WO2019001254A1 - 虹膜活体检测方法及相关产品 - Google Patents

虹膜活体检测方法及相关产品 Download PDF

Info

Publication number
WO2019001254A1
WO2019001254A1 PCT/CN2018/090649 CN2018090649W WO2019001254A1 WO 2019001254 A1 WO2019001254 A1 WO 2019001254A1 CN 2018090649 W CN2018090649 W CN 2018090649W WO 2019001254 A1 WO2019001254 A1 WO 2019001254A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
iris
quality evaluation
image quality
frequency component
Prior art date
Application number
PCT/CN2018/090649
Other languages
English (en)
French (fr)
Inventor
周意保
周海涛
张学勇
唐城
Original Assignee
Oppo广东移动通信有限公司
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 Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2019001254A1 publication Critical patent/WO2019001254A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18—Eye characteristics, e.g. of the iris
    • 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

Definitions

  • the present application relates to the field of electronic device technologies, and in particular, to an iris living body detecting method and related products.
  • iris recognition is increasingly favored by electronic equipment manufacturers, and the safety of iris recognition is also one of the important issues of concern.
  • the iris is usually inspected before the iris is recognized, but the current iris detection accuracy is not high.
  • the embodiment of the present application provides an iris living body detecting method and related products, so as to improve the accuracy of the iris living body detection.
  • an embodiment of the present application provides a method for detecting an iris living body, including:
  • the M group features are trained by using a preset iris living body detection classifier, and it is judged according to the training result whether the iris image is from a living iris.
  • an embodiment of the present application provides an iris living body detecting apparatus, including:
  • a decomposition unit configured to perform multi-scale decomposition on the iris image to obtain K high-frequency component images, where K is an integer greater than 1;
  • a determining unit configured to determine features between different high frequency component images in the K high frequency component images, to obtain M sets of features, wherein the M is an integer greater than 1;
  • a training unit configured to train the M group features by using a preset iris living body detection classifier, and determine, according to the training result, whether the iris image is from a living iris.
  • an embodiment of the present application provides an electronic device, an application processor AP and a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be The AP is executed, and the program includes instructions for performing some or all of the steps as described in the first aspect of the embodiments of the present application.
  • an embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, wherein the computer program causes the computer to execute as implemented in the present application.
  • an embodiment of the present application provides a computer program product, where the computer program product includes a non-transitory computer readable storage medium storing a computer program, the computer program being operative to cause a computer to execute Apply some or all of the steps described in the first aspect of the embodiment.
  • the computer program product can be a software installation package.
  • an iris image is acquired, and the iris image is multi-scale-decomposed to obtain K high-frequency component images, where K is an integer greater than 1, and different high-frequency component images in the K high-frequency component images are determined.
  • K is an integer greater than 1
  • M is an integer greater than 1.
  • the preset iris active detection classifier is used to train the M group features, and according to the training result, it is judged whether the iris image is from the living iris, and thus the iris image can be Multi-scale decomposition is performed to obtain high-frequency component images, and detailed features in the iris image are obtained according to the high-frequency component images, thereby deeply excavating the detailed features of the iris image, and training the detailed features to determine The iris image comes from the living iris, which improves the accuracy of iris detection.
  • FIG. 1A is a schematic structural diagram of an example smart phone provided by an embodiment of the present application.
  • FIG. 1B is a schematic flow chart of an iris living body detecting method disclosed in an embodiment of the present application.
  • FIG. 2 is a schematic flow chart of another iris living body detecting method disclosed in an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • FIG. 4A is a schematic structural view of an iris living body detecting device according to an embodiment of the present application.
  • FIG. 4B is a schematic structural diagram of a determining unit of the iris living body detecting device described in FIG. 4A according to an embodiment of the present application;
  • FIG. 4C is a schematic structural diagram of an acquiring unit of the iris living body detecting device described in FIG. 4A according to an embodiment of the present application;
  • 4D is another schematic structural diagram of an iris living body detecting device provided by an embodiment of the present application.
  • 4E is another schematic structural diagram of an iris living body detecting device according to an embodiment of the present application.
  • 4F is another schematic structural diagram of an iris living body detecting device provided by an embodiment of the present application.
  • 4G is another schematic structural diagram of an iris living body detecting device provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of another electronic device disclosed in the embodiment of the present application.
  • references to "an embodiment” herein mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present application.
  • the appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive. Those skilled in the art will understand and implicitly understand that the embodiments described herein can be combined with other embodiments.
  • the electronic device involved in the embodiments of the present application may include various handheld devices having wireless communication functions, in-vehicle devices, wearable devices, computing devices, or other processing devices connected to the wireless modem, and various forms of user devices (User Equipment, UE), mobile station (MS), terminal device, and the like.
  • user devices User Equipment, UE
  • MS mobile station
  • terminal device terminal device
  • the devices mentioned above are collectively referred to as electronic devices.
  • the iris recognition device of the smart phone 100 may include an infrared fill light 21 and an infrared camera 22.
  • the iris recognition device collects the iris image, and 23 can be the front camera.
  • FIG. 1B is a schematic flowchart of an embodiment of an iris living body detecting method according to an embodiment of the present application.
  • the iris living body detecting method described in this embodiment includes the following steps:
  • the iris image in the embodiment of the present application may be an image of a single-finger iris region or an image including an iris region (for example, a human eye image).
  • the iris image can be acquired by the iris recognition device.
  • the multi-scale decomposition algorithm may be used to perform multi-scale image on the iris image to obtain a low-frequency component image and a plurality of high-frequency component images
  • the multi-scale decomposition algorithm may include but is not limited to: wavelet transform, Laplace transform, contour wave Contourlet transform (CT), non-subsampled contourlet transform (NSCT), shear wave transform, etc., taking contour wave as an example, using contour wave transform to multi-scale decomposition of iris image, Obtaining a low-frequency component image and a plurality of high-frequency component images, and each of the plurality of high-frequency component images has different sizes.
  • a low frequency can be obtained.
  • a component image and a plurality of high frequency component images, and each of the plurality of high frequency component images has the same size. For high frequency components, it contains more details of the image.
  • step 101 the following steps may be further included:
  • Image enhancement processing is performed on the iris image.
  • the image enhancement processing may include, but is not limited to, image denoising (eg, wavelet transform for image denoising), image restoration (eg, Wiener filtering), dark visual enhancement algorithm (eg, histogram equalization, grayscale pull) Stretching, etc.), after image enhancement processing of the iris image, the quality of the iris image can be improved to some extent. Further, during the execution of step 102, the iris image after the enhancement processing may be subjected to multi-scale decomposition.
  • image denoising eg, wavelet transform for image denoising
  • image restoration eg, Wiener filtering
  • dark visual enhancement algorithm eg, histogram equalization, grayscale pull
  • step 101 the following steps may be further included:
  • A1. Perform image quality evaluation on the iris image to obtain an image quality evaluation value
  • A2 Perform image enhancement processing on the iris image when the image quality evaluation value is lower than a preset quality threshold.
  • the preset quality threshold may be set by the user or the system defaults, and the image quality of the iris image may be first evaluated to obtain an image quality evaluation value, and whether the quality of the iris image is good or bad is determined by the image quality evaluation value.
  • the image quality evaluation value is greater than or equal to the preset quality threshold, the iris image quality is considered to be good.
  • the image quality evaluation value is less than the preset quality threshold, the iris image quality may be considered to be poor, and further, the iris image may be subjected to image enhancement processing. Further, during the execution of step 102, the iris image after the enhancement processing may be subjected to multi-scale decomposition.
  • At least one image quality evaluation index may be used to perform image quality evaluation on the iris image, thereby obtaining an image quality evaluation value.
  • Image quality evaluation indicators may be included, and each image quality evaluation index also corresponds to a weight. Thus, each image quality evaluation index can obtain an evaluation result when performing image quality evaluation on the iris image, and finally, a weighting operation is performed. The final image quality evaluation value is also obtained.
  • Image quality evaluation indicators may include, but are not limited to, mean, standard deviation, entropy, sharpness, signal to noise ratio, and the like.
  • Image quality can be evaluated by using 2 to 10 image quality evaluation indicators. Specifically, the number of image quality evaluation indicators and which indicator are selected are determined according to specific implementation conditions. Of course, it is also necessary to select image quality evaluation indicators in combination with specific scenes, and the image quality indicators in the dark environment and the image quality evaluation in the bright environment may be different.
  • an image quality evaluation index may be used for evaluation.
  • the image quality evaluation value is processed by entropy processing, and the entropy is larger, indicating that the image quality is higher.
  • the smaller the entropy the worse the image quality.
  • the image may be evaluated by using multiple image quality evaluation indicators, and the plurality of image quality evaluation indicators may be set when the image quality is evaluated.
  • the weight of each image quality evaluation index in the image quality evaluation index may obtain a plurality of image quality evaluation values, and the final image quality evaluation value may be obtained according to the plurality of image quality evaluation values and corresponding weights, for example, three images
  • the quality evaluation indicators are: A index, B index and C index.
  • the weight of A is a1
  • the weight of B is a2
  • the weight of C is a3.
  • A, B and C are used to evaluate the image quality of an image
  • a The corresponding image quality evaluation value is b1
  • the image quality evaluation value corresponding to B is b2
  • the image quality evaluation value corresponding to C is b3
  • the final image quality evaluation value a1b1+a2b2+a3b3.
  • the larger the image quality evaluation value the better the image quality.
  • step 101 the following steps may be further included:
  • the above P may be specified by the user or the system defaults, and P is an integer greater than 1.
  • the iris image may be divided into P regions according to a preset grid, and P region images may be obtained, and the P regions are independent of each other, and then, image quality evaluation of the P region images may be performed.
  • image quality evaluation values can be obtained.
  • the preset image quality threshold may be set by the user or the system defaults, and an image quality quality evaluation value greater than a preset image quality threshold may be selected from the P image quality evaluation values, and Q image quality evaluation values may be obtained, and the Q is an area image corresponding to the image quality evaluation value, and Q is a positive integer less than or equal to P.
  • step 102 it is only necessary to perform multi-scale decomposition on the region images corresponding to the Q image quality evaluation values.
  • the image of the clear area can be selected from the iris image for living body detection, which can improve the efficiency of living body detection. After all, sometimes the image is not clear enough to have a high false recognition rate, and only the clear area can be detected by living body. Reduce the detection area, on the other hand, reduce the false recognition rate.
  • the embodiment of the present application can determine the fine features of the image by the difference between different high-frequency component images, and the fine features are difficult to be forged, and thus can be used for iris living body detection.
  • determining features between different high-frequency component images in the K high-frequency component images to obtain M-group features may include the following steps:
  • one high-frequency component image may be selected from the K high-frequency component images as a reference image, and the size of the other high-frequency component image may be adjusted to the reference size by using the size of the reference image as a reference size, or All high frequency component images in the K high frequency component images are adjusted to a specified size, which can be set by the user or the system defaults.
  • the above preset sequence may be a random order, or a sequence of generation of K high-frequency component images. Further, according to different high-frequency component images in the K high-frequency component images, the difference results may be performed in a preset order, and M result images may be obtained.
  • feature extraction is performed on M results, and M sets of features can be obtained, and each result image corresponds to a set of features.
  • Harris The corner detection algorithm, the scale invariant feature transform (SIFT), the SUSAN corner detection algorithm, and the like are not described herein.
  • each high-frequency component image of the K high-frequency component images corresponds to one level
  • the adjusted K high-frequency component images are subtracted according to a preset order to obtain
  • the M result images may include the following steps:
  • the adjusted K high-frequency components are divided into a plurality of categories according to the hierarchy, and the subtraction operations between the different high-frequency component images in each category are respectively calculated to obtain M result images.
  • the above levels are related to the factors set by the user in advance. The following specific examples are as follows:
  • the decomposition level of a certain layer of the directional filter bank is 0, the layer will not be decomposed in multiple directions, so that multiple directions
  • the number of decomposition layers is J. After the J layer is decomposed, one low frequency component image is obtained. A high-frequency component image, where 2 j is the number of sub-bands obtained by the direction decomposition at scale j.
  • the number of components is 2, 8, 8, 16 respectively, that is, it corresponds to 4 levels, the first level corresponds to 2 high-frequency component images, the second level corresponds to 8 high-frequency component images, and the third level corresponds to 8 The high-frequency component image, the fourth level corresponds to 16 high-frequency component images, it can be seen that different levels can get different images.
  • the M group features by using a preset iris living body detection classifier, and determine, according to the training result, whether the iris image is from a living iris.
  • the preset iris active detection classifier can be used to train the M group features to obtain training results, and according to the training result, whether the iris image is from the living iris is determined.
  • the training result can be a probability value. For example, if the probability value is 80%, the iris image can be considered to be from the living iris, and the iris image is considered to be from the non-living iris, and the non-living iris can be one of the following: 3D printing
  • the iris, the iris in the photo, and the iris of the person without life features are not limited here.
  • the preset iris living body detection classifier may be set before the implementation of the foregoing embodiment of the present application, and the main settings may include the following steps C1-C7:
  • the first class target classifier and the second class target classifier are used as the preset iris living body detection classifier.
  • X and Y can be set by the user, and the larger the specific number, the better the classification effect of the classifier.
  • the first designated classifier and the second designated classifier may be the same classifier or different classifiers, regardless of the first specified classifier.
  • the second designated classifier may include, but is not limited to, a support vector machine (SVM), a genetic algorithm classifier, a neural network algorithm classifier, a cascade classifier (eg, genetic algorithm + SVM), and the like.
  • an iris image is acquired, and the iris image is multi-scale-decomposed to obtain K high-frequency component images, where K is an integer greater than 1, and different high-frequency component images in the K high-frequency component images are determined.
  • K is an integer greater than 1
  • M is an integer greater than 1.
  • the preset iris active detection classifier is used to train the M group features, and according to the training result, it is judged whether the iris image is from the living iris, and thus the iris image can be Multi-scale decomposition is performed to obtain high-frequency component images, and detailed features in the iris image are obtained according to the high-frequency component images, thereby deeply excavating the detailed features of the iris image, and training the detailed features to determine The iris image comes from the living iris, which improves the accuracy of iris detection.
  • FIG. 2 is a schematic flow chart of an embodiment of a method for detecting an iris living body according to an embodiment of the present application.
  • the iris living body detecting method described in this embodiment includes the following steps:
  • the face image of the electronic device can be used to obtain the face image, and the face image is used as the test image.
  • the test image can also be a human eye image.
  • the M group features by using a preset iris living body detection classifier, and determine, according to the training result, whether the iris image is from a living iris.
  • the test image is acquired, the iris image is extracted from the test image, and the iris image is multi-scale-decomposed to obtain K high-frequency component images, where K is an integer greater than 1, and K high-frequency is determined.
  • K is an integer greater than 1
  • K high-frequency is determined.
  • the characteristics between different high-frequency component images in the component image, the M group features are obtained, and M is an integer greater than 1.
  • the preset iris active detection classifier is used to train the M group features, and according to the training result, whether the iris image is from the living body is determined.
  • the iris thereby, can multi-scale decomposition of the iris image to obtain a high-frequency component image thereof, and obtain detailed features in the iris image according to the high-frequency component image, thereby deeply excavating the detailed features of the iris image,
  • the detailed features are trained to determine that the iris image comes from the living iris, which improves the accuracy of the iris biopsy.
  • FIG. 3 is an electronic device according to an embodiment of the present application, including: an application processor AP and a memory; and one or more programs, where the one or more programs are stored in a memory and configured The execution is performed by the AP, and the program includes instructions for performing the following steps:
  • the M group features are trained by using a preset iris living body detection classifier, and it is judged according to the training result whether the iris image is from a living iris.
  • the program includes instructions for performing the following steps:
  • Feature extraction is performed on the M result images respectively to obtain the M group features.
  • each of the K high-frequency component images corresponds to a level
  • the adjusted K high-frequency component images are subtracted in a preset order to obtain
  • the program includes instructions for performing the following steps:
  • the adjusted K high-frequency components are divided into a plurality of categories according to the hierarchy, and the subtraction operations between the different high-frequency component images in each category are respectively calculated to obtain M result images.
  • the program includes instructions for performing the following steps:
  • the iris image is extracted from the test image.
  • the program further includes instructions for performing the following steps:
  • Image enhancement processing is performed on the iris image; in the multi-scale decomposition of the iris image, the program includes instructions for performing the following steps:
  • the image enhancement processing of the iris image is subjected to multi-scale decomposition.
  • the program further includes instructions for performing the following steps:
  • the program includes instructions for performing the following steps:
  • the multi-scale decomposition is performed on the region images corresponding to the Q image quality evaluation values.
  • the program further includes instructions for performing the following steps:
  • the multi-scale decomposition of the iris image comprising instructions for performing the following steps:
  • the image enhancement processing of the iris image is subjected to multi-scale decomposition.
  • the program includes instructions for performing the following steps:
  • Image quality evaluation is performed on the iris image by using at least one image quality evaluation index to obtain an image quality evaluation value.
  • the program further includes instructions for performing the following steps:
  • the positive sample set comprising X living iris images, the X being a positive integer
  • the first class target classifier and the second class target classifier are used as the preset iris living body detection classifier.
  • FIG. 4A is a schematic structural diagram of an iris living body detecting apparatus according to the embodiment.
  • the iris living body detecting device is applied to an electronic device, and the iris living body detecting device includes an obtaining unit 401, a disassembling unit 402, a determining unit 403, and a training unit 404, wherein
  • An obtaining unit 401 configured to acquire an iris image
  • Decomposition unit 402 configured to perform multi-scale decomposition on the iris image to obtain K high-frequency component images, where K is an integer greater than one;
  • a determining unit 403 configured to determine features between different high-frequency component images in the K high-frequency component images, to obtain M sets of features, where M is an integer greater than 1;
  • the training unit 404 is configured to train the M group features by using a preset iris living body detection classifier, and determine whether the iris image is from a living iris according to the training result.
  • FIG. 4B is a specific detailed structure of the determining unit 403 of the iris living body detecting apparatus described in FIG. 4A, and the determining unit 403 may include: an adjusting module 4031, a calculating module 4032, and a first extracting module 4033. ,details as follows:
  • the adjusting module 4031 is configured to adjust the size of all the high frequency component images in the K high frequency component images to be consistent;
  • a calculation module 4032 configured to perform subtraction of the adjusted K high-frequency component images according to a preset order to obtain the M result images
  • the first extraction module 4033 is configured to perform feature extraction on the M result images to obtain the M group features.
  • FIG. 4C is a specific refinement structure of the acquiring unit 401 of the iris living body detecting device described in FIG. 4A, and the obtaining unit 401 may include: an obtaining module 4011 and a second extracting module 4012, as follows: :
  • Obtaining module 4011 acquiring a test image
  • the second extraction module 4012 is configured to extract the iris image from the test image.
  • FIG. 4D is a modified structure of the iris living body detecting device described in FIG. 4A, and the device may further include: a first processing unit 405, as follows:
  • the first processing unit 405 is configured to perform image enhancement processing on the iris image, and is specifically used by the decomposition unit 402 to perform multi-scale decomposition on the image enhancement processed iris image.
  • FIG. 4E is a modified structure of the iris living body detecting device described in FIG. 4A, and the device may further include: a dividing unit 406, a first evaluating unit 407, and a selecting unit 408, as follows:
  • a dividing unit 406 configured to divide the iris image into P regions, to obtain the P region images, where P is an integer greater than 1;
  • a first evaluation unit 407 configured to perform image quality evaluation on the P area images respectively, to obtain the P image quality evaluation values
  • the selecting unit 408 is configured to select an image quality evaluation value that is greater than a preset image quality threshold from the P image quality evaluation values, obtain Q image quality evaluation values, and obtain an area image corresponding to the Q image quality evaluation values.
  • the Q is a positive integer that is not greater than the P, and is specifically used by the decomposing unit 402 to perform multi-scale decomposition on the region image corresponding to the Q image quality evaluation values.
  • FIG. 4F is a modified structure of the iris living body detecting device described in FIG. 4A.
  • the method further includes: a second evaluating unit 409 and a second processing unit 410, as follows:
  • a second evaluation unit 409 configured to perform image quality evaluation on the iris image to obtain an image quality evaluation value
  • the second processing unit 410 is configured to perform image enhancement processing on the iris image when the image quality evaluation value is lower than a preset quality threshold;
  • the decomposing unit 402 is specifically configured to:
  • the image enhancement processing of the iris image is subjected to multi-scale decomposition.
  • the second processing unit 410 is specifically configured to:
  • Image quality evaluation is performed on the iris image by using at least one image quality evaluation index to obtain an image quality evaluation value.
  • FIG. 4G is a modified structure of the iris living body detecting device described in FIG. 4A.
  • the method further includes: an extracting unit 411, as follows:
  • the obtaining unit 401 is configured to obtain a positive sample set, where the positive sample set includes X living iris images, the X is a positive integer, and obtain a negative sample set, where the negative sample set includes Y a non-living iris image, the Y being a positive integer;
  • the extracting unit 411 is configured to perform feature extraction on the positive sample set to obtain the X group feature, and perform feature extraction on the negative sample set to obtain the Y group feature.
  • the training unit 404 is configured to train the X group features by using a first specified classifier to obtain a first class target classifier; and use the second specified classifier to train the Y group features to obtain a second class a target classifier; the first class target classifier and the second class target classifier are used as the preset iris living body detection classifier.
  • the embodiment of the present application further provides another electronic device. As shown in FIG. 5, for the convenience of description, only the parts related to the embodiment of the present application are shown. If the specific technical details are not disclosed, refer to the method of the embodiment of the present application. section.
  • the electronic device may be any terminal device including a mobile phone, a tablet computer, a PDA (personal digital assistant), a POS (point of sales), an in-vehicle computer, and the like, and the electronic device is used as a mobile phone as an example:
  • FIG. 5 is a block diagram showing a partial structure of a mobile phone related to an electronic device provided by an embodiment of the present application.
  • the mobile phone includes: a radio frequency (RF) circuit 910, a memory 920, an input unit 930, a sensor 950, an audio circuit 960, a wireless fidelity (WiFi) module 970, an application processor AP980, and a power supply. 990 and other components.
  • RF radio frequency
  • the input unit 930 can be configured to receive input numeric or character information and to generate key signal inputs related to user settings and function controls of the handset.
  • the input unit 930 may include a touch display screen 933, an iris recognition device 931, and other input devices 932.
  • the iris recognition device 931 is coupled to the touch display screen 933, and the iris recognition area of the iris recognition device 931 can be located in the first area of the touch display screen 933.
  • the input unit 930 can also include other input devices 932.
  • other input devices 932 may include, but are not limited to, one or more of physical buttons, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.
  • the iris recognition device 931 is configured to: acquire an iris image
  • the AP 980 is configured to perform the following steps:
  • the M group features are trained by using a preset iris living body detection classifier, and it is judged according to the training result whether the iris image is from a living iris.
  • the AP 980 is the control center of the handset, which utilizes various interfaces and lines to connect various portions of the entire handset, and executes the handset by running or executing software programs and/or modules stored in the memory 920, as well as invoking data stored in the memory 920. A variety of functions and processing data to monitor the phone as a whole.
  • the AP 980 may include one or more processing units; preferably, the AP 980 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application, etc., and performs modulation and demodulation.
  • the processor primarily handles wireless communications. It can be understood that the above modem processor may not be integrated into the AP 980.
  • memory 920 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
  • the RF circuit 910 can be used for receiving and transmitting information.
  • RF circuit 910 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like.
  • LNA Low Noise Amplifier
  • RF circuitry 910 can also communicate with the network and other devices via wireless communication.
  • the above wireless communication may use any communication standard or protocol, including but not limited to global system of mobile communication (GSM), general packet radio service (GPRS), code division multiple access (code division) Multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), e-mail, short messaging service (SMS), and the like.
  • GSM global system of mobile communication
  • GPRS general packet radio service
  • CDMA code division multiple access
  • WCDMA wideband code division multiple access
  • LTE long term evolution
  • SMS short messaging service
  • the handset may also include at least one type of sensor 950, such as a light sensor, motion sensor, and other sensors.
  • the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the touch display screen according to the brightness of the ambient light, and the proximity sensor can turn off the touch display when the mobile phone moves to the ear. And / or backlight.
  • the accelerometer sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity.
  • the mobile phone can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for the mobile phone can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, no longer Narration.
  • the gesture of the mobile phone such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration
  • vibration recognition related functions such as pedometer, tapping
  • the mobile phone can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, no longer Narration.
  • An audio circuit 960, a speaker 961, and a microphone 962 can provide an audio interface between the user and the handset.
  • the audio circuit 960 can transmit the converted electrical data of the received audio data to the speaker 961 for conversion to the sound signal by the speaker 961; on the other hand, the microphone 962 converts the collected sound signal into an electrical signal by the audio circuit 960. After receiving, it is converted into audio data, and then the audio data is played by the AP 980, sent to the other mobile phone via the RF circuit 910, or the audio data is played to the memory 920 for further processing.
  • WiFi is a short-range wireless transmission technology
  • the mobile phone can help users to send and receive emails, browse web pages, and access streaming media through the WiFi module 970, which provides users with wireless broadband Internet access.
  • FIG. 5 shows the WiFi module 970, it can be understood that it does not belong to the essential configuration of the mobile phone, and may be omitted as needed within the scope of not changing the essence of the invention.
  • the mobile phone also includes a power source 990 (such as a battery) that supplies power to various components.
  • a power source 990 such as a battery
  • the power source can be logically connected to the AP980 through a power management system to manage functions such as charging, discharging, and power management through the power management system.
  • the mobile phone may further include a camera, a Bluetooth module, and the like, and details are not described herein again.
  • each step method flow can be implemented based on the structure of the mobile phone.
  • each unit function can be implemented based on the structure of the mobile phone.
  • the embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, the computer program causing the computer to execute any one of the iris living body detection methods as described in the foregoing method embodiments. Some or all of the steps.
  • the embodiment of the present application further provides a computer program product, comprising: a non-transitory computer readable storage medium storing a computer program, the computer program being operative to cause a computer to perform the operations as recited in the foregoing method embodiments Any or all of the steps of any iris in vivo detection method.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software program module.
  • the integrated unit if implemented in the form of a software program module and sold or used as a standalone product, may be stored in a computer readable memory.
  • a computer device which may be a personal computer, server or network device, etc.
  • the foregoing memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk, and the like, which can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Ophthalmology & Optometry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Processing (AREA)

Abstract

本申请实施例公开了一种虹膜活体检测方法及相关产品，方法包括：获取虹膜图像；对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。本申请实施例可深度挖掘虹膜图像的细节性特征，对该细节性特征进行训练，以判断虹膜图像来自于来活体虹膜，可提高虹膜活体检测的准确率。

Description

虹膜活体检测方法及相关产品
本申请要求2017年6月29日递交的发明名称为“虹膜活体检测方法及相关产品”的申请号201710514944.4的在先申请优先权，上述在先申请的内容以引入的方式并入本文本中。
技术领域
本申请涉及电子设备技术领域，具体涉及一种虹膜活体检测方法及相关产品。
背景技术
随着电子设备(手机、平板电脑等)的大量普及应用，电子设备能够支持的应用越来越多，功能越来越强大，电子设备向着多样化、个性化的方向发展，成为用户生活中不可缺少的电子用品。
目前来看，虹膜识别越来越受到电子设备生产厂商的青睐，虹膜识别的安全性也是其关注的重要问题之一。出于安全性考虑，通常情况下，会在虹膜识别之前，先对虹膜进行活体检测，但是目前的虹膜活体检测准确性并不高。
发明内容
本申请实施例提供了一种虹膜活体检测方法及相关产品，以期提高虹膜活体检测的准确性。
第一方面，本申请实施例提供一种虹膜活体检测方法，包括：
获取虹膜图像；
对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
第二方面，本申请实施例提供了一种虹膜活体检测装置，包括：
获取单元，用于获取虹膜图像；
分解单元，用于对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
确定单元，用于确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
训练单元，用于采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
第三方面，本申请实施例提供了一种电子设备，应用处理器AP和存储器；以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置成由所述AP执行，所述程序包括用于执行如本申请实施例第一方面中所描述的部分或全部步骤的指令。
第四方面，本申请实施例提供了一种计算机可读存储介质，其中，所述计算机可读存储介质存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如本申请实施例第一方面中所描述的部分或全部步骤。
第五方面，本申请实施例提供了一种计算机程序产品，其中，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如本申请实施例第一方面中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包。
实施本申请实施例，具有如下有益效果：
可以看出，本申请实施例中，获取虹膜图像，对虹膜图像进行多尺度分解，得到K个高频分量图像，K为大于1的整数，确定K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，M为大于1的整数，采用预设虹膜活体检测分类器对M组特征进行训练，并根据训练结果判断虹膜图像是否来自活体虹膜，从而，可对虹膜图像进行多尺度分解，以得到其高频分量图像，并根据该高频分量图像得到虹膜图像中的细节性特征，从而，深度挖掘虹膜图像的细节性特征，对该细节性特征进行训练，以判断虹膜图像来自于来活体虹膜，可提高虹膜活体检测的准确率。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1A是本申请实施例提供的一种示例智能手机的架构示意图；
图1B是本申请实施例公开的一种虹膜活体检测方法的流程示意图；
图2是本申请实施例公开的另一种虹膜活体检测方法的流程示意图；
图3是本申请实施例提供的一种电子设备的结构示意图；
图4A是本申请实施例提供的一种虹膜活体检测装置的结构示意图；
图4B是本申请实施例提供的图4A所描述的虹膜活体检测装置的确定单元的结构示意图；
图4C是本申请实施例提供的图4A所描述的虹膜活体检测装置的获取单元的结构示意图；
图4D是本申请实施例提供的一种虹膜活体检测装置的另一结构示意图；
图4E是本申请实施例提供的一种虹膜活体检测装置的另一结构示意图；
图4F是本申请实施例提供的一种虹膜活体检测装置的另一结构示意图；
图4G是本申请实施例提供的一种虹膜活体检测装置的另一结构示意图；
图5是本申请实施例公开的另一种电子设备的结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、***、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
本申请实施例所涉及到的电子设备可以包括各种具有无线通信功能的手持设备、车载设备、可穿戴设备、计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的用户设备(User Equipment，UE)，移动台(Mobile Station，MS)，终端设备(terminal device)等等。为方便描述，上面提到的设 备统称为电子设备。下面对本申请实施例进行详细介绍。如图1A所示的一种示例智能手机100，该智能手机100的虹膜识别装置可以包括红外补光灯21和红外摄像头22，在虹膜识别装置工作过程中，红外补光灯21的光线打到虹膜上之后，经过虹膜反射回红外摄像头22，虹膜识别装置采集虹膜图像，23可为前置摄像头。
请参阅图1B，可应用于如图1A所描述的智能手机，为本申请实施例提供的一种虹膜活体检测方法的实施例流程示意图。本实施例中所描述的虹膜活体检测方法，包括以下步骤：
101、获取虹膜图像。
其中，本申请实施例中的虹膜图像可为单指虹膜区域的图像，或者，包含虹膜区域的图像(例如，一只人眼图像)。例如，在用户使用电子设备时，可通过虹膜识别装置获取虹膜图像。
102、对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数。
其中，可采用多尺度分解算法对虹膜图像进行多尺度图像，得到低频分量图像和多个高频分量图像，上述多尺度分解算法可包括但不仅限于：小波变换、拉普拉斯变换、轮廓波变换(contourlet transform，CT)、非下采样轮廓波变换(non-subsampled contourlet transform，NSCT)、剪切波变换等等，以轮廓波为例，采用轮廓波变换对虹膜图像进行多尺度分解，可以得到一个低频分量图像和多个高频分量图像，并且该多个高频分量图像中每一图像的尺寸大小不一，以NSCT为例，采用NSCT对虹膜图像进行多尺度分解，可以得到一个低频分量图像和多个高频分量图像，并且该多个高频分量图像中每一图像的尺寸大小一样。对于高频分量而言，其包含了较多图像的细节信息。
可选的，在上述步骤101与步骤102之间，还可以包含如下步骤：
对所述虹膜图像进行图像增强处理。
其中，图像增强处理可包括但不仅限于：图像去噪(例如，小波变换进行图像去噪)、图像复原(例如，维纳滤波)、暗视觉增强算法(例如，直方图均衡化、灰度拉伸等等)，在对虹膜图像进行图像增强处理之后，虹膜图像的质量可在一定程度上得到提升。进一步地，在执行步骤102的过程中，可对增强处理之后的虹膜图像进行多尺度分解。
可选地，在上述步骤101与步骤102之间，还可以包含如下步骤：
A1、对所述虹膜图像进行图像质量评价，得到图像质量评价值；
A2、在所述图像质量评价值低于预设质量阈值时，对所述虹膜图像进行图像增强处理。
其中，上述预设质量阈值可由用户自行设置或者***默认，可先对虹膜图像进行图像质量评价，得到一个图像质量评价值，通过该图像质量评价值判断该虹膜图像的质量是好还是坏，在图像质量评价值大于或等于预设质量阈值时，可认为虹膜图像质量好，在图像质量评价值小于预设质量阈值时，可认为虹膜图像质量差，进而，可对虹膜图像进行图像增强处理。进一步地，在执行步骤102的过程中，可对增强处理之后的虹膜图像进行多尺度分解。
其中，上述步骤A1中，可采用至少一个图像质量评价指标对虹膜图像进行图像质量评价，从而，得到图像质量评价值。
可包含多个图像质量评价指标，每一图像质量评价指标也对应一个权重，如此，每一图像质量评价指标对虹膜图像进行图像质量评价时，均可得到一个评价结果，最终，进行加权运算，也就得到最终的图像质量评价值。图像质量评价指标可包括但不仅限于：均值、标准差、熵、清晰度、信噪比等等。
需要说明的是，由于采用单一评价指标对图像质量进行评价时，具有一定的局限性，因此，可采用多个图像质量评价指标对图像质量进行评价，当然，对图像质量进行评价时，并非图像质量评价指标越多越好，因为图像质量评价指标越多，图像质量评价过程的计算复杂度越高，也不见得图像质量评价效果越好，因此，在对图像质量评价要求较高的情况下，可采用2～10个图像质量评价指标对图像质量进行评价。具体地，选取图像质量评价指标的个数及哪个指标，依据具体实现情况而定。当然，也得结合具体地场景选取图像质量评价指标，在暗环境下进行图像质量评价和亮环境下进行图像质量评价选取的图像质量指标可不一样。
可选地，在对图像质量评价精度要求不高的情况下，可用一个图像质量评价指标进行评价，例如，以熵对待处理图像进行图像质量评价值，可认为熵越大，则说明图像质量越好，相反地，熵越小，则说明图像质量越差。
可选地，在对图像质量评价精度要求较高的情况下，可以采用多个图像质量评价指标对图像进行评价，在多个图像质量评价指标对图像进行图像质量评价时，可设置该多个图像质量评价指标中每一图像质量评价指标的权重，可得到多个图像质量评价值，根据该多个图像质量评价值及其对应的权重可得到最终的图像质量评价值，例如，三个图像质量评价指标分别为：A指标、B指标和C指标，A的权重为a1，B的权重为a2，C的权重为a3，采用A、B和C对某一图像进行图像质量评价时，A对应的图像质量评价值为b1，B对应的 图像质量评价值为b2，C对应的图像质量评价值为b3，那么，最后的图像质量评价值＝a1b1+a2b2+a3b3。通常情况下，图像质量评价值越大，说明图像质量越好。
可选地，在上述步骤101-步骤102之间，还可以包含如下步骤：
B1、将所述虹膜图像划分为P个区域，得到所述P个区域图像，所述P为大于1的整数；
B2、分别对所述P个区域图像进行图像质量评价，得到所述P个图像质量评价值；
B3、从所述P个图像质量评价值中选取大于预设图像质量阈值的图像质量评价值，得到Q个图像质量评价值，并获取该Q个图像质量评价值对应的区域图像，所述Q为不大于所述P的正整数。
其中，上述P可由用户指定或者***默认，P为大于1的整数。在执行上述步骤B1过程中，可按照预设网格将虹膜图像划分为P个区域，可得到P个区域图像，上述P个区域相互独立，进而，可对该P个区域图像进行图像质量评价，具体如何进行图像质量评价，可参照上述描述，在此不再赘述，可得到P个图像质量评价值。上述预设图像质量阈值可由用户自行设置或者***默认，可从上述P个图像质量评价值中选取大于预设图像质量阈值的图像质量质量评价值，可得到Q个图像质量评价值，并获取该Q个图像质量评价值对应的区域图像，Q为小于或等于P的正整数。那么，在步骤102中，则只需要对Q个图像质量评价值对应的区域图像进行多尺度分解即可。如此，可从虹膜图像中选取清晰区域的图像进行活体检测，可提高活体检测效率，毕竟有些时候图像不够清晰会有较高的误识别率，而只对清晰区域进行活体检测，则一方面可以减少检测面积，另一方面可降低误识别率。
103、确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数。
其中，本申请实施例可通过不同高频分量图像之间的差异性确定图像的精细特征，该精细特征很难被伪造，从而，可用于虹膜活体检测。
可选地，上述步骤103中，确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，可包括如下步骤：
31、将所述K个高频分量图像中所有高频分量图像的尺寸大小调整为一致；
32、将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像；
33、分别对所述M个结果图像进行特征提取，得到所述M组特征。
其中，可以从K个高频分量图像中选取一个高频分量图像作为基准图像，以该基准图像的尺寸作为基准尺寸，将其他的高频分量图像的尺寸大小调整为该基准尺寸，或者，可将K个高频分量图像中所有高频分量图像调整为指定尺寸，该指定尺寸可由用户自行设置或者***默认。上述预设顺序可为随机顺序，或者，K个高频分量图像的生成顺序。进而，可根据K个高频分量图像中的不同高频分量图像按照预设顺序进行作差，可得到M个结果图像，举例说明下，以图像A与B为例，结果图像＝|A-B|，即A与B对应像素点相减并取绝对值，进而，对M个结果进行特征提取，可得到M组特征，每一结果图像对应一组特征，上述特征提取可采用如下算法实现：Harris角点检测算法、尺度不变特征变换(scale invariant feature transform，SIFT)、SUSAN角点检测算法等等，在此不再赘述。
可选地，上述步骤32中，所述K个高频分量图像中每一高频分量图像对应一个层次，则将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像，可包括如下步骤：
按照层次将调整后的所述K个高频分量划分为多个类别，分别计算每个类别中不同高频分量图像之间的作减运算，得到M个结果图像。上述层次与用户预先设置的系数有关，以下具体举例说明下:
在采用NSCT算法对图像进行多尺度分解的过程中，在非下采样金字塔分解过后，令方向滤波器组的某一层分解级数为0，则该层就不进行多方向分解，令多方向分解层数为J，经过J层分解，会得到1个低频分量图像与
Figure PCTCN2018090649-appb-000001
个高频分量图像，其中2 j为尺度j下的方向分解得到的子带个数。其中，非下采样选择金字塔滤波器“dfilt”，非下采样方向滤波器组选择“pfilt”，方向滤波器组的分解层数分别为“1，3，3，4”，每一层的方向分量个数分别为2,8,8,16，即其对应4个层次，第一个层次对应2个高频分量图像，第二个层次对应8个高频分量图像，第三个层次对应8个高频分量图像，第四个层次对应16个高频分量图像，可以看出不同层次可以得到不同的图像。
104、采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
其中，可采用预设虹膜活体检测分类器对M组特征进行训练，得到训练结果，并根据该训练结果判断虹膜图像是否来自活体虹膜。训练结果可为一个概率值，例如，概率值为80％，则可认为虹膜图像来自于活体虹膜，低于则认为虹膜图像来自于非活体虹膜，该非活体虹膜可为以下一种：3D打印的虹膜、 照片中的虹膜、没有生命特征的人的虹膜，在此不做限定。
其中，上述预设虹膜活体检测分类器可在执行上述本申请实施例之前设置，其主要设置可包含如下步骤C1-C7：
C1、获取正样本集，所述正样本集包含X个活体虹膜图像，所述X为正整数；
C2、获取负样本集，所述负样本集包含Y个非活体虹膜图像，所述Y为正整数；
C3、对所述正样本集进行特征提取，得到所述X组特征；
C4、对所述负样本集进行特征提取，得到所述Y组特征；
C5、采用第一指定分类器对所述X组特征进行训练，得到第一类目标分类器；
C6、采用第二指定分类器对所述Y组特征进行训练，得到第二类目标分类器；
C7、将所述第一类目标分类器和所述第二类目标分类器作为所述预设虹膜活体检测分类器。
其中，X与Y均可由用户设置，其具体数量越大，则分类器分类效果越好。上述C3、C4中的特征提取的具体方式可参考上述步骤102和步骤103，另外，第一指定分类器和第二指定分类器可为同一分类器或者不同的分类器，无论是第一指定分类器还是第二指定分类器均可包括但不仅限于：支持向量机(support vector machine，SVM)、遗传算法分类器、神经网络算法分类器、级联分类器(如遗传算法+SVM)等等。
可以看出，本申请实施例中，获取虹膜图像，对虹膜图像进行多尺度分解，得到K个高频分量图像，K为大于1的整数，确定K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，M为大于1的整数，采用预设虹膜活体检测分类器对M组特征进行训练，并根据训练结果判断虹膜图像是否来自活体虹膜，从而，可对虹膜图像进行多尺度分解，以得到其高频分量图像，并根据该高频分量图像得到虹膜图像中的细节性特征，从而，深度挖掘虹膜图像的细节性特征，对该细节性特征进行训练，以判断虹膜图像来自于来活体虹膜，可提高虹膜活体检测的准确率。
请参阅图2，为本申请实施例提供的一种虹膜活体检测方法的实施例流程示意图。本实施例中所描述的虹膜活体检测方法，包括以下步骤：
201、获取测试图像。
其中，可利用电子设备的摄像头获取人脸图像，将该人脸图像作为测试图像。当然，测试图像还可以为人眼图像。
202、从所述测试图像中提取虹膜图像。
203、对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数。
204、确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数。
205、采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
其中，上述步骤202-步骤205的具体描述可参照图1B所描述的虹膜活体检测方法的对应步骤，在此不再赘述。
可以看出，本申请实施例中，获取测试图像，从测试图像中提取虹膜图像，对虹膜图像进行多尺度分解，得到K个高频分量图像，K为大于1的整数，确定K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，M为大于1的整数，采用预设虹膜活体检测分类器对M组特征进行训练，并根据训练结果判断虹膜图像是否来自活体虹膜，从而，可对虹膜图像进行多尺度分解，以得到其高频分量图像，并根据该高频分量图像得到虹膜图像中的细节性特征，从而，深度挖掘虹膜图像的细节性特征，对该细节性特征进行训练，以判断虹膜图像来自于来活体虹膜，可提高虹膜活体检测的准确率。
请参阅图3，图3是本申请实施例提供的一种电子设备，包括：应用处理器AP和存储器；以及一个或多个程序，该一个或多个程序被存储在存储器中，并且被配置成由AP执行，程序包括用于执行以下步骤的指令：
获取虹膜图像；
对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
在一个可能的示例中，在所述确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征方面，所述程序包括用于执行以下步骤的指令：
将所述K个高频分量图像中所有高频分量图像的尺寸大小调整为一致；
将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像；
分别对所述M个结果图像进行特征提取，得到所述M组特征。
在一个可能的示例中，所述K个高频分量图像中每一高频分量图像对应一个层次，在所述将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像方面，所述程序包括用于执行以下步骤的指令：
按照层次将调整后的所述K个高频分量划分为多个类别，分别计算每个类别中不同高频分量图像之间的作减运算，得到M个结果图像。
在一个可能的示例中，在所述获取虹膜图像方面，所述程序包括用于执行以下步骤的指令：
获取测试图像；
从所述测试图像中提取所述虹膜图像。
在一个可能的示例中，所述程序还包括用于执行以下步骤的指令：
对所述虹膜图像进行图像增强处理；在所述对所述虹膜图像进行多尺度分解方面，所述程序包括用于执行以下步骤的指令：
对所述图像增强处理后的虹膜图像进行多尺度分解。
在一个可能的示例中，所述程序还包括用于执行以下步骤的指令：
将所述虹膜图像划分为P个区域，得到所述P个区域图像，所述P为大于1的整数；
分别对所述P个区域图像进行图像质量评价，得到所述P个图像质量评价值；
从所述P个图像质量评价值中选取大于预设图像质量阈值的图像质量评价值，得到Q个图像质量评价值，并获取该Q个图像质量评价值对应的区域图像，所述Q为不大于所述P的正整数；在所述对所述虹膜图像进行多尺度分解方面，所述程序包括用于执行以下步骤的指令：
对所述Q个图像质量评价值对应的区域图像进行多尺度分解。
在一个可能的示例中，所述程序还包括用于执行以下步骤的指令:
对所述虹膜图像进行图像质量评价，得到图像质量评价值；
在所述图像质量评价值低于预设质量阈值时，对所述虹膜图像进行图像增强处理；
所述对所述虹膜图像进行多尺度分解，所述程序包括用于执行以下步骤的指令：
对所述图像增强处理后的虹膜图像进行多尺度分解。
在一个可能的示例中，在所述对所述虹膜图像进行图像质量评价，得到图像质量评价值方面，所述程序包括用于执行以下步骤的指令：
采用至少一个图像质量评价指标对所述虹膜图像进行图像质量评价，得到图像质量评价值。
在一个可能的示例中，所述程序还包括用于执行以下步骤的指令：
获取正样本集，所述正样本集包含X个活体虹膜图像，所述X为正整数；
获取负样本集，所述负样本集包含Y个非活体虹膜图像，所述Y为正整数；
对所述正样本集进行特征提取，得到所述X组特征；
对所述负样本集进行特征提取，得到所述Y组特征；
采用第一指定分类器对所述X组特征进行训练，得到第一类目标分类器；
采用第二指定分类器对所述Y组特征进行训练，得到第二类目标分类器；
将所述第一类目标分类器和所述第二类目标分类器作为所述预设虹膜活体检测分类器。
请参阅图4A，图4A是本实施例提供的一种虹膜活体检测装置的结构示意图。该虹膜活体检测装置应用于电子设备，虹膜活体检测装置包括获取单元401、分解单元402、确定单元403和训练单元404，其中，
获取单元401，用于获取虹膜图像；
分解单元402，用于对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
确定单元403，用于确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
训练单元404，用于采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
可选地，如图4B，图4B是图4A所描述的虹膜活体检测装置的确定单元403的具体细节结构，所述确定单元403可包括：调整模块4031、计算模块4032和第一提取模块4033，具体如下：
调整模块4031，用于将所述K个高频分量图像中所有高频分量图像的尺寸大小调整为一致；
计算模块4032，用于将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像；
第一提取模块4033，用于分别对所述M个结果图像进行特征提取，得到所述M组特征。
可选地，如图4C，图4C为图4A所描述的虹膜活体检测装置的获取单元401的具体细化结构，所述获取单元401可包括：获取模块4011和第二提取 模块4012，具体如下：
获取模块4011，获取测试图像；
第二提取模块4012，用于从所述测试图像中提取所述虹膜图像。
可选地，如图4D，图4D为图4A所描述的虹膜活体检测装置的变型结构，所述装置还可包括：第一处理单元405，具体如下：
第一处理单元405，用于对所述虹膜图像进行图像增强处理，并由所述分解单元402具体用于对所述图像增强处理后的虹膜图像进行多尺度分解。
可选地，如图4E，图4E为图4A所描述的虹膜活体检测装置的变型结构，所述装置还可包括：划分单元406、第一评价单元407和选取单元408，具体如下：
划分单元406，用于将所述虹膜图像划分为P个区域，得到所述P个区域图像，所述P为大于1的整数；
第一评价单元407，用于分别对所述P个区域图像进行图像质量评价，得到所述P个图像质量评价值；
选取单元408，用于从所述P个图像质量评价值中选取大于预设图像质量阈值的图像质量评价值，得到Q个图像质量评价值，并获取该Q个图像质量评价值对应的区域图像，所述Q为不大于所述P的正整数，并由所述分解单元402具体用于对所述Q个图像质量评价值对应的区域图像进行多尺度分解。
可选地，如图4F，图4F为图4A所描述的虹膜活体检测装置的变型结构，其与图4A相比较，还可以包括：第二评价单元409和第二处理单元410，具体如下：
第二评价单元409，用于对所述虹膜图像进行图像质量评价，得到图像质量评价值；
第二处理单元410，用于在所述图像质量评价值低于预设质量阈值时，对所述虹膜图像进行图像增强处理；
在所述对所述虹膜图像进行多尺度分解方面，所述分解单元402具体用于：
对所述图像增强处理后的虹膜图像进行多尺度分解。
可选地，在所述对所述虹膜图像进行图像质量评价，得到图像质量评价值方面，所述第二处理单元410具体用于：
采用至少一个图像质量评价指标对所述虹膜图像进行图像质量评价，得到图像质量评价值。
可选地，如图4G，图4G为图4A所描述的虹膜活体检测装置的变型结构， 其与图4A相比较，还可以包括：提取单元411，具体如下：
所述获取单元401，用于获取虹膜图像之前，获取正样本集，所述正样本集包含X个活体虹膜图像，所述X为正整数；以及获取负样本集，所述负样本集包含Y个非活体虹膜图像，所述Y为正整数；
所述提取单元411，用于对所述正样本集进行特征提取，得到所述X组特征；对所述负样本集进行特征提取，得到所述Y组特征；
所述训练单元404，用于采用第一指定分类器对所述X组特征进行训练，得到第一类目标分类器；采用第二指定分类器对所述Y组特征进行训练，得到第二类目标分类器；将所述第一类目标分类器和所述第二类目标分类器作为所述预设虹膜活体检测分类器。
可以理解的是，本实施例的虹膜活体检测装置的各程序模块的功能可根据上述方法实施例中的方法具体实现，其具体实现过程可以参照上述方法实施例的相关描述，此处不再赘述。
本申请实施例还提供了另一种电子设备，如图5所示，为了便于说明，仅示出了与本申请实施例相关的部分，具体技术细节未揭示的，请参照本申请实施例方法部分。该电子设备可以为包括手机、平板电脑、PDA(personal digital assistant，个人数字助理)、POS(point of sales，销售终端)、车载电脑等任意终端设备，以电子设备为手机为例：
图5示出的是与本申请实施例提供的电子设备相关的手机的部分结构的框图。参考图5，手机包括：射频(radio frequency，RF)电路910、存储器920、输入单元930、传感器950、音频电路960、无线保真(wireless fidelity，WiFi)模块970、应用处理器AP980、以及电源990等部件。本领域技术人员可以理解，图5中示出的手机结构并不构成对手机的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
下面结合图5对手机的各个构成部件进行具体的介绍：
输入单元930可用于接收输入的数字或字符信息，以及产生与手机的用户设置以及功能控制有关的键信号输入。具体地，输入单元930可包括触控显示屏933、虹膜识别装置931以及其他输入设备932。虹膜识别装置931结合至触控显示屏933，虹膜识别装置931的虹膜识别区域可位于触控显示屏933的第一区域。输入单元930还可以包括其他输入设备932。具体地，其他输入设备932可以包括但不限于物理按键、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
其中，所述虹膜识别装置931用于：获取虹膜图像；
所述AP980，用于执行如下步骤：
对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
AP980是手机的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在存储器920内的软件程序和/或模块，以及调用存储在存储器920内的数据，执行手机的各种功能和处理数据，从而对手机进行整体监控。可选的，AP980可包括一个或多个处理单元；优选的，AP980可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作***、用户界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到AP980中。
此外，存储器920可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
RF电路910可用于信息的接收和发送。通常，RF电路910包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器(Low Noise Amplifier，LNA)、双工器等。此外，RF电路910还可以通过无线通信与网络和其他设备通信。上述无线通信可以使用任一通信标准或协议，包括但不限于全球移动通讯***(global system of mobile communication，GSM)、通用分组无线服务(general packet radio service，GPRS)、码分多址(code division multiple access，CDMA)、宽带码分多址(wideband code division multiple access,WCDMA)、长期演进(long term evolution，LTE)、电子邮件、短消息服务(short messaging service，SMS)等。
手机还可包括至少一种传感器950，比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节触控显示屏的亮度，接近传感器可在手机移动到耳边时，关闭触控显示屏和/或背光。作为运动传感器的一种，加速计传感器可检测各个方向上(一般为三轴)加速度的大小，静止时可检测出重力的大小及方向，可用于识别手机姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等；至于手机还可 配置的陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
音频电路960、扬声器961，传声器962可提供用户与手机之间的音频接口。音频电路960可将接收到的音频数据转换后的电信号，传输到扬声器961，由扬声器961转换为声音信号播放；另一方面，传声器962将收集的声音信号转换为电信号，由音频电路960接收后转换为音频数据，再将音频数据播放AP980处理后，经RF电路910以发送给比如另一手机，或者将音频数据播放至存储器920以便进一步处理。
WiFi属于短距离无线传输技术，手机通过WiFi模块970可以帮助用户收发电子邮件、浏览网页和访问流式媒体等，它为用户提供了无线的宽带互联网访问。虽然图5示出了WiFi模块970，但是可以理解的是，其并不属于手机的必须构成，完全可以根据需要在不改变发明的本质的范围内而省略。
手机还包括给各个部件供电的电源990(比如电池)，优选的，电源可以通过电源管理***与AP980逻辑相连，从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。
尽管未示出，手机还可以包括摄像头、蓝牙模块等，在此不再赘述。
前述图1B～图2所示的实施例中，各步骤方法流程可以基于该手机的结构实现。
前述图3、图4A～图4G所示的实施例中，各单元功能可以基于该手机的结构实现。
本申请实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行如上述方法实施例中记载的任何一种虹膜活体检测方法的部分或全部步骤。
本申请实施例还提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如上述方法实施例中记载的任何一种虹膜活体检测方法的部分或全部步骤。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详 述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件程序模块的形式实现。
所述集成的单元如果以软件程序模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、ROM、RAM、磁盘或光盘等。
以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种虹膜活体检测方法，其特征在于，包括：
    获取虹膜图像；
    对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
    确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
    采用预设虹膜活体检测分类器对所述M组特征进行训练，并根据训练结果判断所述虹膜图像是否来自活体虹膜。
  2. 根据权利要求1所述的方法，其特征在于，所述确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，包括：
    将所述K个高频分量图像中所有高频分量图像的尺寸大小调整为一致；
    将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像；
    分别对所述M个结果图像进行特征提取，得到所述M组特征。
  3. 根据权利要求2所述的方法，其特征在于，所述K个高频分量图像中每一高频分量图像对应一个层次，所述将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像，包括：
    按照层次将调整后的所述K个高频分量划分为多个类别，分别计算每个类别中不同高频分量图像之间的作减运算，得到M个结果图像。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，所述获取虹膜图像，包括：
    获取测试图像；
    从所述测试图像中提取所述虹膜图像。
  5. 根据权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    对所述虹膜图像进行图像增强处理；
    所述对所述虹膜图像进行多尺度分解，包括：
    对所述图像增强处理后的虹膜图像进行多尺度分解。
  6. 根据权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    将所述虹膜图像划分为P个区域，得到所述P个区域图像，所述P为大于1的整数；
    分别对所述P个区域图像进行图像质量评价，得到所述P个图像质量评价值；
    从所述P个图像质量评价值中选取大于预设图像质量阈值的图像质量评价值，得到Q个图像质量评价值，并获取该Q个图像质量评价值对应的区域图像，所述Q为不大于所述P的正整数；
    所述对所述虹膜图像进行多尺度分解，包括：
    对所述Q个图像质量评价值对应的区域图像进行多尺度分解。
  7. 根据权利要求1-4任一项所述的方法，其特征在于，所述方法还包括：
    对所述虹膜图像进行图像质量评价，得到图像质量评价值；
    在所述图像质量评价值低于预设质量阈值时，对所述虹膜图像进行图像增强处理；
    所述对所述虹膜图像进行多尺度分解，包括：
    对所述图像增强处理后的虹膜图像进行多尺度分解。
  8. 根据权利要求7所述的方法，其特征在于，所述对所述虹膜图像进行图像质量评价，得到图像质量评价值，包括：
    采用至少一个图像质量评价指标对所述虹膜图像进行图像质量评价，得到图像质量评价值。
  9. 根据权利要求1-8任一项所述的方法，其特征在于，所述方法还包括：
    获取正样本集，所述正样本集包含X个活体虹膜图像，所述X为正整数；
    获取负样本集，所述负样本集包含Y个非活体虹膜图像，所述Y为正整数；
    对所述正样本集进行特征提取，得到所述X组特征；
    对所述负样本集进行特征提取，得到所述Y组特征；
    采用第一指定分类器对所述X组特征进行训练，得到第一类目标分类器；
    采用第二指定分类器对所述Y组特征进行训练，得到第二类目标分类器；
    将所述第一类目标分类器和所述第二类目标分类器作为所述预设虹膜活体检测分类器。
  10. 一种虹膜活体检测装置，其特征在于，包括：
    获取单元，用于获取虹膜图像；
    分解单元，用于对所述虹膜图像进行多尺度分解，得到K个高频分量图像，所述K为大于1的整数；
    确定单元，用于确定所述K个高频分量图像中不同高频分量图像之间的特征，得到M组特征，所述M为大于1的整数；
    训练单元，用于采用预设虹膜活体检测分类器对所述M组特征进行训练， 并根据训练结果判断所述虹膜图像是否来自活体虹膜。
  11. 根据权利要求10所述的装置，其特征在于，所述确定单元包括：
    调整模块，用于将所述K个高频分量图像中所有高频分量图像的尺寸大小调整为一致；
    计算模块，用于将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像；
    第一提取模块，用于分别对所述M个结果图像进行特征提取，得到所述M组特征。
  12. 根据权利要求11所述的装置，其特征在于，所述K个高频分量图像中每一高频分量图像对应一个层次，在所述将调整后的所述K个高频分量图像按照预设顺序进行减运算，得到所述M个结果图像方面，所述计算模块具体用于：
    按照层次将调整后的所述K个高频分量划分为多个类别，分别计算每个类别中不同高频分量图像之间的作减运算，得到M个结果图像。
  13. 根据权利要求10-12任一项所述的装置，其特征在于，所述获取单元包括：
    获取模块，获取测试图像；
    第二提取模块，用于从所述测试图像中提取所述虹膜图像。
  14. 根据权利要求10-13任一项所述的装置，其特征在于，所述装置还包括：
    第一处理单元，用于对所述虹膜图像进行图像增强处理，并由所述分解单元具体用于对所述图像增强处理后的虹膜图像进行多尺度分解。
  15. 根据权利要求10-13任一项所述的装置，其特征在于，所述装置还包括：
    划分单元，用于将所述虹膜图像划分为P个区域，得到所述P个区域图像，所述P为大于1的整数；
    第一评价单元，用于分别对所述P个区域图像进行图像质量评价，得到所述P个图像质量评价值；
    选取单元，用于从所述P个图像质量评价值中选取大于预设图像质量阈值的图像质量评价值，得到Q个图像质量评价值，并获取该Q个图像质量评价值对应的区域图像，所述Q为不大于所述P的正整数，并由所述分解单元具体用于对所述Q个图像质量评价值对应的区域图像进行多尺度分解。
  16. 根据权利要求10-13任一项所述的装置，其特征在于，所述装置还包 括：
    第二评价单元，用于对所述虹膜图像进行图像质量评价，得到图像质量评价值；
    第二处理单元，用于在所述图像质量评价值低于预设质量阈值时，对所述虹膜图像进行图像增强处理；
    在所述对所述虹膜图像进行多尺度分解方面，所述分解单元具体用于：
    对所述图像增强处理后的虹膜图像进行多尺度分解。
  17. 根据权利要求16所述的装置，其特征在于，在所述对所述虹膜图像进行图像质量评价，得到图像质量评价值方面，所述第二处理单元具体用于：
    采用至少一个图像质量评价指标对所述虹膜图像进行图像质量评价，得到图像质量评价值。
  18. 一种电子设备，其特征在于，包括：应用处理器AP和存储器；以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置成由所述AP执行，所述程序包括用于如权利要求1-9任一项方法的指令。
  19. 一种计算机可读存储介质，其特征在于，其存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1-9任一项所述的方法。
  20. 一种计算机程序产品，其特征在于，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序可操作来使计算机执行如权利要求1-9任一项所述的方法。
PCT/CN2018/090649 2017-06-29 2018-06-11 虹膜活体检测方法及相关产品 WO2019001254A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710514944.4 2017-06-29
CN201710514944.4A CN107368791A (zh) 2017-06-29 2017-06-29 虹膜活体检测方法及相关产品

Publications (1)

Publication Number Publication Date
WO2019001254A1 true WO2019001254A1 (zh) 2019-01-03

Family

ID=60305747

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/090649 WO2019001254A1 (zh) 2017-06-29 2018-06-11 虹膜活体检测方法及相关产品

Country Status (2)

Country Link
CN (1) CN107368791A (zh)
WO (1) WO2019001254A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110163174A (zh) * 2019-05-27 2019-08-23 成都科睿埃科技有限公司 一种基于单目摄像头的活体人脸检测方法
CN111325271A (zh) * 2020-02-18 2020-06-23 Oppo广东移动通信有限公司 图像分类方法及装置
CN113807166A (zh) * 2021-07-31 2021-12-17 深圳市数商时代科技有限公司 图像处理方法、装置及存储介质

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107368791A (zh) * 2017-06-29 2017-11-21 广东欧珀移动通信有限公司 虹膜活体检测方法及相关产品
CN108062575A (zh) * 2018-01-03 2018-05-22 广东电子工业研究院有限公司 一种高相似度图像识别与分类方法
CN111611848B (zh) * 2020-04-02 2024-02-06 北京中科虹霸科技有限公司 尸体虹膜识别方法和装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6760467B1 (en) * 1999-03-23 2004-07-06 Lg Electronics Inc. Falsification discrimination method for iris recognition system
CN1924892A (zh) * 2006-09-21 2007-03-07 杭州电子科技大学 虹膜识别中的活体检测方法及装置
CN101833646A (zh) * 2009-03-11 2010-09-15 中国科学院自动化研究所 一种虹膜活体检测方法
CN107368791A (zh) * 2017-06-29 2017-11-21 广东欧珀移动通信有限公司 虹膜活体检测方法及相关产品

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1209073C (zh) * 2001-12-18 2005-07-06 中国科学院自动化研究所 基于活体虹膜的身份识别方法
CN1330275C (zh) * 2003-12-07 2007-08-08 倪蔚民 基于虹膜纹理分析的生物测定方法
CN101042730A (zh) * 2006-03-23 2007-09-26 长春吉大计算机发展有限责任公司 基于小波新技术的虹膜安全认证预处理方法
CN101344913B (zh) * 2007-07-10 2011-11-09 电子科技大学中山学院 一种通过提取虹膜纹理特征进行身份识别的方法
CN101241550B (zh) * 2008-01-19 2011-04-13 电子科技大学中山学院 一种虹膜图像质量判断方法
CN106327457B (zh) * 2016-08-23 2020-02-18 北京金山安全软件有限公司 一种图片处理方法、装置及设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6760467B1 (en) * 1999-03-23 2004-07-06 Lg Electronics Inc. Falsification discrimination method for iris recognition system
CN1924892A (zh) * 2006-09-21 2007-03-07 杭州电子科技大学 虹膜识别中的活体检测方法及装置
CN101833646A (zh) * 2009-03-11 2010-09-15 中国科学院自动化研究所 一种虹膜活体检测方法
CN107368791A (zh) * 2017-06-29 2017-11-21 广东欧珀移动通信有限公司 虹膜活体检测方法及相关产品

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110163174A (zh) * 2019-05-27 2019-08-23 成都科睿埃科技有限公司 一种基于单目摄像头的活体人脸检测方法
CN111325271A (zh) * 2020-02-18 2020-06-23 Oppo广东移动通信有限公司 图像分类方法及装置
CN111325271B (zh) * 2020-02-18 2023-09-12 Oppo广东移动通信有限公司 图像分类方法及装置
CN113807166A (zh) * 2021-07-31 2021-12-17 深圳市数商时代科技有限公司 图像处理方法、装置及存储介质
CN113807166B (zh) * 2021-07-31 2024-03-08 深圳市数商时代科技有限公司 图像处理方法、装置及存储介质

Also Published As

Publication number Publication date
CN107368791A (zh) 2017-11-21

Similar Documents

Publication Publication Date Title
CN107292285B (zh) 虹膜活体检测方法及相关产品
WO2019011206A1 (zh) 活体检测方法及相关产品
WO2019001254A1 (zh) 虹膜活体检测方法及相关产品
CN107590461B (zh) 人脸识别方法及相关产品
WO2019020014A1 (zh) 解锁控制方法及相关产品
RU2731370C1 (ru) Способ распознавания живого организма и терминальное устройство
WO2019052329A1 (zh) 人脸识别方法及相关产品
CN107657218B (zh) 人脸识别方法及相关产品
CN107403147B (zh) 虹膜活体检测方法及相关产品
CN107451454B (zh) 解锁控制方法及相关产品
WO2019024717A1 (zh) 防伪处理方法及相关产品
WO2019011098A1 (zh) 解锁控制方法及相关产品
US11055547B2 (en) Unlocking control method and related products
CN107784271B (zh) 指纹识别方法及相关产品
WO2019015418A1 (zh) 解锁控制方法及相关产品
CN107451444B (zh) 解锁控制方法及相关产品
CN107506708B (zh) 解锁控制方法及相关产品
WO2019024718A1 (zh) 防伪处理方法、防伪处理装置及电子设备
CN107392135A (zh) 活体检测方法及相关产品
US10706282B2 (en) Method and mobile terminal for processing image and storage medium
WO2019015574A1 (zh) 解锁控制方法及相关产品
US11200437B2 (en) Method for iris-based living body detection and related products
WO2019015432A1 (zh) 识别虹膜活体的方法及相关产品
CN114897158A (zh) 数据处理模型的训练方法、数据处理方法、装置及设备

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: 18825445

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: 18825445

Country of ref document: EP

Kind code of ref document: A1