WO2022161367A1 - Living body fingerprint detection system, method and apparatus - Google Patents

Abstract

A living body fingerprint detection system, method and apparatus. Said system comprises: a light source apparatus, a multi-spectrum apparatus, and a control unit; the light source apparatus is used for providing light of a plurality of different wavebands; the control unit is used for controlling the light source apparatus to emit the light of a plurality of wavebands to a finger contact surface of a prism; the multi-spectrum apparatus is used for sensing, by means of a multi-spectrum sensor, fingerprint-reflected light corresponding to the light of each waveband to obtain a spectrum response value and send same to the control unit, wherein the fingerprint-reflected light is reflected light formed by the light emitted by the light source apparatus being reflected by the finger contact surface of the prism; and the control unit is further used for comparing the similarity between the spectrum response value and a reference spectrum response value, and if the similarity does not satisfy a preset condition, determining that the fingerprint is a non-living body fingerprint.

Description

A fingerprint living body detection system, method and device

This application claims the priority of the Chinese patent application filed on January 27, 2021 with the application number 202110114090.7 and titled "A Fingerprint Living Body Detection System, Method and Device", the entire contents of which are incorporated herein by reference Applying.

technical field

The present application relates to the field of computer technology, and in particular, to a fingerprint living body detection system, method and device.

Background technique

Fingerprint identification is a very mature biometric identification method, which is widely used in access control occasions. However, optical fingerprint devices are easy to be broken by fake fingerprints (such as fingerprints on fingerprints, the most common fingerprint is silicone fingerprints), which reduces the number of fingerprint recognition devices such as time attendance machines based on fingerprint recognition, fingerprint readers in access control systems, etc. security. Therefore, the current fingerprint identification equipment manufacturers provide products based on living fingerprint identification. The so-called living fingerprint identification is a fingerprint identification technology for living fingers, that is, only the identification response to the living fingerprint of the real person, and the fingerprints on all other substances. For example, the fingerprint on the silicone fingerprint is not recognized, and is used for fingerprint recognition equipment, such as time attendance machines, fingerprint readers in access control systems, etc.

In order to realize living fingerprint recognition, it is necessary to detect whether the fingerprint is the fingerprint of a real person, and this process is called fingerprint living detection in this paper. However, the calculation process of the fingerprint living detection scheme used in the current living fingerprint identification products is time-consuming, the algorithm is complex, and the identification efficiency is limited.

Therefore, there is a need to provide a more efficient fingerprint living detection solution.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a system, method, and device for fingerprint living detection, so as to improve the efficiency and reliability of fingerprint living detection.

An embodiment of the present application provides a fingerprint living body detection system, including: a light source device, a multispectral device, and a control unit, wherein:

The light source device is used to provide a plurality of light in different wavelength bands;

the control unit, configured to control the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

The multi-spectral device is used for sensing the fingerprint reflected light corresponding to the light of each wavelength band through a multi-spectral sensor, obtaining a spectral response value and sending it to the control unit, wherein the fingerprint reflected light is the light emitted by the light source device The reflected light formed by reflection on the finger contact surface of the prism;

The control unit is further configured to compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint.

The embodiment of the present application also provides a fingerprint living body detection method, including:

Controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

Receive the spectral response value obtained by the multi-spectral sensor sensing the reflected light of the fingerprint corresponding to the light of each band;

Compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet the preset condition, it is determined as a non-living fingerprint.

The embodiment of the present application also provides a fingerprint living body detection device, including:

a control module for controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

The receiving module is used to receive the spectral response value obtained by the multi-spectral sensor sensing the fingerprint reflected light corresponding to the light of each wavelength band, wherein the fingerprint reflected light is formed by the light emitted by the light source device reflected on the finger contact surface of the prism the reflected light;

A comparison module, configured to compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint.

The embodiment of the present application also provides an electronic device, characterized in that it includes:

processor; and

A memory arranged to store computer-executable instructions which, when executed, cause the processor to perform the steps of a method as described above.

Embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and the one or more programs are executed by an electronic device including multiple application programs to execute the above method A step of.

The embodiment of the present application realizes that the spectral response value is obtained by emitting light of multiple wavelength bands and sensing the reflected light of the fingerprint corresponding to the light of each wavelength band through a multi-spectral sensor, which is used as the basis for determining the living fingerprint. The problem of long calculation time caused by multiple emission of light beams and multiple analysis of spectral data is avoided, thereby effectively improving the efficiency of fingerprint living detection.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

FIG. 1 is a schematic structural diagram of a fingerprint living body detection system according to an embodiment of the present application;

FIG. 2 corresponds to reflectance spectrum data corresponding to different materials provided by an embodiment of the present application;

3 is a schematic diagram of a specific structure of a fingerprint living body detection system provided by an embodiment of the present application;

4 is a schematic structural diagram of an internal array of a multispectral sensor provided by an embodiment of the present application;

5 is a schematic diagram of a normalized spectral response of a multispectral sensor provided by an embodiment of the present application;

6 is a schematic diagram of an optical path structure of a fingerprint living body detection system provided by an embodiment of the present application;

FIG. 7 is a schematic flowchart of a fingerprint living body detection method provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a fingerprint living body detection device provided by an embodiment of the present application;

FIG. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic structural diagram of a fingerprint living body detection system according to an embodiment of the application. Referring to FIG. 1 , the system may specifically include: a light source device, a multispectral device, and a control unit, wherein:

The light source device is used to provide a plurality of light in different wavelength bands;

Wherein, the light source device may include one light source or multiple light sources. If the light source includes only one light source, the one light source should be able to emit light of multiple wavelength bands. If the light source includes multiple light sources, then multiple different wavelength bands The light can be separately provided by multiple light sources. Exemplarily, taking the red light, green light, and blue light of multiple different wavelength bands as an example, the light source device may include only one light source for emitting white light, because the spectrum of white light includes red light, green light, and blue light, so The light source emitting white light can provide red light, green light, and blue light, and the light source device may also include a first light source emitting red light, a second light source emitting green light, and a third light source emitting blue light, and the first light source provides red light. Light, the second light source provides green light, and the third light source provides blue light.

the control unit, configured to control the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

Among them, for the case where the light source device only includes one light source, since the light of multiple wavelength bands is emitted by the same light source, the light of multiple wavelength bands is obviously emitted at the same time, so the control unit controls the light source device to emit simultaneously to the finger contact surface of the prism multiple wavelengths of light.

For the case where the light source device includes multiple light sources, since the lights of multiple wavelength bands are emitted by different light sources, the turn-on moments of different light sources can be the same or different, so the control unit can control the light source device to emit sequentially to the finger contact surface of the prism For the light of multiple wavelength bands, the light source device can also be controlled to emit multiple wavelength bands of light simultaneously to the finger contact surface of the prism. For example, it is assumed that the light of the plurality of wavelength bands includes light of the first wavelength band and the light of the second wavelength band, and the light source device includes a first light source and a second light source, the first light source is used to emit light of the first wavelength band, and the second light source is used to emit light of the first wavelength band. the light of the second wavelength band, the control unit can control the first light source in the light source device to emit light of the first wavelength band to the finger contact surface of the prism at the first moment, and control the second light source in the light source device to emit the light of the first wavelength band to the prism at the second moment The finger contact surface of the prism emits light of the second wavelength band, and the first light source and the second light source of the light source device can also be controlled to emit the light of the first wavelength band and the light of the second wavelength band to the finger contact surface of the prism at the same time.

The prism is used to place the finger, and the light provided by the light source device will be reflected by the object to be detected placed on the finger contact surface of the prism when it passes through the prism. Therefore, after passing through the finger contact surface of the prism, the light will carry the signal of the object to be tested, and the reflected light will be referred to as fingerprint reflected light for the convenience of description below; in a possible embodiment, referring to FIG. The surface close to the light source device is frosted, that is, the prism in Figure 6 is close to the surface of the LED (Light-Emitting Diode, light-emitting diode), so that the light beam of the light source device can be scattered evenly, so that the light beam of the light source device can be more uniformly irradiated on the finger contact The required number of LEDs in the light source device is determined according to the light-gathering performance of the system and the exposure parameters of the Sensor; the control unit can be a micro-control unit MCU to realize the miniaturization of the product. In the light path diagram shown in FIG. 6 , the light emitted by the LED of the light source device passes through the prism and is reflected on the finger contact surface of the prism, and the reflected light of the fingerprint is emitted to the Sensor and the multispectral sensor respectively through the light splitting component. The contact face is the face of the prism facing away from the LED.

The multi-spectral device is used for sensing the fingerprint reflected light corresponding to the light of each wavelength band through the multi-spectral sensor to obtain a spectral response value and send it to the control unit, wherein the spectral response value is generated by the multi-spectral sensor in response to the optical signal. The intensity of the electrical signal, the intensity of the electrical signal generated by the multispectral sensor is positively correlated with the intensity of the optical signal, so the spectral response value can represent the light intensity of different wavelengths of light in the reflected light of the fingerprint, and because the process of reflection on the finger contact surface only Part of the light is reflected, while the other part is absorbed, so the light intensity of different wavelengths of light in the reflected light of the fingerprint can reflect the reflectivity of the finger contact surface with different wavelengths of light, that is, the spectral response value can reflect the light placed on the finger. The reflectivity of the object to be tested on the contact surface to light of different wavelengths;

In the case where the control unit controls the light source device to simultaneously emit light of multiple wavelength bands to the finger contact surface of the prism, since the light of multiple wavelength bands is emitted to the finger contact surface of the prism at the same time, the optical path difference is not considered. , the fingerprint emission light corresponding to the light of each band will also be emitted to the multi-spectral device at the same time, so the multi-spectral device can sense the fingerprint reflected light corresponding to the light of each band in one frame, effectively improving the working efficiency of the multi-spectral device .

The control unit is further configured to compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint.

The following is a detailed description of each part of the system:

First, the light source device is described:

By testing the reflection spectrum of human fingers and finger mold materials (because light is a kind of wave, the reflection spectrum is also called reflection spectrum), it can be seen that under the wavelength of 300nm-1100nm, the reflection spectrum of the real finger and the reflection spectrum of the finger mold material are very different. , the reflection spectrum as shown in Figure 2, the vertical dotted line on the far right in the figure (that is, the vertical dotted line at the wavelength of 900nm) passes through the lines from top to bottom. The corresponding materials are: leather lenther, Real finger finger2, real finger finger1, wood glue wood glue, latex latex, silicone foodsilicon, release paper. Among them, the reflection spectrum data corresponding to the real finger and the finger mold material are quite different. Therefore, the wavelengths of the multiple wavelength bands provided by the light source device can be set to be different and all within 300nm-1100nm, so that the control unit can determine the detected When a fingerprint is a living fingerprint, it is only necessary to select the spectral data of certain specific bands for comparison to achieve the purpose of detecting whether the fingerprint is a living fingerprint.

In a possible embodiment, considering the common lighting methods in the market, the light in the multiple wavelength bands can be defined to include at least two of the following four types of light: near-infrared light of 900nm-980nm, red light of 620nm-700nm , 500nm-550nm green light, 435nm-475nm blue light. Taking the case where the light in the multiple wavelength bands includes the aforementioned four kinds of light as an example, with reference to FIG. 3 , the light source device may include a total of four types of LEDs: red, green, blue, and near-infrared (850 nm or 940 nm).

Then, the multispectral device is described:

3, the multispectral device includes a multispectral sensor and a first lens group, wherein:

The first lens group is used for guiding the fingerprint reflected light corresponding to the light of each wavelength band to the multispectral sensor. Wherein, the first lens group may be a Fresnel lens, and its main function is to condense light.

波对应于图4中的NIR。 The multispectral sensor will be described in detail below, taking the case where the multispectral sensor is an AS7341 (a type of multispectral sensor) as an example. The internal array structure of AS7341 is shown in Figure 4, including: F1-F8, NIR (Near Infrared, near-infrared), Flicker (flash) and other sensors for sensing light signals in different bands, the normalized spectral response of AS7341 is as follows As shown in Figure 5, the spectral response of the first wave corresponds to F1 in Figure 4, the spectral response of the second wave corresponds to F2 in Figure 4, the third wave corresponds to F3 in Figure 4, and the second wave corresponds to F3 in Figure 4. Wave ④ corresponds to F4 in Figure 4, wave ⑤ corresponds to F5 in Figure 4, wave ⑥ corresponds to F6 in Figure 4, wave ⑦ corresponds to F7 in Figure 4, and wave ⑧ corresponds to F6 in Figure 4. The wave corresponds to F8 in Fig. 4, the ⑨th wave corresponds to C in Fig. 4, the ⑩th wave corresponds to Flicker in Fig. 4, and the ⑨th wave corresponds to Flicker in Fig.

The waves correspond to the NIR in Figure 4.

Among them, the corresponding 9 peak response bands are shown as vertical lines in FIG. 2 .

Moreover, the AS7341 used in this embodiment is small in size, easy to be integrated in products, has a large response band range, and is highly responsive. It should be noted that the implementation of this embodiment is not limited to this type of sensor, and sensors with similar functions produced by other manufacturers on the market can be used. Replacing different sensors requires adaptation and optimization of the algorithm used to determine the spectral response.

Then, the manner in which the control unit determines the spectral response value, the reference spectral response value and the similarity is described:

The control unit is further configured to obtain the spectral response values corresponding to the batch of fingerprint reflected light samples and calculate the standard deviation and mean of the spectral response values; based on the standard deviation and mean, determine the average of the spectral response values as the reference spectral response value. specifically:

After the fingerprint living detection system is built, it is necessary to use the built fingerprint living detection system to collect samples in order to confirm the reference spectral response value. When collecting the samples, the reflection spectrum formed by the reflection of the human finger is mainly collected. Among them, the sample includes reflection spectra formed by the reflection of the fingers of real people with different attributes, wherein the attributes include: gender, age, etc., and the sample also includes a small part of the reflection spectra formed by the reflection of the finger, so as to be used for judgment. Whether the similarity satisfies a preset threshold of a preset condition (hereinafter referred to as S).

After the sample collection is completed, data analysis is performed on the collected sample data, and the expected value of the spectral response value under the built fingerprint living detection system is obtained as the reference spectral response value. Specifically: First, for each sample data, the spectral response value in the sample data is normalized by the multi-spectral sensor, and the normalized value of the spectral response value is obtained, and the value is between (0, 1) ; Then, for each sample data, the spectral response values of the 9 peak response bands sensed by the multispectral sensor are taken from the sample data, as the band data of each peak response band, and each band data is regarded as a collection of spectral response values, Calculate the standard deviation σ and mean μ corresponding to the spectral response value contained in each band of data, and then take the spectral response value with the wavelength at (μ-2σ, μ+2σ) for each band of data to obtain a vector of single sample data Sci=[Si1,Si2,...,Si9], where Sci is the vector of the i-th sample data, Si1 is the peak value of the first band data from the i-th sample data, and Si2 is the data from the i-th sample data. The peak value of the second band data in , and so on, the value of i is any positive integer in the range of [1,n], and n is the total number of sample data.

Then, the arithmetic mean of the vectors of all sample data is calculated, and finally the vector Ec=[E1, E2,..., E9] is obtained as the reference spectral response value, where E1 is the arithmetic of S11, S21,..., Sn1 The average value, E2 is the arithmetic average of S12, S22, ..., Sn2, and so on.

Corresponding to the aforementioned reference spectral response value, in practical application, the control unit can sense the spectral response value corresponding to the reflection spectrum formed by the reflection of the object to be measured through the multi-spectral sensor, so as to generate a vector Tc=[T1, T2,... ,T9], where T1 represents the peak value of the band data of the first band of the 9 peak response bands, T2 represents the peak value of the band data of the second band of the 9 peak response bands, and so on.

According to different application scenarios, the similarity between the spectral response value and the reference spectral response value can be calculated in different ways. Exemplarily, the chi-square value between the spectral response value and the reference spectral response value can be calculated as the similarity, or the distance between the spectral response value and the reference spectral response value can be calculated as the similarity, where the distance can be Refers to the Euclidean distance, and can also refer to the cosine distance.

Depending on how the similarity is calculated, the preset conditions will also be different. If the similarity is positively correlated with the similarity indicated by the similarity, for example, when the cosine distance is used as the similarity, the preset condition is that the similarity is greater than the preset threshold. Conversely, if the similarity is negatively correlated with the similarity indicated by the similarity, for example, in the case of using chi-square value and Euclidean distance as the similarity, the preset condition is that the similarity is less than the preset threshold.

Exemplarily, taking the similarity in the form of a chi-square value as an example, the chi-square value between the spectral response value and the reference spectral response value is calculated: x2=(T1-E1)2/E1+... +(T9-E9)2/E9. Since the preset condition is that the similarity is less than the preset threshold, if x2>S (S is the preset threshold), the object to be tested is not a living body, that is, the detected fingerprint is not a living fingerprint. The object is a real living body, that is, the detected fingerprint is a living fingerprint.

It is not difficult to know that, different from the conventional fingerprint biometric detection, since the present application mainly collects the reflection spectrum formed by the reflection of the human finger when collecting the sample, only a small amount of the reflection spectrum formed by the reflection of the finger is required to be collected. The calculation method of the example does not require a large number of finger mold materials, that is, a large number of negative samples are not required, which can reduce the difficulty of development and reduce the workload.

To sum up, this embodiment emits light of multiple wavelength bands, and senses the reflected light of the fingerprint corresponding to the light of each wavelength band through the multi-spectral sensor, so as to obtain the spectral response value, which is used as the basis for determining the living fingerprint. The problem of long calculation time caused by multiple emission of light beams and multiple analysis of spectral data is avoided, thereby effectively improving the efficiency of fingerprint living detection.

In a feasible embodiment, the fingerprint living body detection system further includes: an imaging device;

The imaging device is used to obtain the fingerprint image on the prism under the light of each wavelength band, and perform fingerprint identification processing, and the fingerprint identification is used to identify whether the fingerprint in the fingerprint image is legal, such as whether it is the same as the registered legal fingerprint. If it matches with the registered legal fingerprint, it is determined that the fingerprint in the fingerprint image is legal, wherein the fingerprint image on the prism is the image formed on the image sensor by the light reflected from the finger contact surface of the prism.

3, the imaging device includes: a light splitting component, a second lens group and an image sensor, wherein:

The spectroscopic component is used to divide the reflected fingerprint light corresponding to the light of each wavelength band reflected by the prism into a first light propagating in a first direction and a second light propagating in a second direction, the first light propagating To the multi-spectral device, the second light propagates to the second lens group; wherein, the first direction is the direction in which the multi-spectral device is located relative to the spectroscopic component, and the second direction is the direction in which the second lens group is located relative to the spectroscopic component, And according to different optical path designs, the first direction and the second direction can be any direction.

The second lens group is used for guiding the second light to the image sensor Sensor.

With reference to Figure 6, the optical path structure of the fingerprint living body detection system can be:

The LED in the light source device simultaneously emits light of multiple wavelength bands to the finger contact surface of the prism; the prism reflects the light along the third direction, and the reflected light is divided into the first light and the second light by the light splitting component. The first direction propagates through the first lens group to the multispectral sensor; the second light propagates in the second direction through the second lens group to the image sensor. Wherein, the third direction is the direction in which the light splitting component is located relative to the prism, and according to different optical path designs, the third direction can be any direction.

The control unit is also used to allow the next step to be processed when it is determined that the fingerprint is a living fingerprint and the imaging device recognizes that the fingerprint is a legitimate fingerprint, such as opening the door, unlocking the screen, etc. Otherwise, rejecting the response, that is, rejecting the next step. one-step processing.

Based on this, in this embodiment, by adding a spectroscopic component to perform spectroscopic processing on the reflected light, the processing of fingerprint living body detection and the processing of fingerprint recognition can be simultaneously performed, so that the fingerprint living body detection system can support the functions of fingerprint living body detection and fingerprint recognition, thereby effectively improving the Reliability of Fingerprint Liveness Detection System and Expanding Applicable Scenarios of Fingerprint Liveness Detection System.

FIG. 7 is a schematic flowchart of a fingerprint living body detection method provided by an embodiment of the present application, which can be executed by the fingerprint living body detection system corresponding to FIG. 1 . Referring to FIG. The control unit, the method may specifically include the following steps:

Step 702, controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

Wherein, the wavelengths of the light in the multiple wavelength bands are different and all are within 300nm-1100nm. The light in the multiple wavelength bands includes: near-infrared light at 900nm-980nm, red light at 620nm-700nm, green light at 500nm-550nm, and blue light at 435nm-475nm.

Step 704: Receive the fingerprint reflected light corresponding to the light of each wavelength band sensed by the multi-spectral sensor, and obtain a spectral response value, wherein the fingerprint reflected light is the reflection formed by the light emitted by the light source device reflected on the finger contact surface of the prism Light;

Step 706: Compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint.

The spectral response value includes spectral response values corresponding to multiple bands, and the number of bands corresponds to the model of the multispectral sensor used. For example, the multispectral sensor of AS7341 has 9 bands. Correspondingly, an implementation manner of step 706 may be:

determining the standard deviation and mean value of the spectral response values corresponding to each of the plurality of bands; determining the average value of the spectral response values based on the standard deviation and mean value of the spectral response values corresponding to each waveband; comparing the average value of the spectral response values The similarity between the value and the reference spectral response value.

In a possible embodiment, controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism includes: controlling the light source device to simultaneously emit light of multiple wavelength bands to the finger contact surface of the prism.

In a possible embodiment, the method further includes: when it is determined that the fingerprint is a living fingerprint and the imaging device identifies that the fingerprint is a legal fingerprint, allowing the next step to be processed, otherwise rejecting the response.

In a possible embodiment, before performing step 706, the method further includes: acquiring spectral response values corresponding to the batch of fingerprint reflected light samples and calculating the standard deviation and mean of the spectral response values; determining the spectral response based on the standard deviation and mean The average of the values is used as the reference spectral response value.

In a possible embodiment, the batch of fingerprint reflected light samples includes: fingerprint reflected light samples of a user group corresponding to a preset user feature, where the preset user feature at least includes an age feature and a gender feature.

In a possible embodiment, the similarity between the spectral response value and the reference spectral response value is compared; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint, including:

Calculate the chi-square value between the spectral response value and the reference spectral response value as similarity;

If the similarity is not less than the preset threshold, it is determined as a non-living fingerprint.

In a possible embodiment, the method further includes:

Obtaining sample data, the sample data includes a reflection spectrum formed by the reflection of a human finger, and a reflection spectrum formed by the reflection of a finger mold;

According to the sample data, the expected value of the spectral response value is determined as the reference spectral response value.

In the following, taking the multispectral sensor of AS7341 and using the chi-square value to represent the similarity as an example, how to judge whether the preset condition is established in step 706 is exemplarily explained, because the chi-square value is used to represent the similarity to determine the preset condition. condition is true, so this example is also called a chi-square test scheme:

First, after the sample collection is completed, data analysis is performed on the collected sample data, and the expected value under the spectral response value of the fingerprint biometric detection system is obtained as the reference spectral response value. Specifically: First, for each sample data, the spectral response value in the sample data is normalized by the multi-spectral sensor, and the normalized value of the spectral response value is obtained, and the value is between (0, 1) .

Then, for each sample data, the spectral response values of the 9 peak response bands sensed by the sensor are taken out from the sample data, as the band data of each peak response band, and each band data is regarded as a collection of spectral response values. The standard deviation σ and the mean μ corresponding to the spectral response values contained in each band of data, and then the spectral response values with wavelengths at (μ-2σ, μ+2σ) are taken for each band of data to obtain the vector Sci of a single sample =[Si1,Si2,...,Si9], where Sci is the vector of the i-th sample data, Si1 is the peak value of the first band data from the i-th sample data, and Si2 is the data from the i-th sample data. The peak value of the second band data, and so on, the value of i is any positive integer in the range of [1,n], and n is the total number of sample data.

Calculate the arithmetic mean of the vectors of all sample data, and finally obtain the vector Ec=[E1,E2,...,E9], the vector Ec can be recorded as the above-mentioned reference spectral response value, where E1 is S11, S21,... , the arithmetic mean of Sn1, E2 is the arithmetic mean of S12, S22, ..., Sn2, and so on.

Similarly, when there is an object to be measured (such as a finger), the vector Tc=[T1, T2,..., T9] corresponding to the reflection spectrum formed by the reflection of the object to be measured can be directly obtained in the same way, which can be recorded as the above finger The corresponding spectral response value, where T1 represents the peak value of the band data of the first band in the 9 peak response bands, T2 represents the peak value of the band data of the second band in the 9 peak response bands, and so on.

Correspondingly, the chi-square value between the spectral response value and the reference spectral response value: χ2=(T1-E1)2/E1+...+(T9-E9)2/E9. Since the preset condition is that the similarity is less than the preset threshold, if χ2>S (S is the preset threshold), the object to be tested is not a live human body, and otherwise, the object to be tested is a live human body.

Based on this, this embodiment emits light in multiple wavelength bands, and uses a multispectral sensor to sense the reflected light of the fingerprint corresponding to the light in each wavelength band to obtain a spectral response value, which is used as a basis for determining a living fingerprint. The problem of long calculation time caused by multiple emission of light beams and multiple analysis of spectral data is avoided, thereby effectively improving the efficiency of fingerprint living detection.

FIG. 8 is a schematic structural diagram of a fingerprint living body detection device provided by an embodiment of the present application. Referring to FIG. 8 , the fingerprint living body detection device provided by the present application is applied to a control unit in the aforementioned fingerprint living body detection system. The device may specifically include: controlling Module 801, receiving module 802 and comparing module 803, wherein:

The control module 801 is used to control the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

The receiving module 802 is used to obtain the spectral response value obtained by the multi-spectral sensor sensing the fingerprint reflected light corresponding to the light of each wavelength band, wherein the fingerprint reflected light is the light emitted by the light source device reflected on the finger contact surface of the prism the reflected light formed;

The comparison module 803 is configured to compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint.

In a possible embodiment, the control module 801 is specifically configured to control the light source device to simultaneously emit light of multiple wavelength bands to the finger contact surface of the prism;

In a possible embodiment, the wavelengths of the light in the multiple wavelength bands are different and all are within 300nm-1100nm.

In a possible embodiment, the light in the plurality of wavelength bands includes at least two of the following four kinds of light: near-infrared light at 900nm-980nm, red light at 620nm-700nm, green light at 500nm-550nm, and 435nm -475nm blue light.

In a possible embodiment, the apparatus further includes:

The processing module is configured to allow the next step to be processed when it is determined that the fingerprint is a living fingerprint and the imaging device recognizes that the fingerprint is a legitimate fingerprint, otherwise it refuses to respond.

In a possible embodiment, the apparatus further includes:

The pre-preparation module is used to obtain the spectral response values corresponding to the batch fingerprint reflected light samples and calculate the standard deviation and mean of the spectral response values; based on the standard deviation and mean, determine the average value of the spectral response values as the reference spectral response value.

In a possible embodiment, the comparison module 803 compares the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint, including :

Calculate the chi-square value between the spectral response value and the reference spectral response value as similarity;

If the similarity is not less than the preset threshold, it is determined as a non-living fingerprint.

In a possible embodiment, the comparison module 803 is further configured to acquire sample data, where the sample data includes a reflection spectrum formed by reflection of a human finger, and a reflection spectrum formed by reflection of a finger model;

According to the sample data, the expected value of the spectral response value is determined as the reference spectral response value.

Based on this, this embodiment emits light in multiple wavelength bands, and uses a multispectral sensor to sense the reflected light of the fingerprint corresponding to the light in each wavelength band to obtain a spectral response value, which is used as a basis for determining a living fingerprint. The problem of long calculation time caused by multiple emission of light beams and multiple analysis of spectral data is avoided, thereby effectively improving the efficiency of fingerprint living detection.

In addition, for the above-mentioned apparatus embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and reference may be made to the partial description of the method embodiment for related parts. Moreover, it should be noted that, in each component of the device of the present application, the components are logically divided according to the functions to be implemented, but the present application is not limited to this, and each component can be implemented as required. Re-divide or combine.

FIG. 9 is a schematic structural diagram of an electronic device according to an embodiment of the application. Referring to FIG. 9 , the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course may also include other business required hardware. The processor reads the corresponding computer program from the non-volatile memory into the memory and runs it, forming a fingerprint living body detection device on a logical level. Of course, in addition to software implementations, this application does not exclude other implementations, such as logic devices or a combination of software and hardware. hardware or logic device.

Network interfaces, processors and memories can be interconnected through a bus system. The bus can be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or an EISA (Extended Industry Standard Architecture, extended industry standard structure) bus and the like. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one bidirectional arrow is used in FIG. 9, but it does not mean that there is only one bus or one type of bus.

Memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory, which may include read-only memory and random access memory, provides instructions and data to the processor. The memory may include high-speed random-access memory (Random-Access Memory, RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

a processor, configured to execute the program stored in the memory, and specifically execute:

Controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism;

Receive the reflected light of the fingerprint corresponding to the light of each wavelength band sensed by the multi-spectral sensor, and obtain the spectral response value;

Compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet the preset condition, it is determined as a non-living fingerprint.

The above-mentioned method performed by the fingerprint living body detection apparatus or the manager (Master) node disclosed in the embodiment shown in FIG. 8 of the present application may be applied to a processor, or implemented by a processor. A processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above-mentioned method can be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software. The above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processor, DSP), dedicated integrated Circuit (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.

The fingerprint living detection device can also execute the method shown in FIG. 7 and implement the method executed by the manager node.

Corresponding to the foregoing fingerprint living detection method, embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and the one or more programs, when included in multiple applications When the electronic device of the program is executed, the electronic device is made to execute the fingerprint living body detection method provided by the embodiment corresponding to FIG. 7 .

The various embodiments in this application are described in a progressive manner, and the same and similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

The foregoing describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include forms of non-persistent memory, random access memory (RAM) and/or non-volatile memory in computer readable media, such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture, or device that includes the element.

It will be appreciated by those skilled in the art that the embodiments of the present application may be provided as a method, a system or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The above are only preferred embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection of the present application. within the range.

Claims (22)

A fingerprint living body detection system, comprising: a light source device, a multispectral device and a control unit, wherein: The light source device is used to provide a plurality of light in different wavelength bands; the control unit, configured to control the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism; The multi-spectral device is used for sensing the fingerprint reflected light corresponding to the light of each wavelength band through a multi-spectral sensor, obtaining a spectral response value and sending it to the control unit, wherein the fingerprint reflected light is the light emitted by the light source device The reflected light formed by reflection on the finger contact surface of the prism; The control unit is further configured to compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint. The system of claim 1, wherein the control unit provides a plurality of light in different wavelength bands, including: The light source device is controlled to emit light of multiple wavelength bands simultaneously to the finger contact surface of the prism. The system according to claim 1, wherein the wavelengths of the light in the multiple wavelength bands are different and all are within 300nm-1100nm. The system of claim 3, wherein: The light in the plurality of wavelength bands includes at least two of the following four kinds of light: near-infrared light at 900nm-980nm, red light at 620nm-700nm, green light at 500nm-550nm, and blue light at 435nm-475nm. The system according to any one of claims 1-4, wherein the multispectral device comprises: a multispectral sensor and a first lens group, wherein: The first lens group is used for guiding the fingerprint reflected light corresponding to the light of each wavelength band to the multispectral sensor. The system according to any one of claims 1-4, wherein the system further comprises: an imaging device; The imaging device is used for acquiring fingerprint images on the prism under light of each wavelength band, and performing fingerprint identification processing. The system according to claim 6, wherein the imaging device comprises: a light splitting component, a second lens group and an image sensor, wherein: The spectroscopic component is used to divide the reflected fingerprint light corresponding to the light of each wavelength band reflected by the prism into a first light propagating in a first direction and a second light propagating in a second direction, the first light propagating to the multispectral device; the second lens group for guiding the second light to the image sensor. The system of claim 6, wherein: The control unit is further configured to allow the next step to be processed when it is determined that the fingerprint is a living fingerprint and the imaging device recognizes that the fingerprint is a legitimate fingerprint, otherwise, refuse to respond. The system of claim 1, wherein: The control unit is further configured to obtain the spectral response values corresponding to the batch of fingerprint reflected light samples and calculate the standard deviation and mean of the spectral response values; based on the standard deviation and mean, determine the average of the spectral response values as the reference spectral response value. The system according to claim 1, wherein the control unit compares the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living body Fingerprints, including: Calculate the chi-square value between the spectral response value and the reference spectral response value as similarity; If the similarity is not less than the preset threshold, it is determined as a non-living fingerprint. The system according to claim 1, wherein the multispectral device is further configured to collect sample data, and the sample data includes a reflection spectrum formed by reflection of a human finger, and a reflection spectrum formed by reflection of a finger model; The control unit is further configured to determine an expected value of the spectral response value as a reference spectral response value according to the sample data. A fingerprint living body detection method, comprising: Controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism; Receiving the spectral response value obtained by the multi-spectral sensor sensing the fingerprint reflected light corresponding to the light of each wavelength band, wherein the fingerprint reflected light is the reflected light formed by the light emitted by the light source device reflected on the finger contact surface of the prism; Compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet the preset condition, it is determined as a non-living fingerprint. The method according to claim 12, wherein the control light source device emits light of multiple wavelength bands to the finger contact surface of the prism, comprising: The light source device is controlled to emit light of multiple wavelength bands simultaneously to the finger contact surface of the prism. The method according to claim 12, wherein the spectral response value comprises spectral response values corresponding to multiple bands; Wherein, the comparing the similarity between the spectral response value and the reference spectral response value includes: determining the standard deviation and mean of the spectral response values corresponding to each of the multiple bands; Determine the average value of the spectral response value based on the standard deviation and mean value of the spectral response value corresponding to each band; Compare the similarity between the average of the spectral response values and the reference spectral response value. The method according to claim 14, wherein before the comparing the similarity between the spectral response value and the reference spectral response value, the method further comprises: Obtain the spectral response values corresponding to the batch fingerprint reflected light samples and calculate the standard deviation and mean of the spectral response values; Based on the standard deviation and the mean, the average value of the spectral response values is determined as the reference spectral response value. The method of claim 15, wherein: The batch of fingerprint reflected light samples includes: fingerprint reflected light samples of user groups corresponding to preset user characteristics; Wherein, the preset user characteristics include at least age characteristics and gender characteristics. The method according to claim 12, wherein the comparing the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint, include: Calculate the chi-square value between the spectral response value and the reference spectral response value as similarity; If the similarity is not less than the preset threshold, it is determined as a non-living fingerprint. The method of claim 17, wherein the method further comprises: Obtaining sample data, the sample data includes a reflection spectrum formed by the reflection of a human finger, and a reflection spectrum formed by the reflection of a finger mold; According to the sample data, the expected value of the spectral response value is determined as the reference spectral response value. A fingerprint living body detection device, comprising: a control module for controlling the light source device to emit light of multiple wavelength bands to the finger contact surface of the prism; The receiving module is used to receive the spectral response value obtained by the multi-spectral sensor sensing the fingerprint reflected light corresponding to the light of each wavelength band, wherein the fingerprint reflected light is formed by the light emitted by the light source device reflected on the finger contact surface of the prism the reflected light; A comparison module, configured to compare the similarity between the spectral response value and the reference spectral response value; if the similarity does not meet a preset condition, it is determined as a non-living fingerprint. An electronic device comprising a processor; and A memory arranged to store computer-executable instructions which, when executed, cause the processor to perform the steps of the method of any of claims 12-17. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs, and the one or more programs, when executed by an electronic device including a plurality of application programs, are as claimed in claims 12-17 the steps of any of the methods. A computer program product which, when run on a computer, causes the computer to perform the steps of the method as claimed in any one of claims 12-17.

Images