WO2020073169A1 - 生物特征识别的方法、装置和电子设备 - Google Patents

生物特征识别的方法、装置和电子设备 Download PDF

Info

Publication number
WO2020073169A1
WO2020073169A1 PCT/CN2018/109349 CN2018109349W WO2020073169A1 WO 2020073169 A1 WO2020073169 A1 WO 2020073169A1 CN 2018109349 W CN2018109349 W CN 2018109349W WO 2020073169 A1 WO2020073169 A1 WO 2020073169A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
recognition
light source
imaging
biometric
Prior art date
Application number
PCT/CN2018/109349
Other languages
English (en)
French (fr)
Inventor
张玮
青小刚
周飞
Original Assignee
深圳市汇顶科技股份有限公司
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 深圳市汇顶科技股份有限公司 filed Critical 深圳市汇顶科技股份有限公司
Priority to PCT/CN2018/109349 priority Critical patent/WO2020073169A1/zh
Priority to CN201880001745.6A priority patent/CN109496308A/zh
Priority to EP18936824.4A priority patent/EP3798876A4/en
Publication of WO2020073169A1 publication Critical patent/WO2020073169A1/zh
Priority to US17/112,686 priority patent/US20210117645A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G06V10/12—Details of acquisition arrangements; Constructional details thereof
    • G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
    • G06V10/143—Sensing or illuminating at different wavelengths
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • 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
    • G06V40/12—Fingerprints or palmprints
    • G06V40/13—Sensors therefor
    • G06V40/1318—Sensors therefor using electro-optical elements or layers, e.g. electroluminescent sensing
    • 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
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1335—Combining adjacent partial images (e.g. slices) to create a composite input or reference pattern; Tracking a sweeping finger movement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging

Definitions

  • the present application relates to the field of information technology, and more specifically, to a method, device, and electronic device for biometric identification.
  • biometric recognition technology has been widely used in various fields such as mobile terminals and smart homes.
  • a certain wavelength of visible light is used to illuminate the biometrics.
  • the reflected light signal carrying biometric information is transmitted to the sensor for collection. According to the collected information and the biometrics registered and stored in advance Compare to confirm the legitimacy of the user's identity.
  • the above method is easily affected by the contact between the biometrics and the detection surface.
  • the pressing force and the point of application are different, and the finger is dry, etc., which may affect the recognition performance.
  • Embodiments of the present application provide a method, device, and electronic device for biometric recognition, which can effectively improve the performance of biometric recognition.
  • a method for biometric identification including:
  • the imaging is sequentially performed according to the light signal transmitted from the skin when each light source in the at least one light source illuminates the skin; and the biometric recognition is performed according to at least one image obtained by the imaging.
  • each light source in at least one light source is used to irradiate the skin, and the principle of light transmission imaging is used to obtain at least one image for biometrics identification.
  • the biometrics may not be used in conjunction with the detection surface. Contact reduces the impact of contact on biometrics, thereby improving the performance of biometrics.
  • the at least one light source is an infrared light source
  • the optical signal is an infrared optical signal
  • the at least one light source is a plurality of light sources, and the plurality of light sources are disposed in different directions relative to the identification area.
  • the light sources in different directions can be used for imaging sequentially, which solves the problem of poor imaging quality when irradiated in a certain direction when a single light source is used in the biometric recognition process Problems, which can further improve the performance of biometrics.
  • the biometric recognition based on at least one image obtained by imaging includes: fusing multiple images obtained by imaging to obtain a fused image; and performing biometric recognition according to the fused image.
  • the biometric recognition based on the at least one image obtained by imaging includes: performing biometric recognition based on the first image obtained by imaging; if the recognition based on the first image fails, Then biometric recognition is performed according to the next image obtained by imaging; if the recognition of multiple images obtained by imaging fails, the multiple images are fused to obtain a fused image; biometric recognition is performed according to the fused image .
  • the biometric recognition based on the at least one image obtained by imaging includes: biometric recognition based on the first image obtained by imaging; if the recognition fails according to the first image, Then, multiple images obtained by imaging are fused to obtain a fused image; and biometric recognition is performed according to the fused image.
  • the first image is an image obtained by imaging according to an optical signal transmitted from the skin when the default light source among the plurality of light sources illuminates the skin.
  • the plurality of light sources include a first light source and a second light source, and a line connecting the first light source and the center of the identification area is perpendicular to the second light source and the identification area Center connection.
  • a device for biometric identification including:
  • At least one light source a sensor for sequentially imaging according to the light signal transmitted from the skin when each of the at least one light source illuminates the skin, wherein at least one image obtained by imaging the sensor is used for biometric recognition.
  • the at least one light source is an infrared light source
  • the optical signal is an infrared optical signal
  • the at least one light source is a plurality of light sources, and the plurality of light sources are disposed in different directions relative to the identification area.
  • the plurality of light sources include a first light source and a second light source, and a line connecting the first light source and the center of the identification area is perpendicular to the second light source and the identification area Center connection.
  • the device further includes:
  • the processor is configured to perform biometric recognition based on at least one image obtained by imaging with the sensor.
  • the processor is used to: fuse multiple images obtained by imaging to obtain a fused image; and perform biometric recognition according to the fused image.
  • the processor is configured to: perform biometric recognition based on the first image obtained by imaging; if recognition fails based on the first image, perform biometrics based on the next image obtained by imaging Feature recognition; if the recognition of multiple images obtained by imaging fails, the multiple images are fused to obtain a fused image; and the biometric recognition is performed according to the fused image.
  • the processor is configured to: perform biometric recognition based on the first image obtained by imaging; if recognition fails based on the first image, fuse multiple images obtained by imaging, Obtain a fusion image; perform biometric recognition according to the fusion image.
  • the first image is an image obtained by the sensor imaging the light signal transmitted from the skin when the default light source among the plurality of light sources illuminates the skin.
  • an electronic device for biometric identification including the biometric identification device in the second aspect or any possible implementation manner of the second aspect.
  • FIG. 1 is a schematic diagram of an apparatus for biometric recognition according to an embodiment of the present application.
  • FIGS. 2 and 3 are schematic diagrams of biometric images with different irradiation directions according to an embodiment of the present application.
  • FIGS 4 and 5 are schematic diagrams of light source installation positions according to embodiments of the present application.
  • FIG. 6 is a schematic diagram of image fusion according to an embodiment of the present application.
  • FIG. 7 is a schematic flowchart of a method for biometric identification according to an embodiment of the present application.
  • FIG. 8 is an exemplary flowchart of a method for biometric recognition according to another embodiment of the present application.
  • biometric technology is to use computers and optical, acoustic, biosensors and biostatistics principles to closely combine high-tech methods, using the inherent physiological characteristics of the human body (such as fingerprints, face images, irises, etc.) and behavioral characteristics (such as handwriting , Voice, gait, etc.) for personal identification, which can be widely used in government, military, banking, social security, e-commerce, security and defense.
  • biometric identification is gradually emerging, and gradually replacing traditional password identification will be the general trend.
  • the specific identification process of optical biometrics can be: using visible light with a certain wavelength as the light source for illuminating the biometrics, usually using green light with a wavelength of 500 nm-560 nm.
  • the detection surface When a biometric touches, presses, or approaches (for ease of description, in this application collectively referred to as pressing) the detection surface, the visible light emitted by the visible light source undergoes reflection of the biometrics in contact with the detection surface to form an optical signal containing biometric information
  • the optical sensor receives the reflected light and uses the reflection imaging principle of the light to perform biometric identification.
  • the embodiments of the present application provide a technical solution of biometrics recognition based on the principle of light transmission imaging.
  • FIG. 1 shows a schematic diagram of an apparatus for biometric recognition according to an embodiment of the present application.
  • the apparatus for biometric recognition may include at least one light source 110; and a sensor 120.
  • At least one light source 110 is an excitation light source for biometric identification.
  • the sensor 120 sequentially performs imaging according to the light signal transmitted from the skin when each light source of the at least one light source illuminates the skin, wherein at least one image obtained by imaging the sensor 120 is used for biometric recognition.
  • imaging is performed according to the light signal transmitted from the skin.
  • the light source 110 generates light that can transmit through the skin. This light illuminates the finger and transmits the finger skin into the dermis layer. After being reflected and scattered by the tissue under the epidermis of the finger, it is transmitted out of the skin.
  • the transmitted light passes through the valleys and ridges in the fingerprint of the finger, the fingerprint valleys and the fingerprint ridges have different light absorption capabilities. Specifically, the fingerprint valleys have a weaker light absorption capacity, and the transmitted light intensity is stronger, while the fingerprint ridges The light absorption capacity is strong, and the transmitted light is weak. Therefore, the optical signal carrying the fingerprint characteristic information transmitted from the finger skin enters the sensor 120, and the sensor 120 collects the fingerprint characteristic information included in the optical signal for imaging to perform fingerprint recognition.
  • each light source in at least one light source is used to irradiate the skin, and the principle of light transmission imaging is used to obtain at least one image for biometrics identification.
  • the biometrics may not be used for the detection surface Contact reduces the impact of contact on biometrics, thereby improving the performance of biometrics.
  • the technical solutions of the embodiments of the present application may also perform other biometrics recognition based on the principle of transmission imaging, for example, face recognition, etc., which is not limited in the embodiments of the present application.
  • biometrics recognition based on the principle of transmission imaging, for example, face recognition, etc., which is not limited in the embodiments of the present application.
  • the embodiments of the present application take fingerprint identification as an example for description.
  • the light source 110 may be an infrared light source, and the light signal transmitted through the finger skin is an infrared light signal.
  • the light source 110 may be a light-emitting diode (Light-Emitting Diode, LED), a laser diode (Laser Diode, LD), or a photodiode that can generate infrared light.
  • LED Light-Emitting Diode
  • LD Laser Diode
  • photodiode that can generate infrared light.
  • the light source 110 may also be other light that can transmit skin, such as near-infrared light, and the corresponding transmitted light signal is a near-infrared signal, which is not limited in the embodiments of the present application.
  • the embodiments of the present application do not particularly limit the relative positional relationship between the light source 110 and the sensor 120.
  • the light source 110 and the sensor 120 may be placed side by side, or placed in other ways as long as the light source 110 and the sensor 120 can be biometrically identified.
  • the technical solution of the embodiment of the present application may be a technical solution for off-screen biometric identification, that is, a sensor or related component is provided under the display screen, or may be a technical solution for in-screen biometric identification, that is, a sensor or related component is provided on the display screen Inside.
  • the senor 120 may be a complementary metal oxide semiconductor (Complementary Metal Oxide Semiconductor (CMOS)) sensor, and the sensor 120 is used to collect biological characteristics of a desired detection area.
  • CMOS Complementary Metal Oxide Semiconductor
  • the CMOS sensor technology is relatively mature, the range of the center sensitive wavelength is easier to achieve through process doping, the cost is lower than that of the charge-coupled device (Charge-coupled Device, CCD), and the driving circuit is simpler than the CCD.
  • CCD charge-coupled Device
  • the sensor 120 may also use other types of sensors, which are not limited in the embodiments of the present application.
  • the senor 120 may also be used in combination with a distance sensor, the distance sensor is used to detect a user's biometrics, such as the distance from the finger or palm to the biometric detection area, and may further be at the distance When it is less than or equal to a specific distance threshold, the sensor 120 is switched from the standby (sleep) state to the working state to facilitate image acquisition.
  • a distance sensor is used to detect a user's biometrics, such as the distance from the finger or palm to the biometric detection area, and may further be at the distance When it is less than or equal to a specific distance threshold, the sensor 120 is switched from the standby (sleep) state to the working state to facilitate image acquisition.
  • the sensor 120 when the sensor 120 is in the working state, when the biometrics are close, the sensor 120 can perform image acquisition; when the sensor 120 is in the standby state, even if the biometrics are close to the sensor 120, the sensor 120 does not perform image acquisition, therefore, When the image acquisition is not performed, switching the sensor 120 to the standby state can reduce the power consumption of the device.
  • the distance threshold may be the imaging distance of the sensor 120, that is, the furthest distance that the sensor 120 can image, for example, the distance threshold may be 10cm, 5cm, etc. The specific value may be based on actual needs Decide.
  • the principle of light transmission imaging is mainly used.
  • the direction in which the light source illuminates the biological feature and the direction of the lines in the biological feature are more important for the imaging result.
  • a clear biometrics image can basically be obtained, as shown in Figure 2.
  • the direction of the light source is parallel to the direction of most of the lines in the biometrics, the overall image quality is poor.
  • the complete information of the biometrics cannot be accurately represented, which affects the subsequent authentication of the biometrics.
  • the embodiment of the present application provides multiple light sources 110 in different directions relative to the recognition area, and the multiple light sources 110 can illuminate the organism from different directions Feature, the sensor 120 images correspondingly to obtain multiple images, which are used for biometric recognition to improve the performance of biometric recognition.
  • the identification area may be a partial area of the display screen, or may be the entire area of the display screen, that is, full-screen biometric identification.
  • the plurality of light sources 110 may include a first light source and a second light source, a line connecting the first light source and the center of the identification area is perpendicular to a center of the second light source and the center of the identification area Connect. That is, at least two light sources of the plurality of light sources are arranged so that the direction in which they illuminate the biological feature is perpendicular.
  • FIG. 4 shows a schematic diagram of two light sources in one embodiment of the present application.
  • FIG. 4 is a top view.
  • the two light sources 110 and the sensor 120 may form an isosceles triangle.
  • the apex angle of the isosceles triangle may be an obtuse angle
  • the recognition area may be disposed above the sensor 120, so that the two light sources 110 may illuminate the biological features on the recognition area in a substantially vertical irradiation direction.
  • the two light sources 110 may sequentially illuminate the skin from different directions, and the sensor 120 may sequentially image the light signals transmitted from the skin when each light source illuminates the skin. In this way, two images can be acquired, and biometric identification can be performed based on at least one image as needed.
  • FIG. 5 shows a schematic diagram of four light sources in another embodiment of the present application.
  • FIG. 5 is a top view.
  • the four light sources 110 may be disposed at four corners of a rectangle centered on the center of the sensor 120.
  • the recognition area may be disposed above the sensor 120, so that the four light sources 110 may illuminate the biological features on the recognition area in a substantially vertical irradiation direction.
  • the four light sources 110 sequentially illuminate the skin from different directions, and accordingly the sensor 120 may sequentially image according to the light signal transmitted from the skin when each light source illuminates the skin. In this way, four images can be acquired, and then biometrics can be identified based on at least one image as needed.
  • the light sources in different directions can be used for imaging sequentially, which solves the problem of poor imaging quality when irradiated in a certain direction when a single light source is used in the biometric recognition process Problems, which can further improve the performance of biometrics.
  • multiple light sources may be provided at one light source position shown in FIGS. 4 and 5, which is not limited in the embodiments of the present application.
  • connection between one light source and the center of the identification area is perpendicular to the connection between the other light source and the center of the identification area.
  • the angle between the two may be approximately 90
  • the degree is not limited to 90 degrees.
  • it may be 80 degrees or 100 degrees, which is not limited in the embodiments of the present application.
  • multiple biometric images may be acquired by serially scanning light sources in different directions.
  • the biometric identification device may further include a control circuit for sequentially controlling the turn-on sequence of each light source.
  • the control circuit is connected to each light source and is used to control the turn-on sequence of the light sources. For example, the control circuit first turns on the first light source to illuminate the skin, the sensor performs imaging according to the light signal transmitted from the skin, and then the control circuit controls to turn off the first light source, turn on the second light source, and then acquire the corresponding biometric image to And so on.
  • the light sources can be turned on in any order, which is not limited in the embodiments of the present application.
  • the biometric identification device may further include a processor, configured to perform biometric identification based on at least one image imaged by the sensor 120.
  • the processor may be a processor of an electronic device, or may be a separately provided processor for biometric identification, which is not limited in this embodiment of the present application.
  • the processor is used to:
  • Biometric recognition is performed according to the fusion image.
  • the processor directly fuses multiple images obtained in sequence to obtain a fused image, and performs biometric recognition according to the fused image.
  • the processor may also perform biometric recognition based on the first image obtained first, and then determine whether multiple images need to be fused according to the recognition result, which will be described in detail below.
  • the processor is used to:
  • biometric recognition is performed according to the next image obtained by imaging
  • the multiple images are fused to obtain a fused image
  • Biometric recognition is performed according to the fusion image.
  • the first image is acquired first.
  • the first image may be an image obtained by imaging the sensor according to an optical signal transmitted from the skin when the default light source among the plurality of light sources illuminates the skin.
  • the default light source may be a light source that can obtain the highest quality image when the finger approaches the display screen in the most customary manner.
  • the processor first performs biometric recognition according to the first image obtained by imaging, and if the recognition is successful, the recognition process ends. If the recognition fails, the next image is collected, and the processor performs biometric recognition according to the next image obtained by imaging, and so on. If the recognition of multiple images obtained by imaging fails, the multiple images are fused to obtain a fused image, and biometric recognition is performed according to the fused image. With the method of this embodiment, under normal circumstances, it is not necessary to collect all images and perform image fusion, so that the recognition speed can be improved.
  • the processor is used to:
  • Biometric recognition is performed according to the fusion image.
  • the first image is acquired first.
  • the first image may be similar to that in the foregoing embodiment, and will not be repeated here.
  • the processor first performs biometric recognition according to the first image obtained by imaging, and if the recognition is successful, the recognition process ends. If the recognition fails, other images are collected, and the processor fuse the obtained multiple images to obtain a fusing image, and perform biometric recognition according to the fusing image.
  • the method of this embodiment under normal circumstances, it is not necessary to collect all images and perform image fusion, so that the recognition speed can be improved.
  • FIG. 6 is a schematic diagram of image fusion according to an embodiment of the present application.
  • the figure contains three acquired fingerprint images, namely image (a), image (b), and image (c), respectively, when three light sources sequentially illuminate the skin
  • the light signal transmitted from the skin is imaged.
  • the illumination direction of the light source used for imaging is different, and may be parallel to the direction of part of the lines in the fingerprint, so the fingerprint image generated is unclear. If the top part of the fingerprint image in image (a) is unclear, the part on the right side of the fingerprint image in image (b) is unclear, and the left side of the fingerprint image in image (c) is unclear.
  • three defective images can be processed by image fusion to obtain a clear fingerprint image.
  • the fused image contains complete biometric details information, and improves the image quality and further enhances the biological quality. Feature recognition performance.
  • the image fusion method in the embodiment of the present application may adopt any fusion method, such as wavelet transform, gray-scale weighted average method, or pyramid decomposition fusion method, which is not limited in the embodiment of the present application.
  • FIG. 7 shows a schematic flowchart of a method for biometric recognition according to an embodiment of the present application.
  • each step in FIG. 7 may be performed in a different order than that presented in FIG. 7, and it may not be necessary to perform all operations in FIG. 7.
  • the method shown in FIG. 7 may be performed by the apparatus for biometric identification in the foregoing embodiments of the present application.
  • reference may be made to the foregoing embodiments.
  • the descriptions in the following embodiments may also be incorporated into the foregoing embodiments, for simplicity ,No longer.
  • the method 700 may include the following steps.
  • 701 Perform imaging sequentially according to the optical signal transmitted from the skin when each of the at least one light source illuminates the skin.
  • At least one image for biometric identification does not necessarily correspond to at least one light source in 701.
  • an image is obtained, and the at least one light source is At least one image corresponds.
  • the at least one light source is a plurality of light sources, multiple images may be obtained, or only one image may be obtained, and at least one image used for biometric identification does not necessarily correspond to at least one light source in one-to-one correspondence.
  • multiple images obtained by imaging may be fused to obtain a fused image; and biometric recognition may be performed according to the fused image.
  • biometric recognition may be performed based on the first image obtained by imaging; if recognition fails based on the first image, biometrics may be performed based on the next image obtained by imaging Recognition; if the recognition of multiple images obtained by imaging fails, the multiple images are fused to obtain a fused image; biometric recognition is performed according to the fused image.
  • biometric recognition may be performed according to the first image obtained by imaging; if recognition fails according to the first image, multiple images obtained by imaging are fused to obtain Fusion image; biometric recognition based on the fusion image.
  • FIG. 8 shows an example flowchart of a method for biometric recognition according to an embodiment of the present application.
  • the light sources provided in various directions are scanned in series, and images are sequentially formed according to the light signals transmitted from the skin when the light sources of the two light sources illuminate the skin.
  • an image corresponding to the first light source is first collected.
  • the first light source may be the default light source described in the foregoing embodiments.
  • biometric recognition is performed according to the image corresponding to the first light source, and if the recognition is successful, the recognition process is stopped. If the recognition fails, an image corresponding to the second light source is collected in 803, and biometric recognition is performed according to the image corresponding to the second light source in 804. Similarly, if the recognition is successful, the recognition process is stopped. If the recognition fails, the two images are fused in 805, and the fused images are used for biometric recognition.
  • the image fusion technology can extract the favorable information in each biometric image, and finally integrate it into a high-quality biometric image, which improves the performance of biometric recognition. Moreover, when performing biometric recognition, each single image is used for biometric recognition first, and image fusion is performed only when the recognition of all single images fails, and the speed of biometric recognition can be improved.
  • a light source on the habitual side can be first selected to transmit the imaging image of the skin for biometric recognition.
  • the image obtained through the skin of the light source on the habit side can be used for biometric recognition first. If the recognition is successful, the recognition is stopped, indicating that the user is an authorized legal user; if If the recognition fails, the multiple images obtained by fusion are used for biometric recognition based on the fused image.
  • the image obtained through the skin through the light source on the habit side is used for biometric recognition first. If the recognition is successful, the recognition is stopped, indicating that the user is an authorized legitimate user; if the recognition fails, the remaining Each image is biometrically identified. If there is at least one image that biometrics is successful, then stop biometrics; if all single images fail biometrics, then fuse all the images and use the fused images for biometrics Feature recognition.
  • the image obtained through the skin through the light source on the habit side is first used for biometric recognition. If the recognition is successful, the recognition is stopped, indicating that the user is an authorized legitimate user; if the recognition fails, the remaining Choose one of the images for biometric recognition, if the recognition is successful, stop the recognition; if the recognition fails, fuse the two images, use the fused image for biometric recognition, if the recognition is successful, stop the recognition; If the recognition fails, continue to select any one of the remaining images except the two images for biometric recognition. If the recognition succeeds, stop the biometric recognition; if the recognition fails, merge the three images and use After the fusion, the image is biometrically recognized.
  • the recognition is stopped; if the recognition fails, the above operation is continued until the biometric recognition is performed according to the last image. If the recognition is successful, the recognition is stopped; if the recognition fails, then All images are fused, and biometrics are identified based on the fused image.
  • An embodiment of the present application also provides an electronic device.
  • the electronic device includes a display screen and the above-mentioned biometric identification devices in various embodiments of the present application.
  • the electronic device may be any electronic device with a display screen, which uses the technical solutions of the embodiments of the present application to implement biometric identification.
  • the display screen can use any material that can transmit infrared light, which is not limited in this application.
  • the disclosed system and device may be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a division of logical functions.
  • there may be other divisions for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual couplings or direct couplings or communication connections may be indirect couplings or communication connections through some interfaces, devices, or units, and may also be electrical, mechanical, or other forms of connection.
  • 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, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments of the present application.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or software function unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the technical solution of the present application essentially or part of the contribution to the existing technology, or all or part of the technical solution can be embodied in the form of a software product
  • the computer software product is stored in a storage medium
  • several instructions are included to enable a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Security & Cryptography (AREA)
  • Human Computer Interaction (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Input (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种生物特征识别的方法、装置和电子设备。该生物特征识别的方法包括：依次根据至少一个光源中各个光源照射皮肤时从所述皮肤透射出的光信号进行成像；根据成像得到的至少一幅图像进行生物特征识别。该方法能够有效提升生物特征识别的性能。

Description

生物特征识别的方法、装置和电子设备 技术领域
本申请涉及信息技术领域，并且更具体地，涉及一种生物特征识别的方法、装置和电子设备。
背景技术
随着科学技术的快速发展，生物特征识别技术已经广泛应用到移动终端、智能家居等各个领域。目前，在生物特征识别时，采用一定波长的可见光照射生物特征，利用可见光的反射成像原理，将携带生物特征信息的反射光信号传送给传感器进行采集，根据采集的信息与事先注册存储的生物特征进行对比来确认用户身份的合法性。
然而，上述方式容易受到生物特征与检测面接触的影响。用户每次在进行生物特征识别时按压的力度大小和着力点不同，手指干燥等，可能会影响识别的性能。
因此，如何有效提升生物特征识别的性能成为一个亟待解决的问题。
发明内容
本申请实施例提供了一种生物特征识别的方法、装置以及电子设备，能够有效提升生物特征识别的性能。
第一方面，提供了一种生物特征识别的方法，包括：
依次根据至少一个光源中各个光源照射皮肤时从所述皮肤透射出的光信号进行成像；根据成像得到的至少一幅图像进行生物特征识别。
在本申请实施例中，采用至少一个光源中各个光源照射皮肤，利用光的透射成像原理，获取至少一幅用来进行生物特征识别的图像，在生物特征识别过程中生物特征可以不用与检测面接触，减小了接触面对生物特征识别的影响，从而提升了生物特征识别的性能。
在一些可能的实现方式中，所述至少一个光源为红外光源，所述光信号为红外光信号。
在一些可能的实现方式中，所述至少一个光源为多个光源，所述多个光源设置于相对于识别区域的不同方向上。
通过在相对于识别区域的不同方向上设置多个光源，可以依次利用不同方向上的光源进行成像，解决了在生物特征识别过程中采用单一光源时可能存在的某个方向照射时成像质量差的问题，从而能够进一步提升生物特征识别的性能。
在一些可能的实现方式中，所述根据成像得到的至少一幅图像进行生物特征识别，包括：对成像得到的多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可能实现的方式中，所述根据成像得到的至少一幅图像进行生物特征识别，包括：根据成像得到的第一幅图像进行生物特征识别；若根据所述第一幅图像的识别失败，则根据成像得到的下一幅图像进行生物特征识别；若根据成像得到的多幅图像的识别均失败，则对所述多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可能的实现方式中，所述根据成像得到的至少一幅图像进行生物特征识别，包括：根据成像得到的第一幅图像进行生物特征识别；若根据所述第一幅图像的识别失败，则对成像得到的多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可能的实现方式中，所述第一幅图像为根据所述多个光源中的默认光源照射所述皮肤时从所述皮肤透射出的光信号进行成像得到的图像。
在一些可能的实现方式中，所述多个光源包括第一光源和第二光源，所述第一光源与所述识别区域的中心的连线垂直于所述第二光源与所述识别区域的中心的连线。
第二方面，提供了一种生物特征识别的装置，包括：
至少一个光源；传感器，用于依次根据至少一个光源中各个光源照射皮肤时从所述皮肤透射出的光信号进行成像，其中，所述传感器成像得到的至少一幅图像用于进行生物特征识别。
在一些可能的实现方式中，所述至少一个光源为红外光源，所述光信号为红外光信号。
在一些可能的实现方式中，所述至少一个光源为多个光源，所述多个光源设置于相对于识别区域的不同方向上。
在一些可能的实现方式中，所述多个光源包括第一光源和第二光源，所述第一光源与所述识别区域的中心的连线垂直于所述第二光源与所述识别 区域的中心的连线。
在一些可能的实现方式中，所述装置还包括：
处理器，用于根据所述传感器成像得到的至少一幅图像进行生物特征识别。
在一些可能的实现方式中，所述处理器用于：对成像得到的多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可能的实现方式中，所述处理器用于：根据成像得到的第一幅图像进行生物特征识别；若根据所述第一幅图像的识别失败，则根据成像得到的下一幅图像进行生物特征识别；若根据成像得到的多幅图像的识别均失败，则对所述多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可能的实现方式中，所述处理器用于：根据成像得到的第一幅图像进行生物特征识别；若根据所述第一幅图像的识别失败，则对成像得到的多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可能的实现方式中，所述第一幅图像为所述传感器根据所述多个光源中的默认光源照射所述皮肤时从所述皮肤透射出的光信号进行成像得到的图像。
第三方面，提供了一种生物特征识别的电子设备，包括第二方面或第二方面的任意可能的实现方式中的生物特征识别装置。
附图说明
图1是本申请实施例的生物特征识别的装置的示意图。
图2和图3是本申请实施例的不同照射方向的生物特征图像的示意图。
图4和图5是本申请实施例的光源设置位置的示意图。
图6是本申请实施例的图像融合的示意图。
图7是本申请一个实施例的生物特征识别的方法的示意性流程图。
图8是本申请另一个实施例的生物特征识别的方法的示例流程图。
具体实施方式
下面将结合附图，对本申请实施例中的技术方案进行描述。
电子设备日益普及，逐步渗透到人们日常生活的各个方面，在为人们生 活提供便利的同时引起了信息安全的问题。随着科技的发展，传统密码识别技术存在容易丢失，被盗，遗忘等缺点。另外，它与用户并不唯一绑定，一旦别人获得了这些信息，他将拥有与失主同样的权利，对人们的生活造成了严重的安全影响。而生物特征识别很好地弥补了传统密码识别的缺点，因此生物特征识别技术越来越受到关注。
所谓生物识别技术就是，通过计算机与光学、声学、生物传感器和生物统计学原理等高科技手段密切结合，利用人体固有的生理特性，(如指纹、脸象、虹膜等)和行为特征(如笔迹、声音、步态等)来进行个人身份的鉴定，可广泛用于政府、军队、银行、社会福利保障、电子商务、安全防务。在当今信息化和科技化的时代，生物特征识别正在逐渐兴起，逐步取代传统密码识别将是大势所趋。
光学生物特征识别具体识别过程可以为：采用一定波长的可见光作为照射生物特征的光源，通常采用波长为500nm-560nm的绿光。当生物特征触摸、按压或者接近(为便于描述，在本申请中统称为按压)检测面时，可见光源发射的可见光经过与检测面接触的生物特征的反射，形成包含生物特征信息的光信号，光学传感器接收该反射光线，利用光的反射成像原理进行生物特征识别。
但由于可见光不能穿透皮肤表层，只能扫描手指皮肤的表面或者死性皮肤层，容易受到手指和检测面接触的影响，降低了生物特征识别的性能。
为了提升生物特征识别的性能，本申请实施例提供了一种基于光的透射成像原理的生物特征识别的技术方案。
图1示出了本申请实施例的生物特征识别的装置的示意图。
如图1所示，本申请实施例的生物特征识别的装置可以包括至少一个光源110；以及传感器120。
至少一个光源110为生物特征识别的激励光源。
传感器120依次根据至少一个光源中各个光源照射皮肤时从所述皮肤透射出的光信号进行成像，其中，所述传感器120成像得到的至少一幅图像用于进行生物特征识别。
在本申请实施例中，根据从皮肤透射出的光信号进行成像。以指纹识别为例，如图1所示，光源110产生能够透射皮肤的光，该光照射手指并透射手指皮肤进入真皮层，经过手指表皮下组织的反射和散射后，再从皮肤透射 出去。当透射出的光经过手指指纹中的谷和脊时，指纹谷和指纹脊对光的吸收能力不同，具体地，指纹谷对光的吸收能力较弱，透射出的光强，而指纹脊对光的吸收能力较强，透射出的光较弱。因此从手指皮肤透射出的携带有指纹特征信息的光信号进入传感器120中，传感器120采集光信号中包括的指纹特征信息成像，进行指纹识别。
在本申请实施例中，采用至少一个光源中各个光源照射皮肤，利用光的透射成像原理，获取至少一幅用来进行生物特征识别的图像，在生物特征识别过程中生物特征可以不用与检测面接触，减小了接触面对生物特征识别的影响，从而提升了生物特征识别的性能。
应理解，本申请实施例的技术方案可以应用于各种电子设备，例如智能手机、笔记本电脑、平板电脑、游戏设备等便携式或移动计算设备，以及电子数据库、汽车、银行自动柜员机(Automated Teller Machine，ATM)等其他电子设备，但本申请实施例对此并不限定。
还应理解，本申请实施例的技术方案除了可以进行指纹识别外，还可以进行其他基于透射成像原理的生物特征识别，例如，人脸识别等，本申请实施例对此也不限定。为了便于描述，本申请实施例以指纹识别为例进行说明。
在一些可替代的实施例中，光源110可以为红外光源，透射出手指皮肤的光信号为红外光信号。
可选地，在一些实施例中，该光源110可以为能够产生红外光的发光二极管(Light-Emitting Diode，LED)，激光二极管(Laser Diode，LD)或光电二极管等，本申请实施例对此不作限定。
在一些可替代的实施例中，光源110还可以为其它能够透射皮肤的光，例如近红外光等，相应的透射的光信号为近红外信号，本申请实施例对此并不作限定。
应理解，本申请实施例并不特别限定光源110和传感器120的相对位置关系，光源110和传感器120可以并排放置，或者按照其他方式放置，只要光源110和传感器120可以生物特征识别即可。
本申请实施例的技术方案可以为屏下生物特征识别的技术方案，即传感器或相关部件设置于显示屏下，也可以为屏内生物特征识别的技术方案，即传感器或相关部件设置于显示屏内。
可选地，在一些实施例中，该传感器120可以为互补金属氧化物半导体 (Complementary Metal Oxide Semiconductor，CMOS)传感器，使用传感器120采集所需检测区域的生物特征。CMOS传感器工艺较成熟，中心敏感波长的范围通过工艺掺杂更容易实现，成本相对电荷耦合元件(Charge-coupled Device，CCD)低，驱动电路相对CCD更简单。传感器120也可使用其他类型的传感器，本申请实施例对此不作限定。
可选地，在一些实施例中，该传感器120还可以和距离传感器结合使用，该距离传感器用于检测用户的生物特征，如手指或手掌等到该生物特征检测区域的距离，进一步可以在该距离小于或等于特定的距离阈值时，将该传感器120从待机(休眠)状态切换至工作状态，以便于进行图像的采集。
应理解，当传感器120处于工作状态时，在生物特征靠近时，传感器120可以进行图像采集；当传感器120处于待机状态时，即使生物特征靠近传感器120，该传感器120也不进行图像采集，因此，在不进行图像采集时，将传感器120切换至待机状态，能够降低设备的功耗。
可选地，在一些实施例中，该距离阈值可以为传感器120的成像距离，即该传感器120能够成像的最远距离，例如，该距离阈值可以为10cm，5cm等，具体值可以根据实际需求决定。
在本申请实施例中，主要利用了光透射成像原理，光源照射生物特征的方向与生物特征中纹路的方向对于成像结果比较重要。当光源照射的方向与生物特征中纹路的方向垂直时，基本可以获取清晰的生物特征图像，如图2所示。当光源照射的方向与生物特征中大部分纹路的方向平行时，图像整体质量较差，如图3所示，不能准确表示出生物特征的完整信息，影响到后续对生物特征的认证。
为了解决上述单一光源透射皮肤成像时引起的问题，进一步提升生物特征识别的性能，本申请实施例在相对于识别区域的不同方向上设置多个光源110，多个光源110可以从不同方向照射生物特征，传感器120相应地成像得到多幅图像，用于进行生物特征识别，以提升生物特征识别的性能。
上述识别区域可以为显示屏的部分区域，也可以为显示屏的整个区域，即全屏生物特征识别。
可选地，所述多个光源110可以包括第一光源和第二光源，所述第一光源与所述识别区域的中心的连线垂直于所述第二光源与所述识别区域的中心的连线。也就是说，多个光源中至少两个光源的设置位置使得它们照射生 物特征的方向垂直。
图4示出了本申请一个实施例中两个光源的设置位置的示意图。
图4为俯视图，如图4所示，两个光源110与传感器120可以形成一个等腰三角形。可选地，等腰三角形的顶角可以为钝角，识别区域可设置于传感器120的上方，这样，两个光源110可以以大致垂直的照射方向照射识别区域上的生物特征。在进行识别时，两个光源110可以依次从不同方向照射皮肤，传感器120相应地依次根据每个光源照射皮肤时从皮肤透射的光信号进行成像。这样可以获取两幅图像，后续可以根据需要基于至少一幅图像进行生物特征识别。
图5示出了本申请另一个实施例中四个光源的设置位置的示意图。
图5为俯视图，如图5所示，四个光源110可以设置于以传感器120的中心为中心的矩形的四个角的位置。识别区域可设置于传感器120的上方，这样，四个光源110可以以大致垂直的照射方向照射识别区域上的生物特征。在进行识别时，四个光源110依次从不同方向照射皮肤，传感器120相应地可以依次根据每个光源照射皮肤时从皮肤透射的光信号进行成像。这样可以获取四幅图像，后续可以根据需要基于至少一幅图像进行生物特征识别。
通过在相对于识别区域的不同方向上设置多个光源，可以依次利用不同方向上的光源进行成像，解决了在生物特征识别过程中采用单一光源时可能存在的某个方向照射时成像质量差的问题，从而能够进一步提升生物特征识别的性能。
在一些可替代的实施例中，在图4和图5示出的一个光源位置处还可以设置多个光源，本申请实施例对此不作限定。
应理解，以上仅示出了两个光源和四个光源的位置的示意图，还可以设置更多个光源，本申请实施例对比不作限定。
还应理解，本申请实施例中，一个光源与所述识别区域的中心连线垂直于另一个光源与所述识别区域的中心连线，实际应用中，两者之间的角度可以是近似90度，而不限定于90度，例如，可以为80度，也可以为100度，本申请实施例对此不作限定。
在一些可替代的实施方式中，依次得到多幅生物特征图像的过程中，可以通过串行扫描不同方向的光源，获取多幅生物特征图像。
在一些可替代的实施方式中，生物特征识别的装置中还可以包括控制电 路，用于依次控制各个光源开启顺序。该控制电路与每个光源连接，用于控制光源的开启顺序。例如，通过控制电路先开启第一光源照射皮肤，传感器根据从所述皮肤透射出的光信号进行成像，然后控制电路控制关闭第一光源，开启第二光源，再获取对应的生物特征图像，以此类推。
应理解，实际应用中，可以以任一顺序控制光源开启，本申请实施例对此并不作限定。
可选地，生物特征识别装置还可以包括处理器，用于根据所述传感器120成像得到的至少一幅图像进行生物特征识别。
该处理器可以是电子设备的处理器，也可以是单独设置的用于生物特征识别的处理器，本申请实施例对此并不限定。
可选地，在本申请一个实施例中，所述处理器用于：
对成像得到的多幅图像进行融合，得到融合图像；
根据所述融合图像进行生物特征识别。
在本实施例中，处理器直接对依次得到的多幅图像进行融合，得到融合图像，并根据所述融合图像进行生物特征识别。
可选地，处理器也可以先根据最先得到的第一幅图像进行生物特征识别，再根据识别结果确定是否需要进行多幅图像的融合，下面进行详细描述。
可选地，在本申请一个实施例中，所述处理器用于：
根据成像得到的第一幅图像进行生物特征识别；
若根据所述第一幅图像的识别失败，则根据成像得到的下一幅图像进行生物特征识别；
若根据成像得到的多幅图像的识别均失败，则对所述多幅图像进行融合，得到融合图像；
根据所述融合图像进行生物特征识别。
具体而言，在本实施例中，先采集第一幅图像。可选地，所述第一幅图像可以为所述传感器根据所述多个光源中的默认光源照射所述皮肤时从所述皮肤透射出的光信号进行成像得到的图像。例如，该默认光源可以是手指以最习惯的方式接近显示屏时，能获取最高质量的图像的光源。处理器先根据成像得到的第一幅图像进行生物特征识别，若识别成功则结束识别流程。若识别失败，则采集下一幅图像，处理器根据成像得到的下一幅图像进行生物特征识别，以此类推。若根据成像得到的多幅图像的识别均失败，则再对 所述多幅图像进行融合，得到融合图像，并根据所述融合图像进行生物特征识别。采用该实施例的方式，在通常情况下可以不用采集所有的图像以及进行图像融合，从而可以提高识别速度。
可选地，在本申请一个实施例中，所述处理器用于：
根据成像得到的第一幅图像进行生物特征识别；
若根据所述第一幅图像的识别失败，则对成像得到的多幅图像进行融合，得到融合图像；
根据所述融合图像进行生物特征识别。
具体而言，在本实施例中，先采集第一幅图像。所述第一幅图像可以与前述实施例中的类似，不再赘述。处理器先根据成像得到的第一幅图像进行生物特征识别，若识别成功则结束识别流程。若识别失败，则采集其他图像，处理器对得到的多幅图像进行融合，得到融合图像，并根据所述融合图像进行生物特征识别。类似地，采用该实施例的方式，在通常情况下可以不用采集所有的图像以及进行图像融合，从而可以提高识别速度。
图6是本申请实施例的图像融合的示意图。
如图6所示，以指纹成像为例，图中包含三幅获取的指纹图像，分别为图像(a)、图像(b)、图像(c)，分别为三个光源依次照射皮肤时从所述皮肤透射出的光信号进行成像得到的。用于成像的光源的照射方向不同，可能与指纹中部分纹路方向平行，因此生成的指纹图像不清楚。如图像(a)中指纹图像的顶部部分不清楚，图像(b)中指纹图像右侧存在部分不清楚，图像(c)中指纹图像左侧不清楚。为了得到一幅清晰的指纹图像，可将三幅存在缺陷的图像经过图像融合处理，得到清晰的指纹图像，融合后的图像包含完整的生物特征细节信息，而且提高了图像质量，进一步提升了生物特征识别的性能。
应理解，本申请实施例中图像融合的方法可以采用任意一种融合方法，例如小波变换、灰度加权平均法或者金字塔分解融合方法，本申请实施例对此不作限定。
图7示出了本申请一个实施例的生物特征识别的方法的示意性流程图。
图7中的步骤或操作仅是示例，本申请实施例还可以执行其它操作或者图7的各种操作的变形。此外，图7中的各个步骤可以分别按照与图7所呈现的不同的顺序来执行，并且有可能并非要执行图7中的全部操作。
图7所示的方法可以由前述本申请实施例中的生物特征识别的装置执 行，相关描述可以参考前述实施例，另外，以下实施例中的描述，也可以结合到前述实施例中，为了简洁，不再赘述。
如图7所示，该方法700可以包括如下步骤。
701，依次根据至少一个光源中各个光源照射皮肤时从皮肤透射的光信号进行成像。
702，根据成像得到的至少一幅图像进行生物特征识别。
应说明的是，本申请实施例中，进行生物特征识别的至少一幅图像不一定与701中至少一个光源对应，当只有一个光源时，获得一幅图像，此时所述的至少一个光源与至少一幅图像对应。当至少一个光源为多个光源时，可以得到多幅图像，也可以只得到一幅图像，用于进行生物特征识别的至少一幅图像与至少一个光源并不一定一一对应。
可选地，在本申请一个实施例中，可以对成像得到的多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
可选地，在本申请一个实施例中，可以根据成像得到的第一幅图像进行生物特征识别；若根据所述第一幅图像的识别失败，则根据成像得到的下一幅图像进行生物特征识别；若根据成像得到的多幅图像的识别均失败，则对所述多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
可选地，在本申请一个实施例中，可以根据成像得到的第一幅图像进行生物特征识别；若根据所述第一幅图像的识别失败，则对成像得到的多幅图像进行融合，得到融合图像；根据所述融合图像进行生物特征识别。
在一些可替代的实施方式中，并不需要将所获取的所有图像全部进行融合，可以任取其中几幅进行融合，利用融合后图像进行生物特征识别，本申请实施例对此不作限定。
实际中，在进行生物特征识别的过程中，图像融合算法计算复杂度较高，随着参与融合的图像数量增加，复杂度增大，耗时大，生物特征识别的实时性变差，影响实际应用，由此可以根据需要进行图像融合，进一步提高识别速度。
图8示出了本申请一个实施例的生物特征识别的方法的示例流程图。
应说明的是，在本申请实施例中，以两个光源为例，在实际中，光源的个数并不限于此，可根据实际应用场景的不同来设置，本申请实施例对此并 不作限定。
如图8所示，优选地，在进行生物特征识别时，串行扫描各个方向设置的光源，依次根据两个光源中的各个光源照射皮肤时从所述皮肤透射出的光信号进行成像。为了提高生物特征识别的速度，在801中先采集第一光源对应的图像。第一光源可以为前述实施例中描述的默认光源。在802中根据第一光源对应的图像进行生物特征识别，若识别成功，则停止识别过程。若该识别失败，则在803中采集第二光源对应的图像，并在804中根据第二光源对应的图像进行生物特征识别。同样地，若识别成功，则停止识别过程。若识别失败，则在805中将这两幅图像进行融合，利用融合得到的图像进行生物特征识别。
由于图像融合技术能够提取各个生物特征图像中的有利信息，最后综合成高质量的生物特征图像，提高了生物特征识别的性能。而且，在进行生物特征识别时，先利用各个单幅图像进行生物特征识别，当所有单幅图像识别失败时才进行图像融合，又能够提升生物特征识别的速度。
可选地，在实际应用中，可以先选择习惯侧的光源(默认光源)透射皮肤的成像图像进行生物特征识别。
在一些可替代的实施方式中，具有多个光源时，可以先利用习惯侧的光源透射皮肤得到的图像进行生物特征识别，若识别成功，则停止识别，表明该用户为授权的合法用户；若识别失败，则融合所得到的多幅图像，根据融合后图像进行生物特征识别。
在一些可替代的实施方式中，先利用习惯侧的光源透射皮肤得到的图像进行生物特征识别，若识别成功，则停止识别，表明该用户为授权的合法用户；若识别失败，则先利用其余各幅图像分别进行生物特征识别，若存在至少一幅图像生物特征识别成功，则停止生物特征识别；若所有的单幅图像均生物特征识别失败，则融合所有的图像，利用融合后图像进行生物特征识别。
在一些可替代的实施方式中，先利用习惯侧的光源透射皮肤得到的图像进行生物特征识别，若识别成功，则停止识别，表明该用户为授权的合法用户；若识别失败，则从剩余的图像中任选一幅图像用来进行生物特征识别，若识别成功，则停止识别；若识别失败，则融合这两幅图像，利用融合后图像进行生物特征识别，若识别成功，则停止识别；若识别失败，则继续在除过这两幅图像的其余图像中任意选择一幅用来进行生物特征识别，若识别成 功，则停止生物特征识别；若识别失败，则融合这三幅图像，利用融合后图像进行生物特征识别，若识别成功，则停止识别；若识别失败，则继续重复上述操作，直至根据最后一幅图像进行生物特征识别，若识别成功，则停止识别；若识别失败，则融合所有的图像，根据融合后图像进行生物特征识别。
本申请实施例还提供了一种电子设备，该电子设备包括显示屏以及上述本申请各种实施例中的生物特征识别装置。
该电子设备可以为任何具有显示屏的电子设备，其采用本申请实施例的技术方案实现生物特征识别。
显示屏可以采用任何能够透射红外光的材质，本申请对此不作限定。
应理解，本申请实施例中的具体的例子只是为了帮助本领域技术人员更好地理解本申请实施例，而非限制本申请实施例的范围。
应理解，在本申请实施例和所附权利要求书中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请实施例。例如，在本申请实施例和所附权利要求书中所使用的单数形式的“一种”、“上述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
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，可以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。另外，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，也可以是电的，机械的或其它的形式连接。
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申请实施例方案的目的。
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，也可以是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，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元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介质中。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介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，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。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (18)

  1. 一种生物特征识别的方法，其特征在于，包括：
    依次根据至少一个光源中各个光源照射皮肤时从所述皮肤透射出的光信号进行成像；
    根据成像得到的至少一幅图像进行生物特征识别。
  2. 根据权利要求1所述的方法，其特征在于，所述至少一个光源为红外光源，所述光信号为红外光信号。
  3. 根据权利要求1或2所述的方法，其特征在于，所述至少一个光源为多个光源，所述多个光源设置于相对于识别区域的不同方向上。
  4. 根据权利要求3所述的方法，其特征在于，所述根据成像得到的至少一幅图像进行生物特征识别，包括：
    对成像得到的多幅图像进行融合，得到融合图像；
    根据所述融合图像进行生物特征识别。
  5. 根据权利要求3所述的方法，其特征在于，所述根据成像得到的至少一幅图像进行生物特征识别，包括：
    根据成像得到的第一幅图像进行生物特征识别；
    若根据所述第一幅图像的识别失败，则根据成像得到的下一幅图像进行生物特征识别；
    若根据成像得到的多幅图像的识别均失败，则对所述多幅图像进行融合，得到融合图像；
    根据所述融合图像进行生物特征识别。
  6. 根据权利要求3所述的方法，其特征在于，所述根据成像得到的至少一幅图像进行生物特征识别，包括：
    根据成像得到的第一幅图像进行生物特征识别；
    若根据所述第一幅图像的识别失败，则对成像得到的多幅图像进行融合，得到融合图像；
    根据所述融合图像进行生物特征识别。
  7. 根据权利要求5或6所述的方法，其特征在于，所述第一幅图像为根据所述多个光源中的默认光源照射所述皮肤时从所述皮肤透射出的光信号进行成像得到的图像。
  8. 根据权利要求3至7中任一项所述的方法，其特征在于，所述多个光源包括第一光源和第二光源，所述第一光源与所述识别区域的中心的连线垂直于所述第二光源与所述识别区域的中心的连线。
  9. 一种生物特征识别的装置，其特征在于，包括：
    至少一个光源；
    传感器，用于依次根据至少一个光源中各个光源照射皮肤时从所述皮肤透射出的光信号进行成像，其中，所述传感器成像得到的至少一幅图像用于进行生物特征识别。
  10. 根据权利要求9所述的装置，其特征在于，所述至少一个光源为红外光源，所述光信号为红外光信号。
  11. 根据权利要求9或10所述的装置，其特征在于，所述至少一个光源为多个光源，所述多个光源设置于相对于识别区域的不同方向上。
  12. 根据权利要求9至11中任一项所述的装置，其特征在于，所述多个光源包括第一光源和第二光源，所述第一光源与所述识别区域的中心的连线垂直于所述第二光源与所述识别区域的中心的连线。
  13. 根据权利要求9至12中任一项所述的装置，其特征在于，所述装置还包括：
    处理器，用于根据所述传感器成像得到的至少一幅图像进行生物特征识别。
  14. 根据权利要求13所述的装置，其特征在于，所述处理器用于：
    对成像得到的多幅图像进行融合，得到融合图像；
    根据所述融合图像进行生物特征识别。
  15. 根据权利要求13所述的装置，其特征在于，所述处理器用于：
    根据成像得到的第一幅图像进行生物特征识别；
    若根据所述第一幅图像的识别失败，则根据成像得到的下一幅图像进行生物特征识别；
    若根据成像得到的多幅图像的识别均失败，则对所述多幅图像进行融合，得到融合图像；
    根据所述融合图像进行生物特征识别。
  16. 根据权利要求13所述的装置，其特征在于，所述处理器用于：
    根据成像得到的第一幅图像进行生物特征识别；
    若根据所述第一幅图像的识别失败，则对成像得到的多幅图像进行融合，得到融合图像；
    根据所述融合图像进行生物特征识别。
  17. 根据权利要求15或16所述的装置，其特征在于，所述第一幅图像为所述传感器根据所述多个光源中的默认光源照射所述皮肤时从所述皮肤透射出的光信号进行成像得到的图像。
  18. 一种电子设备，其特征在于，包括：根据权利要求9至17中任一项所述的生物特征识别的装置。
PCT/CN2018/109349 2018-10-08 2018-10-08 生物特征识别的方法、装置和电子设备 WO2020073169A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
PCT/CN2018/109349 WO2020073169A1 (zh) 2018-10-08 2018-10-08 生物特征识别的方法、装置和电子设备
CN201880001745.6A CN109496308A (zh) 2018-10-08 2018-10-08 生物特征识别的方法、装置和电子设备
EP18936824.4A EP3798876A4 (en) 2018-10-08 2018-10-08 BIOMETRIC IDENTIFICATION METHOD AND DEVICE AND ELECTRONIC DEVICE
US17/112,686 US20210117645A1 (en) 2018-10-08 2020-12-04 Method and apparatus for biometric identification and electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/109349 WO2020073169A1 (zh) 2018-10-08 2018-10-08 生物特征识别的方法、装置和电子设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/112,686 Continuation US20210117645A1 (en) 2018-10-08 2020-12-04 Method and apparatus for biometric identification and electronic device

Publications (1)

Publication Number Publication Date
WO2020073169A1 true WO2020073169A1 (zh) 2020-04-16

Family

ID=65713854

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/109349 WO2020073169A1 (zh) 2018-10-08 2018-10-08 生物特征识别的方法、装置和电子设备

Country Status (4)

Country Link
US (1) US20210117645A1 (zh)
EP (1) EP3798876A4 (zh)
CN (1) CN109496308A (zh)
WO (1) WO2020073169A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021035451A1 (zh) 2019-08-23 2021-03-04 深圳市汇顶科技股份有限公司 指纹检测装置、方法和电子设备
CN111095285B (zh) * 2019-08-23 2021-09-17 深圳市汇顶科技股份有限公司 指纹识别装置和电子设备
CN111095282B (zh) 2019-10-18 2023-09-05 深圳市汇顶科技股份有限公司 指纹检测装置和电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4699149A (en) * 1984-03-20 1987-10-13 Joseph Rice Apparatus for the identification of individuals
CN102804229A (zh) * 2009-06-08 2012-11-28 日本电气株式会社 确定设备、指纹输入设备、确定方法以及确定程序
CN104361315A (zh) * 2014-10-27 2015-02-18 浙江工业大学 基于单目多视角立体机器视觉的3d指纹识别装置
CN106778446A (zh) * 2015-11-24 2017-05-31 秦皇岛鸿大科技开发有限公司 一种近红外指静脉图像采集***
CN108596136A (zh) * 2018-05-02 2018-09-28 苏州大学 指纹及静脉双重生物特征提取光学成像***

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002312771A (ja) * 2001-04-16 2002-10-25 Omron Corp 指紋画像入力装置
JP3858263B2 (ja) * 2001-11-09 2006-12-13 日本電気株式会社 指紋画像入力装置及びそれを用いた電子機器
JP2003233805A (ja) * 2001-12-04 2003-08-22 Canon Inc 画像入力装置
US7627151B2 (en) * 2003-04-04 2009-12-01 Lumidigm, Inc. Systems and methods for improved biometric feature definition
JP2006106979A (ja) * 2004-10-01 2006-04-20 Mitsubishi Electric Corp 指紋画像撮像装置
CN205384628U (zh) * 2016-02-27 2016-07-13 深圳市生强科技有限公司 活体指纹识别装置
CN206162730U (zh) * 2016-08-08 2017-05-10 深圳市释金石科技有限公司 具有指静脉识别的门锁
CN108255356A (zh) * 2016-12-29 2018-07-06 上海箩箕技术有限公司 自发光显示面板、显示模组和显示模组的使用方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4699149A (en) * 1984-03-20 1987-10-13 Joseph Rice Apparatus for the identification of individuals
CN102804229A (zh) * 2009-06-08 2012-11-28 日本电气株式会社 确定设备、指纹输入设备、确定方法以及确定程序
CN104361315A (zh) * 2014-10-27 2015-02-18 浙江工业大学 基于单目多视角立体机器视觉的3d指纹识别装置
CN106778446A (zh) * 2015-11-24 2017-05-31 秦皇岛鸿大科技开发有限公司 一种近红外指静脉图像采集***
CN108596136A (zh) * 2018-05-02 2018-09-28 苏州大学 指纹及静脉双重生物特征提取光学成像***

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3798876A4 *

Also Published As

Publication number Publication date
CN109496308A (zh) 2019-03-19
EP3798876A4 (en) 2021-08-18
EP3798876A1 (en) 2021-03-31
US20210117645A1 (en) 2021-04-22

Similar Documents

Publication Publication Date Title
KR102367761B1 (ko) 바이오메트릭 인식을 위한 시스템들 및 방법들
CN107438854B (zh) 使用移动设备捕获的图像执行基于指纹的用户认证的***和方法
JP5609970B2 (ja) 無線端末の機能への制御アクセス
JP5292821B2 (ja) 静脈画像取得装置および静脈画像取得方法
JP4468896B2 (ja) 生体情報による認証装置
US20140341440A1 (en) Identity caddy: a tool for real-time determination of identity in the mobile environment
Buciu et al. Biometrics systems and technologies: A survey
JP4636140B2 (ja) 静脈撮像装置、静脈撮像方法および静脈認証装置
US20210117645A1 (en) Method and apparatus for biometric identification and electronic device
US20110007951A1 (en) System and method for identification of fingerprints and mapping of blood vessels in a finger
CN104933344A (zh) 基于多生物特征模态的移动终端用户身份认证装置及方法
JP2009544108A (ja) 多重生体認証のマルチスペクトル画像
CN104598870A (zh) 基于智能移动信息设备的指纹活体检测方法
WO2013131407A1 (zh) 双验证人脸防伪方法及装置
WO2014025448A1 (en) Spoof detection for biometric authentication
CN204791017U (zh) 基于多生物特征模态的移动终端用户身份认证装置
Drahanský Liveness detection in biometrics
US20220300593A1 (en) System and method of biometric identification of a subject
KR101875182B1 (ko) 생체정보를 이용한 다중 안전 잠금 기능을 구비하는 해킹방지용 금융 거래 중계 시스템의 처리 방법
Sepasian et al. Vitality detection in fingerprint identification
Sepasian et al. Liveness and spoofing in fingerprint identification: Issues and challenges
Patil et al. Iris recognition using fuzzy system
KR20190092635A (ko) 생체정보를 이용한 대중교통 무임승차 작동 방법 및 그의 처리 시스템
CN115457602A (zh) 一种生物特征识别方法和***
Pishva Use of spectral biometrics for aliveness detection

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: 18936824

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018936824

Country of ref document: EP

Effective date: 20201221

NENP Non-entry into the national phase

Ref country code: DE