various pre-processing and/or format conversions for subsequent live object detection and/or facial recognition after being acquired.
  • any image/video recognition technology currently known or later developed may be used in conjunction with embodiments of the present invention, and the scope of the present invention is not limited in this respect.
  • the image acquisition unit 320 further includes a positioning unit 322 adapted to position the cropped eye image from the acquired facial image. The cropped eye image is then transmitted to the living body recognition unit 330 coupled thereto.
  • the living body recognition unit 330 is adapted to analyze the acquired sequence of eye images to obtain an eye feature change pattern. Specifically, the living body recognition unit 330 detects the pupil from the sequence of the eye images, and then processes the image from which the pupil edge scaling feature is extracted.
  • the ocular features include the area and/or diameter of the pupil and/or the blink and/or pupil reflection bright spots.
  • the ocular feature change pattern may be described in the form of an array, a curve, or a model.
  • the specific brightness change mode and the eye feature change mode are described in the same form to facilitate subsequent determination.
  • the determining unit 340 is adapted to determine the above two modes: whether the eye feature change mode corresponds to a specific brightness change mode, and if so, determine that the object is a living body. Specifically judge the rules such as Bottom: If the display screen brightness is increased in the period of the specific brightness change mode, the pupil area and/or the diameter of the eye image is reduced in the eye feature change mode; or, the display screen brightness is decreased in the specific brightness change mode. During the period, the pupil area and/or the diameter of the eye image is enlarged in the eye feature change mode, and it is considered that the eye feature change pattern corresponds to the specific brightness change pattern, thereby determining that the object is a living body.
  • the image acquiring unit 320 is further adapted to collect the eye image of the object to be detected, and after processing, transmit the obtained eye feature to the sequence generating unit 310.
  • the sequence generating unit 310 is further adapted to perform pre-analysis of the eye features of the object to be detected, compare the eye features with a predetermined threshold, and generate a first random sequence component based on the current eye feature pattern, wherein if the eye features are greater than The predetermined threshold is such that the first random sequence component increases the display screen brightness during the first period, otherwise the first random sequence component decreases the display screen brightness during the first period.
  • the predetermined threshold is such that the first random sequence component increases the display screen brightness during the first period, otherwise the first random sequence component decreases the display screen brightness during the first period.
  • modules or units or components of the devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be positioned differently than the devices in this example. In one or more devices.
  • the modules in the foregoing examples may be combined into one module or may be further divided into a plurality of sub-modules.
  • modules in the devices of the embodiments can be adaptively changed and placed in one or more devices different from the embodiment.
  • Can The modules or units or components in the embodiments are combined into one module or unit or component, and further they may be divided into a plurality of sub-modules or sub-units or sub-components.
  • any combination of the features disclosed in the specification, including the accompanying claims, the abstract and the drawings, and any methods so disclosed, or All processes or units of the device are combined.
  • Each feature disclosed in this specification may be replaced by alternative features that provide the same, equivalent or similar purpose.
  • the determining whether the eye feature change mode corresponds to the specific brightness change mode comprises: if the display screen brightness is increased in a period in which the display brightness is increased in the specific brightness change mode, the eye feature change mode is The pupil area and/or the diameter of the eye image is reduced; and in the period in which the screen brightness is reduced in the specific brightness change mode, the pupil area and/or the diameter of the eye image is enlarged in the eye feature change mode, and the eye is judged
  • the feature change mode corresponds to the specific brightness change mode.
  • the method of the present invention further comprising the steps of: pre-analysing the current eye feature of the object to be detected; and comparing the eye feature with a predetermined threshold, wherein the step of generating the random sequence comprises generating based on the current eye feature pattern A first random sequence component, wherein if the eye feature is greater than a predetermined threshold, the first random sequence component increases display screen brightness during the first period, otherwise the first random sequence component decreases display screen brightness during the first period.
  • the method according to the present invention further comprising prompting the object to be detected to look at the display screen by means of text, color or multimedia on the display screen.
  • the ocular features comprise an area and/or diameter of the pupil and/or a blink and/or pupil reflection bright spot.
  • the determining unit is configured to reduce a pupil area and/or a diameter of the eye image in the eye feature change mode in a period in which the display screen brightness is increased in the specific brightness change mode; And in the period in which the display screen brightness is reduced in the specific brightness change mode, the pupil area and/or the diameter of the eye image in the eye feature change mode is enlarged; determining that the eye feature change mode corresponds to the specific brightness change mode .
  • the image acquisition unit is further adapted to acquire an eye image of the object to be detected; and the sequence generation unit is further adapted to perform pre-analysis of the eye features of the object to be detected, comparing the eye features with the predetermined a threshold, and generating a first random sequence component based on the current eye feature pattern, wherein if the eye feature is greater than a predetermined threshold, the first random sequence component increases display screen brightness in the first cycle, Otherwise the first random sequence component reduces the display screen brightness during the first period.
  • the object to be detected is gazing at the display screen by means of text, color or multimedia on the display screen.

Abstract

本发明公开了一种用于检测活体对象的方法，包括步骤：生成适于控制移动终端显示屏幕亮度变化的随机序列；根据随机序列以特定亮度变化模式改变移动终端显示屏幕的亮度；实时采集面对显示屏幕的待检测对象的眼部图像；分析眼部图像序列以得到眼部特征变化模式；以及判断眼部特征变化模式与特定亮度变化模式是否相对应；如果相对应，则确定该对象为活体。

Description

一种用于检测活体对象的方法、装置和移动终端 技术领域
本发明涉及生物特征识别及信息安全的技术领域，更具体地，涉及一种用于检测活体对象的技术。
背景技术
随着视频、图像处理和模式识别技术的发展，生物识别特别是面部识别技术已经成为一种稳定、准确和高效的身份认证技术，在金融、司法、公共安全、军事以及人们日常生活中的各个领域被广泛用于身份认证。
然而，基于生物识别的身份认证也存在某些弊端，例如，非法用户以各种手段获得合法用户的图像/视频，例如通过公开的网络相册、个人简历、针孔照相机等，继而伪造生物特征欺骗识别系统，从而获得合法身份的权限等。因此，生物识别技术面临一项迫切需求是要求被识别的人是活体，而不是照片或者录制的视频，也就是说，生物识别需要依赖活体检测技术。
由于照片和视频不会有人体的温度，故传统的活体检测技术通过测量人体的温度来进行活体识别，但是温度检测设备庞大而且昂贵。现有的一种利用眼部特征进行活体检测的方法是通过用额外的LED灯对人眼进行照明，通过调节LED的亮度来刺激人眼瞳孔的放缩，照片和视频仿照的生物特征不会对LED的亮度有任何反馈，从而实现比温度更加智能的检测活体识别，但是这种方式需要在现有设备上增加额外的硬件，即LED灯和控制LED灯亮度的控制器，针对手机、平板等现有设备需要增加额外的空间和硬件成本，也是一个挑战。
鉴于上述弊端，需要一种快速可靠、又不增加硬件成本的活体对象检测方案。
发明内容
为此，本发明提供一种用于检测活体对象的方法、装置和移动终端，以力图解决或者至少缓解上面存在的至少一个问题。
根据本发明的一个方面，提供了一种用于检测活体对象的方法，包括步骤：生成适于控制移动终端显示屏幕亮度变化的随机序列；根据随机序列以特定亮度变化模式改变移动终端显示屏幕的亮度；实时采集面对显示屏幕的待检测对象的眼部图像；分析眼部图像序列以得到眼部特征变化模式；判断眼部特征变化模式与特定亮度变化模式是否相对应；如果相对应，则确定该对象为活体。
可选地，在根据本发明的方法中，随机序列包括适于控制显示屏幕亮度幅值变化的第一随机序列分量和适于控制显示屏幕亮度的时间或频率变化的第二随机序列分量；以及特定亮度变化模式包括显示屏幕亮度的幅度变化以及时间或频率变化。
可选地，在根据本发明的方法中，实时采集眼部图像的步骤包括：实时采集待检测对象的面部图像；从面部图像中定位裁剪出眼部图像。
可选地，在根据本发明的方法中，分析眼部图像序列的步骤包括：从眼部图像序列中检测瞳孔，并且提取瞳孔边缘缩放特征。
可选地，在根据本发明的方法中，眼部特征包括瞳孔的面积和/或直径和/或眨眼和/或瞳孔反射亮斑。
可选地，在根据本发明的方法中，判断眼部特征变化模式与特定亮度变化模式是否相对应的步骤包括：若在特定亮度变化模式中显示屏幕亮度增加的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径缩小；以及在特定亮度变化模式中显示屏幕亮度减小的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径放大，则判断眼部特征变化模式与所述特定亮度变化模式相对应。
可选地，在根据本发明的方法中，还包括步骤：对待检测对象当前的眼部特征进行预分析；以及比较眼部特征与预定阈值，其中生成随机序列的步骤包括基于当前的眼部特征模式生成第一随机序列分量，其中，如果眼部特 征大于预定阈值，则第一随机序列分量在第一周期使显示屏幕亮度增加，否则第一随机序列分量在第一周期使显示屏幕亮度减小。
可选地，在根据本发明的方法中，还包括在显示屏幕上通过文字、色彩或多媒体的方式提示待检测对象注视显示屏幕。
根据本发明的另一方面，提供了一种用于检测活体对象的装置，包括：序列生成单元，适于生成随机序列，用以控制移动终端显示屏幕的亮度以特定亮度变化模式改变；图像获取单元，适于实时采集面对显示屏幕的待检测对象的眼部图像；活体识别单元，适于分析采集到的眼部图像序列以得到眼部特征变化模式；以及判断单元，适于判断眼部特征变化模式与特定亮度变化模式是否相对应；如果相对应，则确定该对象为活体。
可选地，在根据本发明的装置中，随机序列包括适于控制显示屏幕亮度幅值变化的第一随机序列分量和适于控制显示屏幕亮度的时间或频率变化的第二随机序列分量；以及特定亮度变化模式包括显示屏幕亮度的幅度变化以及时间或频率变化。
可选地，在根据本发明的装置中，图像获取单元适于实时采集面对显示屏幕的待检测对象的面部图像；以及图像获取单元还包括定位单元，适于从面部图像中定位裁剪出眼部图像。
可选地，在根据本发明的装置中，活体识别单元还适于从眼部图像序列中检测瞳孔，并且提取瞳孔边缘缩放特征。
可选地，在根据本发明的装置中，眼部特征包括瞳孔的面积和/或直径和/或眨眼和/或瞳孔反射亮斑。
可选地，在根据本发明的装置中，判断单元被配置为，若在特定亮度变化模式中显示屏幕亮度增加的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径缩小；以及在特定亮度变化模式中显示屏幕亮度减小的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径放大；则判断眼部特征变化模式与所述特定亮度变化模式相对应。
可选地，在根据本发明的装置中，图像获取单元还适于采集待检测对象的眼部图像；以及序列生成单元还适于对待检测对象的眼部特征进行预分析， 比较眼部特征与预定阈值，且基于当前的眼部特征模式生成第一随机序列分量，其中，如果眼部特征大于预定阈值，则第一随机序列分量在第一周期使显示屏幕亮度增加，否则第一随机序列分量在第一周期使显示屏幕亮度减小。
可选地，在根据本发明的装置中，在显示屏幕上通过文字、色彩或多媒体的方式提示待检测对象注视显示屏幕。
根据本发明的另一方面，提供了一种移动终端，包括：显示屏幕，适于通过色彩、文字或多媒体的方式提示待检测对象注视；摄像器件，适于实时采集包含待检测对象面部的图像；以及如上所述的用于检测活体对象的装置。
根据本发明的检测活体对象的方案，利用人眼的生理和物理机能在光的激励下会产生的反应这一本质特征来实现检测，能够快速、有效地检测出眼部图像是否获取自活体对象，提高了活体检测的可靠性。另外，根据本发明的方案，利用常见的移动终端就可以方便地实施活体检测，无需增加额外的硬件或设备，有助于降低成本。
附图说明
为了实现上述以及相关目的，本文结合下面的描述和附图来描述某些说明性方面，这些方面指示了可以实践本文所公开的原理的各种方式，并且所有方面及其等效方面旨在落入所要求保护的主题的范围内。通过结合附图阅读下面的详细描述，本公开的上述以及其它目的、特征和优势将变得更加明显。遍及本公开，相同的附图标记通常指代相同的部件或元素。
图1示出了根据本发明一个实施例的移动终端100的构造框图；
图2示出了根据本发明一个实施例的检测活体对象的方法200的流程图；以及
图3示出了根据本发明一个实施例的检测活体对象的装置300的框图。
具体实施方式
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不 应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。
图1为根据本发明的一个实施方式的移动终端100构造示意图。参照图1，移动终端100包括：存储器接口102、一个或多个数据处理器、图像处理器和/或中央处理单元104，以及外围接口106。存储器接口102、一个或多个处理器104和/或外围接口106既可以是分立元件，也可以集成在一个或多个集成电路中。在移动终端100中，各种元件可以通过一条或多条通信总线或信号线来耦合。传感器、设备和子系统可以耦合到外围接口106，以便帮助实现多种功能。例如，运动传感器110、光传感器112和距离传感器114可以耦合到外围接口106，以方便定向、照明和测距等功能。其他传感器116同样可以与外围接口106相连，例如定位系统(例如GPS接收机)、温度传感器、生物测定传感器或其他感测设备，由此可以帮助实施相关的功能。
相机子系统120和光学传感器122可以用于方便诸如记录照片和视频剪辑的相机功能的实现，其中所述相机子系统和光学传感器例如可以是电荷耦合器件(CCD)或互补金属氧化物半导体(CMOS)光学传感器。可以通过一个或多个无线通信子系统124来帮助实现通信功能，其中无线通信子系统可以包括射频接收机和发射机和/或光(例如红外)接收机和发射机。无线通信子系统124的特定设计和实施方式可以取决于移动终端100所支持的一个或多个通信网络。例如，移动终端100可以包括被设计成支持GSM网络、GPRS网络、EDGE网络、Wi-Fi或WiMax网络以及BlueboothTM网络的通信子系统124。音频子系统126可以与扬声器128以及麦克风130相耦合，以便帮助实施启用语音的功能，例如语音识别、语音复制、数字记录和电话功能。
I/O子系统140可以包括触摸屏控制器142和/或一个或多个其他输入控制器144。触摸屏控制器142可以耦合到触摸屏146。举例来说，该触摸屏146和触摸屏控制器142可以使用多种触摸感测技术中的任何一种来检测与之进行的接触和移动或是暂停，其中感测技术包括但不局限于电容性、电阻性、红外和表面声波技术。一个或多个其他输入控制器144可以耦合到其他输入/控制设备148，例如一个或多个按钮、摇杆开关、拇指旋轮、红外端口、USB端口、和/或指示笔之类的指点设备。所述一个或多个按钮(未显示)可以包括 用于控制扬声器128和/或麦克风130音量的向上/向下按钮。
存储器接口102可以与存储器150相耦合。该存储器150可以包括高速随机存取存储器和/或非易失性存储器，例如一个或多个磁盘存储设备，一个或多个光学存储设备，和/或闪存存储器(例如NAND，NOR)。存储器150可以存储操作系统152，例如Android、IOS或是Windows Phone之类的操作系统。该操作系统152可以包括用于处理基本系统服务以及执行依赖于硬件的任务的指令。存储器150还可以存储应用154。这些应用在操作时，会从存储器150加载到处理器104上，并在已经由处理器104运行的操作系统之上运行，并利用操作系统以及底层硬件提供的接口实现各种用户期望的功能，如即时通信、网页浏览、图片管理等。应用可以是独立于操作系统提供的，也可以是操作系统自带的。
根据本发明的一个实施例，提供了一种用于检测活体对象的装置300，其可以作为一种应用而存储于应用154中。
图2示出了根据本发明的一个实施例的用于检测活体对象的方法200的流程图。该方法始于步骤S210。在步骤S210中，生成适于控制移动终端显示屏幕亮度变化的随机序列。根据本发明的一个实施例，随机生成两组变量数组，其中第一随机序列分量为振幅随机变量数组，用来控制显示屏幕亮度幅值的变化，第二随机序列分量为频率随机变量数组，用来控制显示屏幕亮度的时间或频率变化。应当理解，随机序列可以通过任何随机数生成算法生成，并且采用适合的任意形式，只要能够使屏幕亮度产生随机变化。例如，随机序列可以是[(t1,A1),(t2,A2),(t3,A3)…]，分别控制在不同时间点上的亮度幅值。此外，这种随机序列的随机性不需要完全严格意义上的随机，即虽然每个值具有一定随机性，但其变化趋势可以呈现一定规律，如幅度先增加再减小再增加。
随后在步骤S220中，根据上一步生成的随机序列以特定亮度变化模式改变移动终端显示屏幕的亮度。也就是说，将两组随机序列分量作为输入变量，通过软件控制显示屏幕的亮度变化，如步骤S210所描述，这种特定亮度变化模式包含了显示屏幕亮度的幅度变化以及时间或频率的变化。优选地，可以采用数组、曲线或者模型等任意一种形式来记录特定亮度变化模式。
根据一个实施例，在检测时移动终端100的显示屏幕上可以显示文字、色彩、图标、图案、多媒体或者可引起待检测对象注视的任何适当内容。为了确保能够引起待检测对象的足够注意，上述内容可以被醒目的显示。
随后在步骤S230中，实时采集面对显示屏幕的待检测对象的眼部图像。具体地，首先要实时采集待检测对象的面部图像，而后从该面部图像中定位裁剪出眼部图像。基于图1的描述，可以借助于移动终端100的相机子系统120来获取任意适当格式的面部图像。特别地，面部图像也可以是所捕获的视频中的一个或多个帧。此外，根据本发明的某些实施例，原始图像在被获取之后可以经过各种预处理和/或格式转换，以用于后续活体对象检测和/面部识别。在此方面，任何目前已知或者将来开发的图像/视频识别技术均可与本发明的实施例相结合使用，本发明的范围在此方面不受限制。
随后在步骤S240中，分析上一步采集得到的眼部图像序列，以得到眼部特征变化模式。根据一个实施方式，需要实时采集在一个亮度变化周期中待检测对象的眼部图像，而非一帧图像，也就构成了眼部图像序列。在操作中，从步骤S230中获取的眼部图像序列中检测瞳孔，然后处理图像从中提取出瞳孔边缘缩放特征和信息。任何目前已知或者将来开发的虹膜识别和/或分析方法均可与本发明的实施例结合使用，本发明的范围在此方面不受限制。在本发明中，眼部特征包括瞳孔的面积和/或直径和/或眨眼和/或瞳孔反射亮斑。
在本发明中，例如可以以数组、曲线或者模型等任意形式来描述眼部特征变化模式，优选地，采用同一形式来描述特定亮度变化模式和眼部特征变化模式，以便于后续进行判断。
随后在步骤S250中，判断眼部特征变化模式与特定亮度变化模式是否相对应。根据一个实施方式，判断方法包括：若在特定亮度变化模式中显示屏幕亮度增加的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径缩小；或者说，在特定亮度变化模式中显示屏幕亮度减小的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径放大，那么认为，眼部特征变化模式与特定亮度变化模式是相对应的。
随后在步骤S260中，如果相对应，则确定该对象为活体。反之，则认为 该对象不是活体。
根据本发明的实施例，为了更快速地实现活体对象检测，在生成随机序列之前，可以对待检测对象当前的眼部特征进行预分析，然后基于当前的眼部特征模式生成第一随机序列分量。在操作中，采集得到当前对象的眼部特征，而后比较该眼部特征与预定阈值，如果眼部特征大于预定阈值，则第一随机序列分量在第一周期使显示屏幕亮度增加，否则第一随机序列分量在第一周期使显示屏幕亮度减小。例如，如果采集到的当前对象的瞳孔特征值很大，即瞳孔面积/直径很大，那么就生成第一随机序列分量来控制显示屏幕变量，从而使得待检测对象的眼部接收的光能量增大，刺激其瞳孔缩小，这样就可以快速进行活体检测。
根据本发明的检测活体对象的方案，利用人眼的生理和物理机能在光的激励下会产生的反应这一本质特征来实现检测，能够快速、有效地检测出眼部图像是否获取自活体对象，提高了活体检测的可靠性。
另外，只是利用了具有显示屏幕的移动终端就可以方便地实施活体检测，无需增加额外的硬件或设备，有助于降低成本。
除了利用移动屏幕亮度变化来进行活体检测外，还可以采用其他方式。例如，黑客可能试图使用打印的眼部照片放在摄像头前进行欺诈。在这种情况下，可以利用人眼在移动终端屏幕前的特性进行检测。在屏幕光源下，当人眼直视移动终端屏幕时，移动终端摄像头获得的人眼图像中的瞳孔区域会出现光线的反射光现象，且主要光源集中在此区域的某一点，而瞳孔的其他区域因为结构原因不会反射屏幕光源。而对于打印的眼部图像，在光线照射下，也不会出现聚焦反射效果。因此，可以提取瞳孔反射光斑作为活体检测的依据。此外，如果检测到眨眼的动作也可以判断活体。这种眨眼和/或瞳孔反射亮斑的检测可以单独使用，也可以与之前利用屏幕亮度变化的方案结合使用。
图3示出了根据本发明一个实施例的用于检测活体对象的装置300的框图。该装置包括：序列生成单元310、图像获取单元320、活体识别单元330、以及判断单元340。
序列生成单元310适于生成随机序列，用以控制移动终端100显示屏幕 的亮度以特定亮度变化模式改变。根据本发明的实施例，随机序列包括适于控制显示屏幕亮度幅值变化的第一随机序列分量和适于控制显示屏幕亮度的时间或频率变化的第二随机序列分量。那么，特定亮度变化模式就包括显示屏幕亮度的幅度变化以及时间或频率变化，可以以数组、曲线或者模型的形式来记录特定亮度变化模式。另一方面，在检测时移动终端100的显示屏幕上可以显示文字、色彩、图标、图案、多媒体或者可引起待检测对象注视的任何适当内容。为了确保能够引起待检测对象的足够注意，上述内容可以被醒目的显示。
然后由图像获取单元320实时采集面对显示屏幕的待检测对象的面部图像，可以借助于移动终端100的相机子系统120来获取任意适当格式的面部图像。应当注意，相机子系统120与图像获取单元320可以是移动终端100中分离的部件，由相机子系统120获取面部图像，而后传送给图像获取单元320，亦可以是同一部件，本发明的范围不限于此。
此外，根据本发明的某些实施例，原始图像在被获取之后可以经过各种预处理和/或格式转换，以用于后续活体对象检测和/面部识别。在此方面，任何目前已知或者将来开发的图像/视频识别技术均可与本发明的实施例相结合使用，本发明的范围在此方面不受限制。
并且该图像获取单元320还包括定位单元322，其适于从采集到的面部图像中定位裁剪出眼部图像。而后将裁剪出的眼部图像传送给与之耦合的活体识别单元330。
活体识别单元330适于分析采集到的眼部图像序列以得到眼部特征变化模式。具体地，活体识别单元330从眼部图像序列中检测瞳孔，然后处理图像从中提取到瞳孔边缘缩放特征。在本发明中，眼部特征包括瞳孔的面积和/或直径和/或眨眼和/或瞳孔反射亮斑。根据本发明的一个实施例，可以以数组、曲线或者模型的形式来描述眼部特征变化模式，优选地，采用同一形式来描述特定亮度变化模式和眼部特征变化模式，以便于后续进行判断。
判断单元340适于判断上述两种模式：眼部特征变化模式与特定亮度变化模式是否相对应，如果相对应，则确定该对象为活体。具体地判断规则如 下：若在特定亮度变化模式中显示屏幕亮度增加的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径缩小；或者说，在特定亮度变化模式中显示屏幕亮度减小的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径放大，那么就认为，眼部特征变化模式与特定亮度变化模式是相对应的，进而确定该对象为活体。
另外，为了更快速地进行活体对象检测，图像获取单元320还适于采集待检测对象的眼部图像，经处理后将得到的眼部特征传送给序列生成单元310。
而后，序列生成单元310还适于对待检测对象的眼部特征进行预分析，比较眼部特征与预定阈值，且基于当前的眼部特征模式生成第一随机序列分量，其中，如果眼部特征大于预定阈值，则第一随机序列分量在第一周期使显示屏幕亮度增加，否则第一随机序列分量在第一周期使显示屏幕亮度减小。例如，如果采集到的当前对象的瞳孔特征值很大，即瞳孔面积/直径很大，那么就生成第一随机序列分量来控制显示屏幕变量，从而使得待检测对象的眼部接收的光能量增大，刺激其瞳孔缩小，这样就可以快速进行活体检测。
应当理解，为了精简本公开并帮助理解各个发明方面中的一个或多个，在上面对本发明的示例性实施例的描述中，本发明的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成反映如下意图：即所要求保护的本发明要求比在每个权利要求中所明确记载的特征更多特征。更确切地说，如下面的权利要求书所反映的那样，发明方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本发明的单独实施例。
本领域那些技术人员应当理解在本文所公开的示例中的设备的模块或单元或组件可以布置在如该实施例中所描述的设备中，或者可替换地可以定位在与该示例中的设备不同的一个或多个设备中。前述示例中的模块可以组合为一个模块或者此外可以分成多个子模块。
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以 把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
A、如本发明所述的方法，其中判断眼部特征变化模式与特定亮度变化模式是否相对应的步骤包括：若在特定亮度变化模式中显示屏幕亮度增加的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径缩小；以及在特定亮度变化模式中显示屏幕亮度减小的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径放大，则判断眼部特征变化模式与所述特定亮度变化模式相对应。B、如本发明所述的方法，还包括步骤：对待检测对象当前的眼部特征进行预分析；以及比较眼部特征与预定阈值，其中生成随机序列的步骤包括基于当前的眼部特征模式生成第一随机序列分量，其中，如果眼部特征大于预定阈值，则第一随机序列分量在第一周期使显示屏幕亮度增加，否则第一随机序列分量在第一周期使显示屏幕亮度减小。C、如本发明所述的方法，还包括在显示屏幕上通过文字、色彩或多媒体的方式提示待检测对象注视显示屏幕。
D、如本发明所述的装置，其中，眼部特征包括瞳孔的面积和/或直径和/或眨眼和/或瞳孔反射亮斑。E、如本发明所述的装置，其中判断单元被配置为，若在特定亮度变化模式中显示屏幕亮度增加的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径缩小；以及在特定亮度变化模式中显示屏幕亮度减小的周期中，眼部特征变化模式中眼部图像的瞳孔面积和/或直径放大；则判断眼部特征变化模式与所述特定亮度变化模式相对应。F、如本发明所述的装置，其中图像获取单元还适于采集待检测对象的眼部图像；以及序列生成单元还适于对待检测对象的眼部特征进行预分析，比较眼部特征与预定阈值，且基于当前的眼部特征模式生成第一随机序列分量，其中，如果眼部特征大于预定阈值，则第一随机序列分量在第一周期使显示屏幕亮度增加， 否则第一随机序列分量在第一周期使显示屏幕亮度减小。G、如本发明所述的装置，其中，在显示屏幕上通过文字、色彩或多媒体的方式提示待检测对象注视显示屏幕。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本发明的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
此外，所述实施例中的一些在此被描述成可以由计算机系统的处理器或者由执行所述功能的其它装置实施的方法或方法元素的组合。因此，具有用于实施所述方法或方法元素的必要指令的处理器形成用于实施该方法或方法元素的装置。此外，装置实施例的在此所述的元素是如下装置的例子：该装置用于实施由为了实施该发明的目的的元素所执行的功能。
如在此所使用的那样，除非另行规定，使用序数词“第一”、“第二”、“第三”等等来描述普通对象仅仅表示涉及类似对象的不同实例，并且并不意图暗示这样被描述的对象必须具有时间上、空间上、排序方面或者以任意其它方式的给定顺序。
尽管根据有限数量的实施例描述了本发明，但是受益于上面的描述，本技术领域内的技术人员明白，在由此描述的本发明的范围内，可以设想其它实施例。此外，应当注意，本说明书中使用的语言主要是为了可读性和教导的目的而选择的，而不是为了解释或者限定本发明的主题而选择的。因此，在不偏离所附权利要求书的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。对于本发明的范围，对本发明所做的公开是说明性的，而非限制性的，本发明的范围由所附权利要求书限定。

Claims (10)

  1. 一种用于检测活体对象的方法，所述方法包括步骤：
    生成适于控制移动终端显示屏幕亮度变化的随机序列；
    根据所述随机序列以特定亮度变化模式改变移动终端显示屏幕的亮度；
    实时采集面对显示屏幕的待检测对象的眼部图像；
    分析所述眼部图像序列以得到眼部特征变化模式；以及
    判断眼部特征变化模式与所述特定亮度变化模式是否相对应；
    如果相对应，则确定该对象为活体。
  2. 如权利要求1所述的方法，其中，所述随机序列包括适于控制显示屏幕亮度幅值变化的第一随机序列分量和适于控制显示屏幕亮度的时间或频率变化的第二随机序列分量；以及
    所述特定亮度变化模式包括显示屏幕亮度的幅度变化以及时间或频率变化。
  3. 如权利要求1或2所述的方法，其中所述实时采集眼部图像的步骤包括：
    实时采集待检测对象的面部图像；
    从所述面部图像中定位裁剪出眼部图像。
  4. 如权利要求1-3中任一项所述的方法，其中所述分析眼部图像序列的步骤包括：
    从眼部图像序列中检测瞳孔，并且提取瞳孔边缘缩放特征。
  5. 如权利要求1-4中任一项所述的方法，其中，
    所述眼部特征包括瞳孔的面积和/或直径和/或眨眼和/或瞳孔反射亮斑。
  6. 一种用于检测活体对象的装置，所述装置包括：
    序列生成单元，适于生成随机序列，用以控制移动终端显示屏幕的亮度以特定亮度变化模式改变；
    图像获取单元，适于实时采集面对显示屏幕的待检测对象的眼部图像；
    活体识别单元，适于分析采集到的眼部图像序列以得到眼部特征变化模式；以及
    判断单元，适于判断眼部特征变化模式与所述特定亮度变化模式是否相对应；如果相对应，则确定该对象为活体。
  7. 如权利要求6所述的装置，其中所述随机序列包括适于控制显示屏幕亮度幅值变化的第一随机序列分量和适于控制显示屏幕亮度的时间或频率变化的第二随机序列分量；以及
    所述特定亮度变化模式包括显示屏幕亮度的幅度变化以及时间或频率变化。
  8. 如权利要求6或7所述的装置，其中，
    所述图像获取单元适于实时采集面对显示屏幕的待检测对象的面部图像；以及
    所述图像获取单元还包括定位单元，适于从所述面部图像中定位裁剪出眼部图像。
  9. 如权利要求6-8中任一项所述的装置，其中，
    所述活体识别单元还适于从所述眼部图像序列中检测瞳孔，并且提取瞳孔边缘缩放特征。
  10. 一种移动终端，包括：
    亮度可调节的显示屏幕；摄像器件，适于实时采集包含待检测对象面部的图像；以及
    如权利要求6-9中任一项所述的用于检测活体对象的装置。
PCT/CN2015/081345 2015-06-12 2015-06-12 一种用于检测活体对象的方法、装置和移动终端 WO2016197389A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201580080750.7A CN107710221B (zh) 2015-06-12 2015-06-12 一种用于检测活体对象的方法、装置和移动终端
PCT/CN2015/081345 WO2016197389A1 (zh) 2015-06-12 2015-06-12 一种用于检测活体对象的方法、装置和移动终端

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2015/081345 WO2016197389A1 (zh) 2015-06-12 2015-06-12 一种用于检测活体对象的方法、装置和移动终端

Publications (1)

Publication Number Publication Date
WO2016197389A1 true WO2016197389A1 (zh) 2016-12-15

Family

ID=57502882

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/081345 WO2016197389A1 (zh) 2015-06-12 2015-06-12 一种用于检测活体对象的方法、装置和移动终端

Country Status (2)

Country Link
CN (1) CN107710221B (zh)
WO (1) WO2016197389A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106874876A (zh) * 2017-02-20 2017-06-20 深圳市科漫达智能管理科技有限公司 一种人脸活体检测方法及装置
WO2019161730A1 (zh) * 2018-02-26 2019-08-29 阿里巴巴集团控股有限公司 一种活体检测的方法、装置及设备
CN111046816A (zh) * 2019-12-18 2020-04-21 杭州天谷信息科技有限公司 真人人脸识别系统及其方法
CN111767829A (zh) * 2020-06-28 2020-10-13 京东数字科技控股有限公司 一种活体检测方法、装置、系统及存储介质
CN112712073A (zh) * 2021-03-29 2021-04-27 北京远鉴信息技术有限公司 基于眼部变化特征的活体识别方法、识别装置及电子设备

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10599934B1 (en) * 2019-03-21 2020-03-24 Alibaba Group Hoding Limited Spoof detection using optokinetic response
CN110648314B (zh) * 2019-09-05 2023-08-04 创新先进技术有限公司 一种识别翻拍图像的方法、装置及设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514440A (zh) * 2012-06-26 2014-01-15 谷歌公司 面部识别
CN104166835A (zh) * 2013-05-17 2014-11-26 诺基亚公司 用于识别活体用户的方法和装置
EP2821938A1 (en) * 2012-02-28 2015-01-07 Intel Corporation Method and device for notification of facial recognition environment, and computer-readable recording medium for executing method
CN104463113A (zh) * 2014-11-28 2015-03-25 福建星网视易信息系统有限公司 一种人脸识别方法、装置及门禁系统

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103544420B (zh) * 2013-08-15 2016-05-11 马建 用于智能眼镜的防伪虹膜身份认证方法
CN104572121A (zh) * 2015-01-27 2015-04-29 合肥联宝信息技术有限公司 用于计算机的屏幕的亮度调节方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2821938A1 (en) * 2012-02-28 2015-01-07 Intel Corporation Method and device for notification of facial recognition environment, and computer-readable recording medium for executing method
CN103514440A (zh) * 2012-06-26 2014-01-15 谷歌公司 面部识别
CN104166835A (zh) * 2013-05-17 2014-11-26 诺基亚公司 用于识别活体用户的方法和装置
CN104463113A (zh) * 2014-11-28 2015-03-25 福建星网视易信息系统有限公司 一种人脸识别方法、装置及门禁系统

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106874876A (zh) * 2017-02-20 2017-06-20 深圳市科漫达智能管理科技有限公司 一种人脸活体检测方法及装置
WO2019161730A1 (zh) * 2018-02-26 2019-08-29 阿里巴巴集团控股有限公司 一种活体检测的方法、装置及设备
US10977508B2 (en) 2018-02-26 2021-04-13 Advanced New Technologies Co., Ltd. Living body detection method, apparatus and device
US11295149B2 (en) 2018-02-26 2022-04-05 Advanced New Technologies Co., Ltd. Living body detection method, apparatus and device
CN111046816A (zh) * 2019-12-18 2020-04-21 杭州天谷信息科技有限公司 真人人脸识别系统及其方法
CN111767829A (zh) * 2020-06-28 2020-10-13 京东数字科技控股有限公司 一种活体检测方法、装置、系统及存储介质
CN111767829B (zh) * 2020-06-28 2023-11-07 京东科技控股股份有限公司 一种活体检测方法、装置、系统及存储介质
CN112712073A (zh) * 2021-03-29 2021-04-27 北京远鉴信息技术有限公司 基于眼部变化特征的活体识别方法、识别装置及电子设备

Also Published As

Publication number Publication date
CN107710221A (zh) 2018-02-16
CN107710221B (zh) 2021-06-29

Similar Documents

Publication Publication Date Title
WO2016197389A1 (zh) 一种用于检测活体对象的方法、装置和移动终端
JP5502837B2 (ja) 電子機器、電子機器においてオペレーションを実行する段階を備える方法、及びプログラム
US10108961B2 (en) Image analysis for user authentication
US9613200B2 (en) Ear biometric capture, authentication, and identification method and system
EP3284016B1 (en) Authentication of a user of a device
WO2018121428A1 (zh) 一种活体检测方法、装置及存储介质
WO2015113479A1 (zh) 一种具有人机交互机制的移动终端虹膜识别装置和方法
US8984622B1 (en) User authentication through video analysis
JP6631808B2 (ja) 虹彩利用生体認証のための装置および方法
WO2017156964A1 (zh) 一种终端解锁的方法及终端
US20160062456A1 (en) Method and apparatus for live user recognition
TW201512880A (zh) 電子裝置、身份驗證系統及方法
WO2019011072A1 (zh) 虹膜活体检测方法及相关产品
TWI752105B (zh) 特徵圖像的獲取方法及獲取裝置、使用者認證方法
JP7131761B2 (ja) 複屈折ベースの生体認証のための方法及び装置
US20160366317A1 (en) Apparatuses and methods for image based biometric recognition
WO2018004921A1 (en) Technologies for efficient identity recognition based on skin features
WO2016115786A1 (zh) 终端解锁方法、装置、终端及计算机存储介质
Beton et al. Biometric secret path for mobile user authentication: A preliminary study
WO2019095097A1 (zh) 电子终端的身份验证方法与电子终端
Wong et al. Towards inclusive design in mobile biometry
CN110677927A (zh) 可穿戴设备自动连接的方法和装置、存储介质、电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15894658

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15894658

Country of ref document: EP

Kind code of ref document: A1