WO2022156088A1 - 指纹签名生成方法、装置、电子设备及计算机存储介质 - Google Patents

指纹签名生成方法、装置、电子设备及计算机存储介质 Download PDF

Info

Publication number
WO2022156088A1
WO2022156088A1 PCT/CN2021/090722 CN2021090722W WO2022156088A1 WO 2022156088 A1 WO2022156088 A1 WO 2022156088A1 CN 2021090722 W CN2021090722 W CN 2021090722W WO 2022156088 A1 WO2022156088 A1 WO 2022156088A1
Authority
WO
WIPO (PCT)
Prior art keywords
fingerprint
data
signature
pressure
texture
Prior art date
Application number
PCT/CN2021/090722
Other languages
English (en)
French (fr)
Inventor
张涛
Original Assignee
平安科技(深圳)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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2022156088A1 publication Critical patent/WO2022156088A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/13Sensors therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/50Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/40Analysis of texture
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition
    • G06V30/32Digital ink
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20212Image combination
    • G06T2207/20221Image fusion; Image merging

Definitions

  • the present application relates to the technical field of data processing, and in particular, to a method, apparatus, electronic device, and computer-readable storage medium for generating a fingerprint signature.
  • a fingerprint signature generation method provided by this application includes:
  • the texture track data, the pressure quantization data and the signature data are equidistantly fused to obtain the user's fingerprint signature.
  • the application also provides a fingerprint signature generation device, the device comprising:
  • an area extraction module used for acquiring the fingerprint image of the user, and extracting the fingerprint area on the fingerprint image to obtain the fingerprint area
  • a trajectory analysis module configured to perform texture trajectory analysis on the fingerprint region to obtain texture trajectory data
  • a pressure analysis module used for acquiring the user's fingerprint pressing data, and performing pressure data analysis on the fingerprint pressing data to obtain pressure quantification data
  • a signature recognition module used to obtain the user's electronic signature, perform signature recognition on the electronic signature, and obtain signature data
  • a data fusion module configured to perform equidistant data fusion of the texture trajectory data, the pressure quantization data and the signature data to obtain the user's fingerprint signature.
  • the present application also provides an electronic device, the electronic device comprising:
  • the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a fingerprint signature generation method as described below:
  • the texture track data, the pressure quantization data and the signature data are equidistantly fused to obtain the user's fingerprint signature.
  • the present application also provides a computer-readable storage medium, including a storage data area and a storage program area, the storage data area stores created data, and the storage program area stores a computer program; wherein, the computer program is implemented as follows when executed by a processor The described fingerprint signature generation method:
  • the texture track data, the pressure quantization data and the signature data are equidistantly fused to obtain the user's fingerprint signature.
  • FIG. 1 is a schematic flowchart of a method for generating a fingerprint signature provided by an embodiment of the present application
  • FIG. 2 is a schematic block diagram of a fingerprint signature generation device provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of the internal structure of an electronic device implementing a fingerprint signature generation method provided by an embodiment of the present application
  • the embodiment of the present application provides a method for generating a fingerprint signature.
  • the execution body of the fingerprint signature generation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application.
  • the fingerprint signature generation method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
  • the fingerprint signature generation method includes:
  • the fingerprint image is an image including the user's fingerprint, for example, an image including an electronic photo of the user's fingerprint or a written text with the user's fingerprint.
  • a mobile phone or any device with a camera function may be used to take a picture to obtain a fingerprint image of the user.
  • the embodiment of the present application uses a convolutional neural network with a feature extraction function to extract the fingerprint region of the fingerprint image, so as to reduce the size of the fingerprint image.
  • the size of the fingerprint image improves the efficiency of obtaining fingerprint information from a fingerprint image, wherein the fingerprint area is an image area in the fingerprint image that contains fingerprint information.
  • the performing fingerprint region extraction on the fingerprint image includes:
  • the fingerprint restoration image is segmented according to the target category probability to obtain a fingerprint area.
  • the segmentation process includes classifying the pixels in the fingerprint restoration image, the preset target category includes a plurality of preset categories, and the fingerprint restoration image is classified according to the preset target category probability.
  • the segmentation process is performed to obtain a fingerprint area, that is, it is determined that the preset category with the highest target category probability of the target pixel point in the fingerprint restoration image is the pixel category of the target pixel point.
  • the preset target category includes category A, category B and category C
  • the probability that the target pixel in the fingerprint restoration image is category A in the preset target category is 20%
  • the target pixel in the fingerprint restoration image is the preset target category
  • the probability of category B in the fingerprint restoration image is 70%
  • the probability that the target pixel in the fingerprint restoration image is the category C in the preset target category is 40%
  • the target pixel in the fingerprint restoration image is determined to be category B. All pixel points have completed the segmentation operation, and it is determined that the area where the pixel points in the restored fingerprint image are classified as the pixels of the fingerprint category is the fingerprint area.
  • the global feature map is upsampled by a first threshold multiple to obtain an intermediate feature map, and then the intermediate feature map is upsampled by a second threshold multiple to obtain a fingerprint restoration image, avoiding direct upsampling of the global feature map
  • the upsampling multiplier is too large to restore the fingerprint image, the image features in the restored fingerprint image are lost, and the integrity of the feature information in the restored fingerprint image is improved.
  • the method may further include:
  • Grayscale pixel conversion and contrast stretching processing are performed on the fingerprint region.
  • the grayscale pixel conversion is to input all the pixels in the fingerprint region into a grayscale value conversion formula to perform grayscale value conversion to generate the grayscale image.
  • the gray value conversion formula is:
  • R, G, and B are the three components of the pixels in the fingerprint area
  • Gary is the grayscale image obtained by converting the grayscale pixels in the fingerprint area.
  • the contrast stretching process includes:
  • the grayscale probability density of each pixel is stretched and transformed to obtain the fingerprint region after the ratio stretching process.
  • a grayscale density function pre-compiled in MATLAB can be used to count the grayscale probability density of each pixel in the fingerprint region after grayscale pixel conversion.
  • the following stretching transformation function can be used to perform contrast stretching processing on the fingerprint region:
  • a is the preset linear slope
  • D a is the gray value of the fingerprint area before the contrast stretching
  • D b is the gray value of the fingerprint area after the contrast stretching
  • b is the intercept of D b on the Y axis .
  • the embodiment of the present application does not analyze the fingerprint region. Perform grayscale pixel conversion and contrast stretching processing.
  • grayscale pixel conversion and contrast stretching are performed on the fingerprint area, which can highlight the texture trajectory of the fingerprint in the fingerprint area. It is beneficial to improve the accuracy of texture trajectory data obtained by analyzing the texture trajectory of the fingerprint region.
  • performing texture trajectory analysis on the fingerprint region to obtain texture trajectory data including:
  • the gray frequency field, the sum of the tangential pixels and the sum of the normal pixels are integrated to obtain texture track data.
  • the embodiment of the present application uses the following calculation formula to calculate the grayscale frequency field f of the fingerprint region:
  • V(x) is the total amount of vertical change of gray level of any two pixels on the fingerprint area
  • x 1 and x 2 are the horizontal coordinate values of any two different pixels on the fingerprint area respectively
  • h( x) represents the grayscale function in the vertical direction of the fingerprint area
  • a m is the average amplitude of the fingerprint waveform between any two different pixels on the fingerprint area.
  • any device with a pressure sensor function can be used to collect and obtain the user's fingerprint pressing data, wherein the fingerprint pressing data refers to the pressure data generated when the user presses the device with the pressure sensor function, including but It is not limited to the magnitude of the pressure, the changing trend of the pressure and/or the direction of applying the pressure, etc.
  • the pressure data analysis is performed on the fingerprint pressing data to obtain pressure quantification data, including:
  • Z is the instantaneous pressure value of pixel point (x, y); T(x, y) is the pressure gradient field of pixel point (x, y); G x (x, y) is the instantaneous pressure value Z at point (x, y) ,y) partial derivative with respect to x G y (x, y) is the partial derivative of instantaneous pressure value Z at point (x, y) to y ⁇ (x,y) is the application direction of the instantaneous pressure value Z;
  • are determined as pressure quantification data.
  • V x (x, y) is the pressure applied in the direction of the horizontal axis
  • V y (x, y) is the pressure applied in the direction of the vertical axis
  • ⁇ (x, y) is the field function of the pressure direction
  • w is the initial direction Parameters
  • G x (x, y) is the partial derivative of the instantaneous pressure function Z at the point (x, y) to x
  • G y (x, y) is the partial derivative of instantaneous pressure function Z at point (x, y) to y
  • i is the preset horizontal axis error of point (x, y)
  • j is the preset vertical axis error of point (x, y).
  • the user's electronic signature can be obtained from the blockchain for storing the user's electronic signature by using a python statement with a data capture function.
  • Using blockchain to keep data confidential can improve the security of electronic signatures, and at the same time, using blockchain's high data throughput can improve the efficiency of obtaining users' electronic signatures.
  • the electronic signature is identified by an OCR (Optical Character Recognition, Optical Character Recognition) model to obtain signature data
  • OCR Optical Character Recognition, Optical Character Recognition
  • the electronic signature can be a user signature in any electronic form, for example, an electronic seal with a user signature electronic images, etc.
  • the OCR model adopts the Bi-LSTM-CRF structure, including:
  • word/word vector layer for converting words and characters in the text contained in the electronic signature into word/word vectors
  • the Bi-LSTM layer is used to segment the word/word vector, encode the segmented word/word vector, and obtain the encoded representation of the word/word vector, and use the encoded representation to classify the segmented word/word vector.
  • the word/word vector is marked to obtain a key value and a result value;
  • the CRF layer is used to concatenate key and result values of the same type into signature data.
  • the word/word vector layer uses the trained word vector as an initialization parameter to convert the words and characters in the text contained in the electronic signature into word/word vectors, and the trained word vectors are pre-trained word vectors. Given a set of standard transformation rules.
  • the Bi-LSTM layer can segment the word/word vector to improve the efficiency of generating signature data.
  • the Bi-LSTM layer can use java language to segment the word/word vector, and encode the segmented word/word vector, and the encoding representation includes Key-B, Value-B, Key-I, Value-I, Other-B, Other-I six types of annotation types. Among them, Key is the key value, Value is the result value, and Other is other values.
  • the CRF layer is used to splicing key values and result values of the same type, such as Key-B, Key-I or Value-B, Value-I. After all key values and result values are spliced together, the signature data can be obtained, wherein the signature data is computer data in the form of an IO data stream.
  • the equidistant data fusion of the texture trajectory data, the pressure quantization data and the signature data to obtain the user's fingerprint signature includes:
  • the first split data, the second split data and the third split data are interspersed and combined to obtain the fingerprint signature of the user.
  • equal-spaced splitting refers to splitting a piece of data into multiple pieces of data according to a preset length.
  • the data & contains data: 123456.
  • the preset length is "2”
  • the data & is split into 12, 34 and 56.
  • the first preset length, the second preset length, and the third preset length may be the same or different.
  • the first split data, the second split data and the third split data are interspersed and combined in a preset order, for example, the first split data are ab, cd and ef, and the second split data are gh, ij and kl, and the third split data is mn, op and qr; when the preset sequence is "first split data - second split data - third split data", the first split data will be The split data, the second split data, and the third split data are interleaved and combined according to a preset sequence as: ab+gh+mn+cd+ij+op+ef+kl+qr.
  • the texture trajectory data, the pressure quantification data and the signature data are equidistantly fused to generate the user's fingerprint signature, and the user's identity can be authenticated through the user's fingerprint texture trajectory data, pressure quantification data and signature data. Improve the security of user authentication with user signatures.
  • the fingerprint signature generation method proposed in this application can improve the security of the electronic signature.
  • FIG. 2 it is a schematic diagram of a module of the fingerprint signature generating device of the present application.
  • the fingerprint signature generating apparatus 100 described in this application can be installed in an electronic device.
  • the fingerprint signature generating device may include a region extraction module 101 , a trajectory analysis module 102 , a pressure analysis module 103 , a signature recognition module 104 and a data fusion module 105 .
  • the modules described in this application may also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of an electronic device and can perform fixed functions, and are stored in the memory of the electronic device.
  • each module/unit is as follows:
  • the area extraction module 101 is used for acquiring the fingerprint image of the user, and extracting the fingerprint area on the fingerprint image to obtain the fingerprint area;
  • the trajectory analysis module 102 is configured to perform texture trajectory analysis on the fingerprint region to obtain texture trajectory data
  • the pressure analysis module 103 is configured to acquire the user's fingerprint pressing data, and perform pressure data analysis on the fingerprint pressing data to obtain pressure quantification data;
  • the signature recognition module 104 is used to obtain the user's electronic signature, perform signature recognition on the electronic signature, and obtain signature data;
  • the data fusion module 105 is configured to perform equidistant data fusion of the texture trajectory data, the pressure quantification data and the signature data to obtain the user's fingerprint signature.
  • a fingerprint signature generation method including the following operation steps can be implemented:
  • step 1 the region extraction module 101 acquires the fingerprint image of the user, and extracts the fingerprint region from the fingerprint image to obtain the fingerprint region.
  • the fingerprint image is an image including the user's fingerprint, for example, an image including an electronic photo of the user's fingerprint or a written text with the user's fingerprint.
  • the region extraction module 101 described in this embodiment of the present application may take a picture by using a mobile phone or any device with a camera function to obtain a fingerprint image of the user.
  • the region extraction module 101 described in this embodiment of the present application uses a convolutional neural network with a feature extraction function to extract the fingerprint region from the fingerprint image. , to reduce the size of the fingerprint image and improve the efficiency of acquiring fingerprint information from the fingerprint image, wherein the fingerprint area is an image area in the fingerprint image that contains fingerprint information.
  • the region extraction module 101 extracts the fingerprint region from the fingerprint image through the following operations to obtain the fingerprint region:
  • the fingerprint restoration image is segmented according to the target category probability to obtain a fingerprint area.
  • the segmentation process includes classifying the pixels in the fingerprint restoration image, the preset target category includes a plurality of preset categories, and the fingerprint restoration image is classified according to the preset target category probability.
  • the segmentation process is performed to obtain a fingerprint area, that is, it is determined that the preset category with the highest target category probability of the target pixel point in the fingerprint restoration image is the pixel category of the target pixel point.
  • the preset target category includes category A, category B and category C
  • the probability that the target pixel in the fingerprint restoration image is category A in the preset target category is 20%
  • the target pixel in the fingerprint restoration image is the preset target category
  • the probability of category B in the fingerprint restoration image is 70%
  • the probability that the target pixel in the fingerprint restoration image is the category C in the preset target category is 40%
  • the target pixel in the fingerprint restoration image is determined to be category B. All pixel points have completed the segmentation operation, and it is determined that the area where the pixel points in the restored fingerprint image are classified as the pixels of the fingerprint category is the fingerprint area.
  • the global feature map is upsampled by a first threshold multiple to obtain an intermediate feature map, and then the intermediate feature map is upsampled by a second threshold multiple to obtain a fingerprint restoration image, avoiding direct upsampling of the global feature map
  • the upsampling multiplier is too large to restore the fingerprint image, the image features in the restored fingerprint image are lost, and the integrity of the feature information in the restored fingerprint image is improved.
  • Step 2 The trajectory analysis module 102 performs texture trajectory analysis on the fingerprint region to obtain texture trajectory data.
  • the fingerprint signature generation device 100 is further configured to:
  • Grayscale pixel conversion and contrast stretching processing are performed on the fingerprint region.
  • the grayscale pixel conversion is to input all the pixels in the fingerprint region into a grayscale value conversion formula to perform grayscale value conversion to generate the grayscale image.
  • the gray value conversion formula is:
  • R, G, and B are the three components of the pixels in the fingerprint area
  • Gary is the grayscale image obtained by converting the grayscale pixels in the fingerprint area.
  • the contrast stretching process includes:
  • the grayscale probability density of each pixel is stretched and transformed to obtain the fingerprint region after the ratio stretching process.
  • the trajectory analysis module 102 can use the pre-compiled gray density function in MATLAB to count the gray probability density of each pixel in the fingerprint region after gray pixel conversion.
  • the trajectory analysis module 102 uses the following stretching transformation function to perform contrast stretching processing on the fingerprint region:
  • a is the preset linear slope
  • D a is the gray value of the fingerprint area before the contrast stretching
  • D b is the gray value of the fingerprint area after the contrast stretching
  • b is the intercept of D b on the Y axis .
  • the analysis module 102 performs grayscale pixel conversion and contrast stretching processing on the fingerprint region.
  • the trajectory analysis module 102 before performing texture trajectory analysis on the fingerprint area, the trajectory analysis module 102 first performs grayscale pixel conversion and contrast stretching on the fingerprint area, which can highlight the texture trajectory characteristics of the fingerprint in the fingerprint area, which is beneficial to improve The accuracy of the texture trajectory data is obtained by analyzing the texture trajectory of the fingerprint area.
  • the trajectory analysis module 102 uses the following operations to perform texture trajectory analysis on the fingerprint region to obtain texture trajectory data:
  • the gray frequency field, the sum of the tangential pixels and the sum of the normal pixels are integrated to obtain texture track data.
  • the trajectory analysis module 102 in this embodiment of the present application uses the following calculation formula to calculate the gray frequency field f of the fingerprint region:
  • V(x) is the total amount of vertical change of gray level of any two pixels on the fingerprint area
  • x 1 and x 2 are the horizontal coordinate values of any two different pixels on the fingerprint area respectively
  • h( x) represents the grayscale function in the vertical direction of the fingerprint area
  • a m is the average amplitude of the fingerprint waveform between any two different pixels on the fingerprint area.
  • Step 3 The pressure analysis module 103 acquires the user's fingerprint pressing data, performs pressure data analysis on the fingerprint pressing data, and obtains pressure quantification data.
  • the pressure analysis module 103 may use any device with a pressure sensor function to collect and obtain the user's fingerprint pressing data, wherein the fingerprint pressing data refers to the pressure generated when the user presses the device with the pressure sensor function.
  • pressure data including but not limited to the magnitude of pressure, the trend of pressure changes and/or the direction of pressure application, etc.
  • the pressure analysis module 103 performs pressure data analysis on the fingerprint pressing data through the following operations to obtain pressure quantification data:
  • Z is the instantaneous pressure value of pixel point (x, y); T(x, y) is the pressure gradient field of pixel point (x, y); G x (x, y) is the instantaneous pressure value Z at point (x, y) ,y) partial derivative with respect to x G y (x, y) is the partial derivative of instantaneous pressure value Z at point (x, y) to y ⁇ (x,y) is the application direction of the instantaneous pressure value Z;
  • are determined as pressure quantification data.
  • the pressure analysis module 103 uses the following calculation direction formula to calculate the application direction ⁇ (x, y) of the pressure:
  • V x (x, y) is the pressure applied in the direction of the horizontal axis
  • V y (x, y) is the pressure applied in the direction of the vertical axis
  • ⁇ (x, y) is the field function of the pressure direction
  • w is the initial direction Parameters
  • G x (x, y) is the partial derivative of the instantaneous pressure function Z at the point (x, y) to x
  • G y (x, y) is the partial derivative of instantaneous pressure function Z at point (x, y) to y
  • i is the preset horizontal axis error of point (x, y)
  • j is the preset vertical axis error of point (x, y).
  • Step 4 The signature recognition module 104 acquires the user's electronic signature, performs signature recognition on the electronic signature, and obtains signature data.
  • the signature identification module 104 can obtain the user's electronic signature from the blockchain for storing the user's electronic signature by using a python statement with a data capture function.
  • Using blockchain to keep data confidential can improve the security of electronic signatures, and at the same time, using blockchain's high data throughput can improve the efficiency of obtaining users' electronic signatures.
  • the signature recognition module 104 uses an OCR (Optical Character Recognition, Optical Character Recognition) model to recognize the electronic signature to obtain signature data
  • OCR Optical Character Recognition, Optical Character Recognition
  • the electronic signature can be a user signature in any electronic form, for example, an electronic signature. Stamps, electronic images with user signatures, etc.
  • the OCR model adopts the Bi-LSTM-CRF structure, including:
  • word/word vector layer for converting words and characters in the text contained in the electronic signature into word/word vectors
  • the Bi-LSTM layer is used to segment the word/word vector, encode the segmented word/word vector, and obtain the encoded representation of the word/word vector, and use the encoded representation to classify the segmented word/word vector.
  • the word/word vector is marked to obtain a key value and a result value;
  • the CRF layer is used to concatenate key and result values of the same type into signature data.
  • the word/word vector layer uses the trained word vector as an initialization parameter to convert the words and characters in the text contained in the electronic signature into word/word vectors, and the trained word vectors are pre-trained word vectors. Given a set of standard transformation rules.
  • the Bi-LSTM layer can segment the word/word vector to improve the efficiency of generating signature data.
  • the Bi-LSTM layer can use java language to segment the word/word vector, and encode the segmented word/word vector, and the encoding representation includes Key-B, Value-B, Key-I, Value-I, Other-B, Other-I six types of annotation types. Among them, Key is the key value, Value is the result value, and Other is other values.
  • the CRF layer is used to splicing key values and result values of the same type, such as Key-B, Key-I or Value-B, Value-I. After all key values and result values are spliced together, the signature data can be obtained, wherein the signature data is computer data in the form of an IO data stream.
  • Step 5 The data fusion module 105 performs equidistant data fusion on the texture trajectory data, the pressure quantization data and the signature data to obtain the user's fingerprint signature.
  • the data fusion module 105 performs equidistant data fusion on the texture trajectory data, the pressure quantization data, and the signature data through the following operations to obtain the user's fingerprint signature:
  • the first split data, the second split data and the third split data are interspersed and combined to obtain the fingerprint signature of the user.
  • equal-spaced splitting refers to splitting a piece of data into multiple pieces of data according to a preset length.
  • the data & contains data: 123456.
  • the preset length is "2”
  • the data & is split into 12, 34 and 56.
  • the first preset length, the second preset length, and the third preset length may be the same or different.
  • the data fusion module 105 interleaves and combines the first split data, the second split data and the third split data in a preset order, for example, the first split data is ab, cd and ef , the second split data is gh, ij and kl, and the third split data is mn, op and qr; when the preset sequence is "first split data - second split data - third split data", Then, the first split data, the second split data, and the third split data are interspersed and combined according to the preset order as: ab+gh+mn+cd+ij+op+ef+kl+qr.
  • the data fusion module 105 performs equidistant data fusion on the texture trajectory data, the pressure quantification data and the signature data to generate the user's fingerprint signature. Authenticate the user's identity, and improve the security of the user's identity authentication by using the user's signature.
  • the fingerprint signature generation device proposed in this application can improve the security of electronic signatures.
  • FIG. 3 it is a schematic structural diagram of an electronic device implementing the fingerprint signature generation method of the present application.
  • the electronic device 1 may include a processor 10, a memory 11 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a fingerprint signature generation program 12.
  • the memory 11 includes at least one type of readable storage medium, and the readable storage medium may be volatile or non-volatile.
  • the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (eg, SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like.
  • the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1 . In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) equipped on the electronic device 1.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 can not only be used to store application software installed in the electronic device 1 and various types of data, such as the code of the fingerprint signature generation program 12, etc., but also can be used to temporarily store data that has been output or will be output.
  • the processor 10 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits.
  • Central processing unit Central Processing unit, CPU
  • microprocessor digital processing chip
  • graphics processor and combination of various control chips, etc.
  • the processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing the program or module stored in the memory 11 (for example, executing fingerprints). signature generation program, etc.), and call data stored in the memory 11 to execute various functions of the electronic device 1 and process data.
  • the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (extended industry standard architecture, EISA for short) bus or the like.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the bus is configured to implement connection communication between the memory 11 and at least one processor 10 and the like.
  • FIG. 3 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 3 does not constitute a limitation on the electronic device 1, and may include fewer or more components than those shown in the figure. components, or a combination of certain components, or a different arrangement of components.
  • the electronic device 1 may also include a power supply (such as a battery) for powering the various components, preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that the power management
  • the device implements functions such as charge management, discharge management, and power consumption management.
  • the power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
  • the electronic device 1 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • a network interface optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 1 Establish a communication connection with other electronic devices.
  • the electronic device 1 may further include a user interface, and the user interface may be a display (Display), an input unit (eg, a keyboard (Keyboard)), optionally, the user interface may also be a standard wired interface or a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
  • the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 1 and for displaying a visualized user interface.
  • the fingerprint signature generation program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple computer programs, and when running in the processor 10, it can realize:
  • the texture track data, the pressure quantization data and the signature data are equidistantly fused to obtain the user's fingerprint signature.
  • the modules/units integrated in the electronic device 1 may be stored in a computer-readable storage medium.
  • the computer-readable storage medium may be volatile or non-volatile.
  • the computer-readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read Only Memory) -Only Memory).
  • the computer usable storage medium may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, and the like; using the created data, etc.
  • modules described as separate components may or may not be physically separated, and components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.
  • the blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Collating Specific Patterns (AREA)

Abstract

本申请涉及数据处理技术,揭露了一种指纹签名生成方法,包括:获取用户的指纹图像,对指纹图像进行指纹区域提取,得到指纹区域;对指纹区域进行纹理轨迹分析,得到纹理轨迹数据;获取用户的指纹按压数据,对指纹按压数据进行压力数据分析,得到压力量化数据;获取用户的电子签名,对电子签名进行签名识别,得到签名数据;将纹理轨迹数据、压力量化数据和签名数据进行等间距数据融合,得到用户的指纹签名。本申请还提出了指纹签名生成装置、设备及计算机可读存储介质。此外,本申请还涉及区块链技术,电子签名可存储于区块链节点中。本申请可以提高电子签名的安全性。

Description

指纹签名生成方法、装置、电子设备及计算机存储介质
本申请要求于2021年01月19日提交中国专利局、申请号为202110068587.X,发明名称为“指纹签名生成方法、装置、电子设备及计算机存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及数据处理技术领域,尤其涉及一种指纹签名生成方法、装置、电子设备及计算机可读存储介质。
背景技术
在日常生活中,很多人都会遇到需要签名的情况,例如,在合同文件中进行手写签名,在电子邮件中进行电子签名,通过签名来对各项事务进行授权等。
发明人意识到,随着网络的发展,电子签名已经逐渐取代了手写签名,成为主要的签名方式。但是,电子签名时,因签名时所使用的设备性能的差异,而无法反映签名人的笔力运用和细微笔画的书写习惯,因此可能会导致无法鉴定出签名者的身份,从而使得电子签名的安全性不高,电子签名具备的法律效用得不到保证。
发明内容
本申请提供的一种指纹签名生成方法,包括:
获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
本申请还提供一种指纹签名生成装置,所述装置包括:
区域提取模块,用于获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
轨迹分析模块,用于对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
压力分析模块,用于获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
签名识别模块,用于获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
数据融合模块,用于将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
本申请还提供一种电子设备,所述电子设备包括:
至少一个处理器;以及,
与所述至少一个处理器通信连接的存储器;其中,
所述存储器存储有可被所述至少一个处理器执行的计算机程序,所述计算机程序被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的指纹签名生成方法:
获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
本申请还提供一种计算机可读存储介质,包括存储数据区和存储程序区,存储数据区存储创建的数据,存储程序区存储有计算机程序;其中,所述计算机程序被处理器执行时实现如下所述的指纹签名生成方法:
获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
附图说明
图1为本申请一实施例提供的指纹签名生成方法的流程示意图;
图2为本申请一实施例提供的指纹签名生成装置的模块示意图;
图3为本申请一实施例提供的实现指纹签名生成方法的电子设备的内部结构示意图;
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供一种指纹签名生成方法。所述指纹签名生成方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述指纹签名生成方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
参照图1所示,为本申请一实施例提供的指纹签名生成方法的流程示意图。在本实施例中,所述指纹签名生成方法包括:
S1、获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域。
本申请实施例中,所述指纹图像是包含了用户的指纹的图像,例如,含有用户指纹电子照片或带有用户指纹的书面文本的图像等。
详细地,本申请实施例可通过手机或任何具有摄像功能的设备拍照以获取用户的指纹图像。
实际应用中,由于获取到的用户的指纹图像中可能包含着大量的无用信息,例如,在很大的一张指纹图像中只有十分之一的区域含有用户的指纹信息,若直接对获取到的指纹图像进行分析,会占用大量计算资源,降低提取指纹信息的效率,因此,本申请实施例利用具有特征提取功能的卷积神经网络来实现对指纹图像进行指纹区域提取,以缩减指纹图形的尺寸,提高从指纹图像中获取指纹信息的效率,其中,所述指纹区域是所述指纹图像中含有指纹信息的图像区域。
详细地,所述对所述指纹图像进行指纹区域提取,包括:
对所述指纹图像进行下采样,得到全局特征图;
将所述全局特征图进行第一阈值倍数的上采样,得到中间特征图;
将所述中间特征图进行第二阈值倍数的上采样,得到指纹复原图像;
利用第一激活函数计算所述指纹复原图像中各像素点属于预设的目标类别的目标类别概率;
根据所述目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域。
具体地,所述分割处理包括对指纹复原图像中像素点进行分类,所述预设的目标类别中包括多个预设类别,所述根据所述预设的目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域,即确定指纹复原图像中目标像素点的目标类别概率最大的预设类别为该目标像素点的像素类别。
例如,预设目标类别中包括类别A、类别B与类别C,指纹复原图像中目标像素点为预设目标类别中类别A的概率为20%,指纹复原图像中目标像素点为预设目标类别中类别B的概率为70%,指纹复原图像中目标像素点为预设目标类别中类别C的概率为40%,则确定指纹复原图像中目标像素点为类别B,当所述指纹复原图像中所有像素点均完成所述分割操作,确定指纹复原图像中像素点分类为指纹类别的像素所在的区域为指纹区域。
本申请实施例中将全局特征图进行第一阈值倍数的上采样,得到中间特征图,再将中间特征图进行第二阈值倍数的上采样,得到指纹复原图像,避免直接将全局特征图上采样至指纹复原图像时上采样倍数过大导致指纹复原图像中图像特征的丢失,提高了指纹复原图像中特征信息的完整性。
S2、对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据。
本申请实施例中,所述对所述指纹区域进行纹理轨迹分析之前,所述方法还可以包括:
对所述指纹区域进行灰度像素转化及对比度拉伸处理。
详细地,所述灰度像素转化是将所述指纹区域中的所有像素点输入至一个灰度值转换公式中进行灰度值转换,生成所述灰度图像。
其中,所述灰度值转换公式为:
Gary=0.30*R+0.59*G+0.11*B
其中R,G,B为所述指纹区域中的像素的三分量,Gary为指纹区域进行灰度像素转化后得到的灰度图像。
进一步地,所述对比度拉伸处理,包括:
遍历并统计灰度像素转化后的指纹区域中每一个像素点的灰度概率密度;
利用预设灰度变换函数将每一个像素点的灰度概率密度进行拉伸变换处理,得到比度拉伸处理后的指纹区域。
具体地,本申请实施例可利用MATLAB中预先编译完成的灰度密度函数统计灰度像素转化后的指纹区域中每一个像素点的灰度概率密度。
详细地,本申请实施例可以利用如下拉伸变换函数对所述指纹区域进行对比度拉伸处理:
D b=f(D a)=a*D a+b
其中,a为预设线性斜率,D a为所述对比度拉伸之前指纹区域的灰度值,D b为对比度拉伸之后指纹区域的灰度值,b为D b在Y轴上的截距。
由于通过对获取的指纹图像直接进行指纹区域提取得到的指纹区域存在着图像较暗、图像不清晰等情况,不利于后续对指纹区域中包含的数据进行分析,因此,本申请实施例对指纹区域进行灰度像素转化及对比度拉伸处理,本申请实施例中,对指纹区域进行纹理轨迹分析之前,先对指纹区域进行灰度像素转化和对比度拉伸,可凸显出指纹区域中指纹的纹理轨迹特征,有利于提高对指纹区域进行纹理轨迹分析得到纹理轨迹数据的精确度。
详细地,所述对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据,包括:
计算所述指纹区域的灰度频率场;
计算所述指纹区域中各个像素点的切向像素之和与法向像素之和;
整合所述灰度频率场、所述切向像素之和及法向像素之和,得到纹理轨迹数据。
具体地,本申请实施例利用如下计算公式计算所述指纹区域的灰度频率场f:
Figure PCTCN2021090722-appb-000001
Figure PCTCN2021090722-appb-000002
其中,V(x)为所述指纹区域上任意两个像素点的灰度垂直变化总量;x 1和x 2分别为指纹区域上任意两个不相同的像素点的横向坐标值;h(x)表示所述指纹区域的垂直方向上的灰度函数;a m为所述指纹区域上任意两个不相同的像素点之间的指纹波形的平均振幅。
S3、获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据。
本申请实施例中,可以利用任何具有的压力传感器功能设备采集获得用户的指纹按压数据,其中,所述指纹按压数据时指用户在按压具有的压力传感器功能设备时所产生的压力数据,包括但不限于压力的大小、压力的变化趋势和/或压力的施加方向等。
所述对所述指纹按压数据进行压力数据分析,得到压力量化数据,包括:
利用如下计算公式计算所述指纹按压数据的瞬时压力值Z和压力梯度场T(x,y):
Z=|T(x,y)|
Figure PCTCN2021090722-appb-000003
其中,Z为像素点(x,y)的瞬时压力值;T(x,y)像素点(x,y)的压力梯度场;G x(x,y)为瞬时压力值Z在点(x,y)对x的偏导数
Figure PCTCN2021090722-appb-000004
G y(x,y)为瞬时压力值Z在点(x,y)对y的偏导数
Figure PCTCN2021090722-appb-000005
θ(x,y)为瞬时压力值Z的施加方向;
确定所述瞬时压力值Z和压力梯度场|T(x,y)|为压力量化数据。
详细地,利用如下计算方向公式计算所述压力的施加方向θ(x,y):
Figure PCTCN2021090722-appb-000006
Figure PCTCN2021090722-appb-000007
Figure PCTCN2021090722-appb-000008
其中,V x(x,y)为横轴方向上施加的压力;V y(x,y)为纵轴方向上施加的压力;θ(x,y)为压力方向场函数;w为初始方向参数;G x(x,y)为瞬时压力函数Z在点(x,y)对x的偏导数
Figure PCTCN2021090722-appb-000009
G y(x,y)为瞬时压力函数Z在点(x,y)对y的偏导数
Figure PCTCN2021090722-appb-000010
i为点(x,y)预设的横轴误差,j为点(x,y)预设的纵轴误差。
S4、获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据。
本申请实施例中,可利用具有数据抓取功能的python语句从用于存储用户的电子签名的区块链中获取用户的电子签名。利用区块链对数据的保密性,可提高电子签名的安全性,同时,利用区块链对数据的高吞吐性,可提高获取用户的电子签名的效率。
本申请实施例中,利用OCR(OpticalCharacterRecognition,光学字符识别)模型对所述电子签名进行识别,得到签名数据,所述电子签名可以为任何电子形式的用户签名,例如,电子印章,带有用户签名的电子图像等。
详细地,所述OCR模型采用Bi-LSTM-CRF结构,包括:
字/词向量层,用于将所述电子签名包含的文本中的单词和字符转化为字/词向量;
Bi-LSTM层,用于将所述字/词向量进行分割,对分割后的所述字/词向量进行编码,得到所述字/词向量的编码表征,利用所述编码表征对分割后的所述字/词向量进行标注,得到键值和结果值;
CRF层,用于将相同类型的键值和结果值拼接为签名数据。
其中,所述字/词向量层利用已经训练好的词向量作为初始化参数,将所述电子签名包含的文本中的单词和字符转化为字/词向量,所述已经训练好的词向量是预先给定一套标准转化规则。
由于所述电子签名中包含的文本可能较多,文本中的语句可能较长,如果只是进行字符转换,可能会出现文本粘滞的情况,不利于后续的文本纠错,因此本申请实施例利用所述Bi-LSTM层可将所述字/词向量进行分割,以提高生成签名数据的效率。
优选地,所述Bi-LSTM层可采用java语言将所述字/词向量进行分割,并对分割后的所述字/词向量进行编码,所述编码表征包含Key-B,Value-B,Key-I,Value-I,Other-B,Other-I六类标注类型。其中,Key为键值,Value为结果值,Other为其他值。
本申请实施例中利用CRF层将相同类型的键值和结果值进行拼接,如Key-B,Key-I或Value-B,Value-I。当所有键值和结果值拼接完成后,即可得到所述签名数据,其中,所述签名数据为IO数据流形式的计算机数据。
S5、将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
本申请实施例中,所述将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名,包括:
将所述纹理轨迹数据按照第一预设长度进行等间距拆分,得到第一拆分数据;
将所述压力量化数据按照第二预设长度进行等间距拆分,得到第二拆分数据;
将所述签名数据按照第三预设长度进行等间距拆分,得到第三拆分数据;
将所述第一拆分数据、第二拆分数据和第三拆分数据按进行穿插组合,得到用户的指纹签名。
详细地,等间距拆分是指将一段数据按照预设长度拆分为多段数据,例如,数据&中包含数据:123456,当预设长度为“2”时,将数据&拆分成12、34和56。
本申请实施例中,所述第一预设长度、第二预设长度和第三预设长度可以相同,也可以不同。
具体地,将所述第一拆分数据、第二拆分数据和第三拆分数据按照预设顺序进行穿插组合,例如,第一拆分数据为ab、cd和ef,第二拆分数据为gh、ij和kl,第三拆分数据为mn、op和qr;当预设顺序为“第一拆分数据-第二拆分数据-第三拆分数据”,则将将第一拆分数据、第二拆分数据和第三拆分数据按照预设顺序进行穿插组合为:ab+gh+mn+cd+ij+op+ef+kl+qr。
本申请实施例中,将纹理轨迹数据、压力量化数据和签名数据进行等间距数据融合生成用户的指纹签名,可通过用户指纹的纹理轨迹数据、压力量化数据和签名数据共同对用户身份进行认证,提高利用用户签名对用户身份验证的安全性。
本申请实施例通过对指纹图像进行指纹区域提取,可避免对指纹图像中没有指纹信息的区域进行分析,进而提高从指纹图像中提取纹理轨迹数据的效率;对指纹按压数据进行压力数据分析,得到压力量化数据,对用户电子签名进行签名识别,得到签名数据,并将纹理轨迹数据、压力量化数据和签名数据等间距融合为指纹签名,使得融合后得到的指纹签名中包含更精确的运笔力度,细微笔画,从而使得指纹签名与预先存储于数据库内的模板的匹配率更高,从而提高了指纹签名的精确度和安全性。因此本申请提出的指纹签名生成方法,可以提高电子签名的安全性。
如图2所示,是本申请指纹签名生成装置的模块示意图。
本申请所述指纹签名生成装置100可以安装于电子设备中。根据实现的功能,所述指纹签名生成装置可以包括区域提取模块101、轨迹分析模块102、压力分析模块103、签名识别模块104和数据融合模块105。本申请所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述区域提取模块101,用于获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
所述轨迹分析模块102,用于对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
所述压力分析模块103,用于获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
所述签名识别模块104,用于获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
所述数据融合模块105,用于将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
详细地,所述指纹签名生成装置100中的各模块在由电子设备的处理器所执行时,可以实现包括下述操作步骤的指纹签名生成方法:
步骤一、所述区域提取模块101获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域。
本申请实施例中,所述指纹图像是包含了用户的指纹的图像,例如,含有用户指纹电子照片或带有用户指纹的书面文本的图像等。
详细地,本申请实施例所述区域提取模块101可通过手机或任何具有摄像功能的设备拍照以获取用户的指纹图像。
实际应用中,由于获取到的用户的指纹图像中可能包含着大量的无用信息,例如,在很大的一张指纹图像中只有十分之一的区域含有用户的指纹信息,若直接对获取到的指纹图像进行分析,会占用大量计算资源,降低提取指纹信息的效率,因此,本申请实施例所述区域提取模块101利用具有特征提取功能的卷积神经网络来实现对指纹图像进行指纹区域提取,以缩减指纹图形的尺寸,提高从指纹图像中获取指纹信息的效率,其中,所述指纹区域是所述指纹图像中含有指纹信息的图像区域。
详细地,所述区域提取模块101在通过下述操作对所述指纹图像进行指纹区域提取,得到指纹区域:
对所述指纹图像进行下采样,得到全局特征图;
将所述全局特征图进行第一阈值倍数的上采样,得到中间特征图;
将所述中间特征图进行第二阈值倍数的上采样,得到指纹复原图像;
利用第一激活函数计算所述指纹复原图像中各像素点属于预设的目标类别的目标类别概率;
根据所述目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域。
具体地,所述分割处理包括对指纹复原图像中像素点进行分类,所述预设的目标类别中包括多个预设类别,所述根据所述预设的目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域,即确定指纹复原图像中目标像素点的目标类别概率最大的预设类别为该目标像素点的像素类别。
例如,预设目标类别中包括类别A、类别B与类别C,指纹复原图像中目标像素点为预设目标类别中类别A的概率为20%,指纹复原图像中目标像素点为预设目标类别中类别B的概率为70%,指纹复原图像中目标像素点为预设目标类别中类别C的概率为40%,则确定指纹复原图像中目标像素点为类别B,当所述指纹复原图像中所有像素点均完成所述分割操作,确定指纹复原图像中像素点分类为指纹类别的像素所在的区域为指纹区域。
本申请实施例中将全局特征图进行第一阈值倍数的上采样,得到中间特征图,再将中间特征图进行第二阈值倍数的上采样,得到指纹复原图像,避免直接将全局特征图上采样至指纹复原图像时上采样倍数过大导致指纹复原图像中图像特征的丢失,提高了指纹复原图像中特征信息的完整性。
步骤二、所述轨迹分析模块102对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据。
本申请实施例中,所述指纹签名生成装置100还用于:
对所述指纹区域进行灰度像素转化及对比度拉伸处理。
详细地,所述灰度像素转化是将所述指纹区域中的所有像素点输入至一个灰度值转换公式中进行灰度值转换,生成所述灰度图像。
其中,所述灰度值转换公式为:
Gary=0.30*R+0.59*G+0.11*B
其中R,G,B为所述指纹区域中的像素的三分量,Gary为指纹区域进行灰度像素转化后得到的灰度图像。
进一步地,所述对比度拉伸处理,包括:
遍历并统计灰度像素转化后的指纹区域中每一个像素点的灰度概率密度;
利用预设灰度变换函数将每一个像素点的灰度概率密度进行拉伸变换处理,得到比度拉伸处理后的指纹区域。
具体地,所述轨迹分析模块102可利用MATLAB中预先编译完成的灰度密度函数统计灰度像素转化后的指纹区域中每一个像素点的灰度概率密度。
详细地,所述轨迹分析模块102利用如下拉伸变换函数对所述指纹区域进行对比度拉伸处理:
D b=f(D a)=a*D a+b
其中,a为预设线性斜率,D a为所述对比度拉伸之前指纹区域的灰度值,D b为对比度拉伸之后指纹区域的灰度值,b为D b在Y轴上的截距。
由于通过对获取的指纹图像直接进行指纹区域提取得到的指纹区域存在着图像较暗、图像不清晰等情况,不利于后续对指纹区域中包含的数据进行分析,因此,本申请实施例所述轨迹分析模块102对指纹区域进行灰度像素转化及对比度拉伸处理。本申请实施例中,对指纹区域进行纹理轨迹分析之前,所述轨迹分析模块102先对指纹区域进行灰度像素转化和对比度拉伸,可凸显出指纹区域中指纹的纹理轨迹特征,有利于提高对指纹区域进行纹理轨迹分析得到纹理轨迹数据的精确度。
详细地,所述轨迹分析模块102采用下述操作对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据:
计算所述指纹区域的灰度频率场;
计算所述指纹区域中各个像素点的切向像素之和与法向像素之和;
整合所述灰度频率场、所述切向像素之和及法向像素之和,得到纹理轨迹数据。
具体地,本申请实施例所述轨迹分析模块102利用如下计算公式计算所述指纹区域的灰度频率场f:
Figure PCTCN2021090722-appb-000011
Figure PCTCN2021090722-appb-000012
其中,V(x)为所述指纹区域上任意两个像素点的灰度垂直变化总量;x 1和x 2分别为指纹区域上任意两个不相同的像素点的横向坐标值;h(x)表示所述指纹区域的垂直方向上的灰度函数;a m为所述指纹区域上任意两个不相同的像素点之间的指纹波形的平均振幅。
步骤三、所述压力分析模块103获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据。
本申请实施例中,所述压力分析模块103可以利用任何具有的压力传感器功能设备采集获得用户的指纹按压数据,其中,所述指纹按压数据时指用户在按压具有的压力传感器功能设备时所产生的压力数据,包括但不限于压力的大小、压力的变化趋势和/或压力的施加方向等。
详细地,所述压力分析模块103通过下述操作对所述指纹按压数据进行压力数据分析,得到压力量化数据:
利用如下计算公式计算所述指纹按压数据的瞬时压力值Z和压力梯度场T(x,y):
Z=|T(x,y)|
Figure PCTCN2021090722-appb-000013
其中,Z为像素点(x,y)的瞬时压力值;T(x,y)像素点(x,y)的压力梯度场;G x(x,y)为瞬时压力值Z在点(x,y)对x的偏导数
Figure PCTCN2021090722-appb-000014
G y(x,y)为瞬时压力值Z在点(x,y)对y的偏导数
Figure PCTCN2021090722-appb-000015
θ(x,y)为瞬时压力值Z的施加方向;
确定所述瞬时压力值Z和压力梯度场|T(x,y)|为压力量化数据。
详细地,所述压力分析模块103利用如下计算方向公式计算所述压力的施加方向θ(x,y):
Figure PCTCN2021090722-appb-000016
Figure PCTCN2021090722-appb-000017
Figure PCTCN2021090722-appb-000018
其中,V x(x,y)为横轴方向上施加的压力;V y(x,y)为纵轴方向上施加的压力;θ(x,y)为压力方向场函数;w为初始方向参数;G x(x,y)为瞬时压力函数Z在点(x,y)对x的偏导数
Figure PCTCN2021090722-appb-000019
G y(x,y)为瞬时压力函数Z在点(x,y)对y的偏导数
Figure PCTCN2021090722-appb-000020
i为点(x,y)预设的横轴误差,j为点(x,y)预设的纵轴误差。
步骤四、所述签名识别模块104获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据。
本申请实施例中,所述签名识别模块104可利用具有数据抓取功能的python语句从用于存储用户的电子签名的区块链中获取用户的电子签名。利用区块链对数据的保密性,可提高电子签名的安全性,同时,利用区块链对数据的高吞吐性,可提高获取用户的电子签名的效率。
本申请实施例中,所述签名识别模块104利用OCR(OpticalCharacterRecognition,光学字符识别)模型对所述电子签名进行识别,得到签名数据,所述电子签名可以为任何电子形式的用户签名,例如,电子印章,带有用户签名的电子图像等。
详细地,所述OCR模型采用Bi-LSTM-CRF结构,包括:
字/词向量层,用于将所述电子签名包含的文本中的单词和字符转化为字/词向量;
Bi-LSTM层,用于将所述字/词向量进行分割,对分割后的所述字/词向量进行编码,得到所述字/词向量的编码表征,利用所述编码表征对分割后的所述字/词向量进行标注,得到键值和结果值;
CRF层,用于将相同类型的键值和结果值拼接为签名数据。
其中,所述字/词向量层利用已经训练好的词向量作为初始化参数,将所述电子签名包含的文本中的单词和字符转化为字/词向量,所述已经训练好的词向量是预先给定一套标准转化规则。
由于所述电子签名中包含的文本可能较多,文本中的语句可能较长,如果只是进行字符转换,可能会出现文本粘滞的情况,不利于后续的文本纠错,因此本申请实施例利用所述Bi-LSTM层可将所述字/词向量进行分割,以提高生成签名数据的效率。
优选地,所述Bi-LSTM层可采用java语言将所述字/词向量进行分割,并对分割后的所述字/词向量进行编码,所述编码表征包含Key-B,Value-B,Key-I,Value-I,Other-B,Other-I六类标注类型。其中,Key为键值,Value为结果值,Other为其他值。
本申请实施例中利用CRF层将相同类型的键值和结果值进行拼接,如Key-B,Key-I或Value-B,Value-I。当所有键值和结果值拼接完成后,即可得到所述签名数据,其中,所述签名数据为IO数据流形式的计算机数据。
步骤五、所述数据融合模块105将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
本申请实施例中,所述数据融合模块105通过下述操作将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名:
将所述纹理轨迹数据按照第一预设长度进行等间距拆分,得到第一拆分数据;
将所述压力量化数据按照第二预设长度进行等间距拆分,得到第二拆分数据;
将所述签名数据按照第三预设长度进行等间距拆分,得到第三拆分数据;
将所述第一拆分数据、第二拆分数据和第三拆分数据按进行穿插组合,得到用户的指纹签名。
详细地,等间距拆分是指将一段数据按照预设长度拆分为多段数据,例如,数据&中包含数据:123456,当预设长度为“2”时,将数据&拆分成12、34和56。
本申请实施例中,所述第一预设长度、第二预设长度和第三预设长度可以相同,也可以不同。
具体地,所述数据融合模块105将所述第一拆分数据、第二拆分数据和第三拆分数据按照预设顺序进行穿插组合,例如,第一拆分数据为ab、cd和ef,第二拆分数据为gh、ij和kl,第三拆分数据为mn、op和qr;当预设顺序为“第一拆分数据-第二拆分数据-第三拆分数据”,则将将第一拆分数据、第二拆分数据和第三拆分数据按照预设顺序进行穿插组合为:ab+gh+mn+cd+ij+op+ef+kl+qr。
本申请实施例中,所述数据融合模块105将纹理轨迹数据、压力量化数据和签名数据进行等间距数据融合生成用户的指纹签名,可通过用户指纹的纹理轨迹数据、压力量化数据和签名数据共同对用户身份进行认证,提高利用用户签名对用户身份验证的安全性。
本申请实施例通过对指纹图像进行指纹区域提取,可避免对指纹图像中没有指纹信息的区域进行分析,进而提高从指纹图像中提取纹理轨迹数据的效率;对指纹按压数据进行压力数据分析,得到压力量化数据,对用户电子签名进行签名识别,得到签名数据,并将纹理轨迹数据、压力量化数据和签名数据等间距融合为指纹签名,使得融合后得到的指纹签名中包含更精确的运笔力度,细微笔画,从而使得指纹签名与预先存储于数据库内的模板的匹配率更高,从而提高了指纹签名的精确度和安全性。因此本申请提出的指纹签名生成装置,可以提高电子签名的安全性。
如图3所示,是本申请实现指纹签名生成方法的电子设备的结构示意图。
所述电子设备1可以包括处理器10、存储器11和总线,还可以包括存储在所述存储器11中并可在所述处理器10上运行的计算机程序,如指纹签名生成程序12。
其中,所述存储器11至少包括一种类型的可读存储介质,所述可读存储介质可以是易失性的,也可以是非易失性的。具体的,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器11在一些实施例中可以是电子设备1的内部存储单元,例如该电子设备1的移动硬盘。所述存储器11在另一些实施例中也可以是电子设备1的外部存储设备,例如电子设备1上配备的插接式移动硬盘、智能存储卡(SmartMediaCard,SMC)、安全数字(SecureDigital,SD)卡、闪存卡(FlashCard)等。进一步地,所述存储器11还可以既包括电子设备1的内部存储单元也包括外部存储设备。所述存储器11不仅可以用于存储安装于电子设备1的应用软件及各类数据,例如指纹签名生成程序12的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器10在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(CentralProcessingunit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器10是所述电子设备的控制核心(ControlUnit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器11内的程序或者模块(例如执行指纹签名生成程序等),以及调用存储在所述存储器11内的数据,以执行电子设备1的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheralcomponentinterconnect,简称PCI)总线或扩展工业标准结构(extendedindustrystandardarchitecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器11以及至少一个处理器10等之间的连接通信。
图3仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图3示出的结构 并不构成对所述电子设备1的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备1还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器10逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备1还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备1还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备1与其他电子设备之间建立通信连接。
可选地,该电子设备1还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(OrganicLight-EmittingDiode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备1中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备1中的所述存储器11存储的指纹签名生成程序12是多个计算机程序的组合,在所述处理器10中运行时,可以实现:
获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
进一步地,所述电子设备1集成的模块/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存储介质中。所述计算机可读存储介质可以是易失性的,也可以是非易失性的。具体的,所述计算机可读存储介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-OnlyMemory)。
进一步地,所述计算机可用存储介质可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序等;存储数据区可存储根据区块链节点的使用所创建的数据等。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,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,所述模块的划分,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。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块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模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背 离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图表记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种指纹签名生成方法,其中,所述方法包括:
    获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
    对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
    获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
    获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
    将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
  2. 如权利要求1所述的指纹签名生成方法,其中,所述对所述指纹图像进行指纹区域提取,包括:
    对所述指纹图像进行下采样,得到全局特征图;
    将所述全局特征图进行第一阈值倍数的上采样,得到中间特征图;
    将所述中间特征图进行第二阈值倍数的上采样,得到指纹复原图像;
    利用第一激活函数计算所述指纹复原图像中各像素点属于预设的目标类别的目标类别概率;
    根据所述目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域。
  3. 如权利要求1所述的指纹签名生成方法,其中,所述对所述指纹区域进行纹理轨迹分析之前,所述方法还包括:
    依次对所述指纹区域进行灰度像素转化及对比度拉伸处理。
  4. 如权利要求3所述的指纹签名生成方法,其中,所述对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据,包括:
    计算所述指纹区域的灰度频率场;
    计算所述指纹区域中各个像素点的切向像素之和与法向像素之和;
    整合所述灰度频率场、所述切向像素之和及法向像素之和,得到纹理轨迹数据。
  5. 如权利要求4所述的指纹签名生成方法,其中,所述计算所述指纹区域的灰度频率场,包括:
    利用如下计算公式计算所述指纹区域的灰度频率场f:
    Figure PCTCN2021090722-appb-100001
    Figure PCTCN2021090722-appb-100002
    其中,V(x)为所述指纹区域上任意两个像素点的灰度垂直变化总量;x 1和x 2分别为指纹区域上任意两个不相同的像素点的横向坐标值;h(x)表示所述指纹区域的垂直方向上的灰度函数;a m为所述指纹区域上任意两个不相同的像素点之间的指纹波形的平均振幅。
  6. 如权利要求1至5中任意一项所述的指纹签名生成方法,其中,所述将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名,包括:
    将所述纹理轨迹数据按照第一预设长度进行等间距拆分,得到第一拆分数据;
    将所述压力量化数据按照第二预设长度进行等间距拆分,得到第二拆分数据;
    将所述签名数据按照第三预设长度进行等间距拆分,得到第三拆分数据;
    将所述第一拆分数据、第二拆分数据和第三拆分数据按进行穿插组合,得到用户的指纹签名。
  7. 如权利要求1至5中任意一项所述的指纹签名生成方法,其中,所述对所述指纹按 压数据进行压力数据分析,得到压力量化数据,包括:
    利用如下计算公式计算所述指纹按压数据的瞬时压力值Z和压力梯度场T(x,y):
    Z=|T(x,y)|
    Figure PCTCN2021090722-appb-100003
    其中,Z为像素点(x,y)的瞬时压力值;T(x,y)像素点(x,y)的压力梯度场;G x(x,y)为瞬时压力值Z在点(x,y)对x的偏导数
    Figure PCTCN2021090722-appb-100004
    G y(x,y)为瞬时压力值Z在点(x,y)对y的偏导数
    Figure PCTCN2021090722-appb-100005
    θ(x,y)为瞬时压力值Z的施加方向;
    确定所述瞬时压力值Z和压力梯度场|T(x,y)|为压力量化数据。
  8. 一种指纹签名生成装置,其中,所述装置包括:
    区域提取模块,用于获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
    轨迹分析模块,用于对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
    压力分析模块,用于获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
    签名识别模块,用于获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
    数据融合模块,用于将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
  9. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的计算机程序,所述计算机程序被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下所述的指纹签名生成方法:
    获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
    对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
    获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
    获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
    将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
  10. 如权利要求9所述的电子设备,其中,所述对所述指纹图像进行指纹区域提取,包括:
    对所述指纹图像进行下采样,得到全局特征图;
    将所述全局特征图进行第一阈值倍数的上采样,得到中间特征图;
    将所述中间特征图进行第二阈值倍数的上采样,得到指纹复原图像;
    利用第一激活函数计算所述指纹复原图像中各像素点属于预设的目标类别的目标类别概率;
    根据所述目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域。
  11. 如权利要求9所述的电子设备,其中,所述对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据,包括:
    计算所述指纹区域的灰度频率场;
    计算所述指纹区域中各个像素点的切向像素之和与法向像素之和;
    整合所述灰度频率场、所述切向像素之和及法向像素之和,得到纹理轨迹数据。
  12. 如权利要求11所述的电子设备,其中,所述计算所述指纹区域的灰度频率场,包括:
    利用如下计算公式计算所述指纹区域的灰度频率场f:
    Figure PCTCN2021090722-appb-100006
    Figure PCTCN2021090722-appb-100007
    其中,V(x)为所述指纹区域上任意两个像素点的灰度垂直变化总量;x 1和x 2分别为指纹区域上任意两个不相同的像素点的横向坐标值;h(x)表示所述指纹区域的垂直方向上的灰度函数;a m为所述指纹区域上任意两个不相同的像素点之间的指纹波形的平均振幅。
  13. 如权利要求9至12中任意一项所述的电子设备,其中,所述将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名,包括:
    将所述纹理轨迹数据按照第一预设长度进行等间距拆分,得到第一拆分数据;
    将所述压力量化数据按照第二预设长度进行等间距拆分,得到第二拆分数据;
    将所述签名数据按照第三预设长度进行等间距拆分,得到第三拆分数据;
    将所述第一拆分数据、第二拆分数据和第三拆分数据按进行穿插组合,得到用户的指纹签名。
  14. 如权利要求9至12中任意一项所述的电子设备,其中,所述对所述指纹按压数据进行压力数据分析,得到压力量化数据,包括:
    利用如下计算公式计算所述指纹按压数据的瞬时压力值Z和压力梯度场T(x,y):
    Z=|T(x,y)|
    Figure PCTCN2021090722-appb-100008
    其中,Z为像素点(x,y)的瞬时压力值;T(x,y)像素点(x,y)的压力梯度场;G x(x,y)为瞬时压力值Z在点(x,y)对x的偏导数
    Figure PCTCN2021090722-appb-100009
    G y(x,y)为瞬时压力值Z在点(x,y)对y的偏导数
    Figure PCTCN2021090722-appb-100010
    θ(x,y)为瞬时压力值Z的施加方向;
    确定所述瞬时压力值Z和压力梯度场|T(x,y)|为压力量化数据。
  15. 一种计算机可读存储介质,包括存储数据区和存储程序区,存储数据区存储创建的数据,存储程序区存储有计算机程序;其中,所述计算机程序被处理器执行时实现如下所述的指纹签名生成方法:
    获取用户的指纹图像,对所述指纹图像进行指纹区域提取,得到指纹区域;
    对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据;
    获取用户的指纹按压数据,对所述指纹按压数据进行压力数据分析,得到压力量化数据;
    获取用户的电子签名,对所述电子签名进行签名识别,得到签名数据;
    将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名。
  16. 如权利要求15所述的计算机可读存储介质,其中,所述对所述指纹图像进行指纹区域提取,包括:
    对所述指纹图像进行下采样,得到全局特征图;
    将所述全局特征图进行第一阈值倍数的上采样,得到中间特征图;
    将所述中间特征图进行第二阈值倍数的上采样,得到指纹复原图像;
    利用第一激活函数计算所述指纹复原图像中各像素点属于预设的目标类别的目标类别概率;
    根据所述目标类别概率对所述指纹复原图像进行分割处理,得到指纹区域。
  17. 如权利要求15所述的计算机可读存储介质,其中,所述对所述指纹区域进行纹理轨迹分析,得到纹理轨迹数据,包括:
    计算所述指纹区域的灰度频率场;
    计算所述指纹区域中各个像素点的切向像素之和与法向像素之和;
    整合所述灰度频率场、所述切向像素之和及法向像素之和,得到纹理轨迹数据。
  18. 如权利要求17所述的计算机可读存储介质,其中,所述计算所述指纹区域的灰度频率场,包括:
    利用如下计算公式计算所述指纹区域的灰度频率场f:
    Figure PCTCN2021090722-appb-100011
    Figure PCTCN2021090722-appb-100012
    其中,V(x)为所述指纹区域上任意两个像素点的灰度垂直变化总量;x 1和x 2分别为指纹区域上任意两个不相同的像素点的横向坐标值;h(x)表示所述指纹区域的垂直方向上的灰度函数;a m为所述指纹区域上任意两个不相同的像素点之间的指纹波形的平均振幅。
  19. 如权利要求15至18中任意一项所述的计算机可读存储介质,其中,所述将所述纹理轨迹数据、所述压力量化数据和所述签名数据进行等间距数据融合,得到用户的指纹签名,包括:
    将所述纹理轨迹数据按照第一预设长度进行等间距拆分,得到第一拆分数据;
    将所述压力量化数据按照第二预设长度进行等间距拆分,得到第二拆分数据;
    将所述签名数据按照第三预设长度进行等间距拆分,得到第三拆分数据;
    将所述第一拆分数据、第二拆分数据和第三拆分数据按进行穿插组合,得到用户的指纹签名。
  20. 如权利要求15至18中任意一项所述的计算机可读存储介质,其中,所述对所述指纹按压数据进行压力数据分析,得到压力量化数据,包括:
    利用如下计算公式计算所述指纹按压数据的瞬时压力值Z和压力梯度场T(x,y):
    Z=|T(x,y)|
    Figure PCTCN2021090722-appb-100013
    其中,Z为像素点(x,y)的瞬时压力值;T(x,y)像素点(x,y)的压力梯度场;G x(x,y)为瞬时压力值Z在点(x,y)对x的偏导数
    Figure PCTCN2021090722-appb-100014
    G y(x,y)为瞬时压力值Z在点(x,y)对y的偏导数
    Figure PCTCN2021090722-appb-100015
    θ(x,y)为瞬时压力值Z的施加方向;
    确定所述瞬时压力值Z和压力梯度场|T(x,y)|为压力量化数据。
PCT/CN2021/090722 2021-01-19 2021-04-28 指纹签名生成方法、装置、电子设备及计算机存储介质 WO2022156088A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110068587.X 2021-01-19
CN202110068587.XA CN112861649B (zh) 2021-01-19 2021-01-19 指纹签名生成方法、装置、电子设备及计算机存储介质

Publications (1)

Publication Number Publication Date
WO2022156088A1 true WO2022156088A1 (zh) 2022-07-28

Family

ID=76007234

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/090722 WO2022156088A1 (zh) 2021-01-19 2021-04-28 指纹签名生成方法、装置、电子设备及计算机存储介质

Country Status (2)

Country Link
CN (1) CN112861649B (zh)
WO (1) WO2022156088A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI788204B (zh) * 2022-01-25 2022-12-21 王士華 用於電子文件的電子簽章方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102394754A (zh) * 2011-11-14 2012-03-28 宇龙计算机通信科技(深圳)有限公司 利用指纹生成手写签名的方法及通信终端
CN103218624A (zh) * 2013-04-25 2013-07-24 华东理工大学 基于生物特征的识别方法及装置
CN107992803A (zh) * 2017-11-10 2018-05-04 深圳市金立通信设备有限公司 一种电子签名的验证方法、终端设备及计算机可读介质
CN111523099A (zh) * 2020-03-27 2020-08-11 平安普惠企业管理有限公司 基于压力轨迹的授权验证方法、装置及可读存储介质
CN112883346A (zh) * 2021-01-19 2021-06-01 遥相科技发展(北京)有限公司 基于复合数据的安全身份认证方法、装置、设备及介质

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7035443B2 (en) * 2002-03-22 2006-04-25 Wong Jacob Y Personal choice biometric signature
CN102103692B (zh) * 2011-03-17 2012-07-18 电子科技大学 一种指纹图像增强方法
CN104113419B (zh) * 2014-07-18 2016-07-13 努比亚技术有限公司 电子签名的认证方法和系统
CN106203039A (zh) * 2016-07-04 2016-12-07 深圳市亚略特生物识别科技有限公司 指纹数字签名装置及电子业务系统
CN108306876B (zh) * 2018-01-30 2021-03-02 平安普惠企业管理有限公司 客户身份验证方法、装置、计算机设备和存储介质
CN108667622B (zh) * 2018-05-21 2022-02-22 平安科技(深圳)有限公司 电子签名认证方法、系统、计算机设备和存储介质
CN109544474A (zh) * 2018-11-16 2019-03-29 四川长虹电器股份有限公司 一种基于相位拉伸变换的指纹图像增强方法
CN110619274A (zh) * 2019-08-14 2019-12-27 深圳壹账通智能科技有限公司 基于印章和签名的身份验证方法、装置和计算机设备
CN110765857A (zh) * 2019-09-12 2020-02-07 敦泰电子(深圳)有限公司 指纹识别方法、芯片及电子装置
CN110942382B (zh) * 2019-10-15 2024-05-28 平安科技(深圳)有限公司 电子合同的生成方法、装置、计算机设备及存储介质
CN111079689B (zh) * 2019-12-27 2023-03-28 深圳纹通科技有限公司 一种指纹图像增强方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102394754A (zh) * 2011-11-14 2012-03-28 宇龙计算机通信科技(深圳)有限公司 利用指纹生成手写签名的方法及通信终端
CN103218624A (zh) * 2013-04-25 2013-07-24 华东理工大学 基于生物特征的识别方法及装置
CN107992803A (zh) * 2017-11-10 2018-05-04 深圳市金立通信设备有限公司 一种电子签名的验证方法、终端设备及计算机可读介质
CN111523099A (zh) * 2020-03-27 2020-08-11 平安普惠企业管理有限公司 基于压力轨迹的授权验证方法、装置及可读存储介质
CN112883346A (zh) * 2021-01-19 2021-06-01 遥相科技发展(北京)有限公司 基于复合数据的安全身份认证方法、装置、设备及介质

Also Published As

Publication number Publication date
CN112861649B (zh) 2024-05-10
CN112861649A (zh) 2021-05-28

Similar Documents

Publication Publication Date Title
JP7050725B2 (ja) ユーザ認証方法及び手書きサインインサーバ
US10140511B2 (en) Building classification and extraction models based on electronic forms
WO2022105179A1 (zh) 生物特征图像识别方法、装置、电子设备及可读存储介质
US9349046B2 (en) Smart optical input/output (I/O) extension for context-dependent workflows
CN112862024B (zh) 一种文本识别方法及系统
US10423817B2 (en) Latent fingerprint ridge flow map improvement
CN112883980B (zh) 一种数据处理方法及系统
CN112330331A (zh) 基于人脸识别的身份验证方法、装置、设备及存储介质
CN113033543A (zh) 曲形文本识别方法、装置、设备及介质
WO2021128846A1 (zh) 电子文件的控制方法、装置、计算机设备及存储介质
CN116912847A (zh) 一种医学文本识别方法、装置、计算机设备及存储介质
WO2022156088A1 (zh) 指纹签名生成方法、装置、电子设备及计算机存储介质
CN111178254A (zh) 一种签名识别方法及设备
CN112883346A (zh) 基于复合数据的安全身份认证方法、装置、设备及介质
CN112651399B (zh) 检测倾斜图像中同行文字的方法及其相关设备
CN111985491A (zh) 基于深度学习的相似信息合并方法、装置、设备及介质
Cai et al. Bank card and ID card number recognition in Android financial APP
US11461411B2 (en) System and method for parsing visual information to extract data elements from randomly formatted digital documents
CN115311664A (zh) 图像中文本类别的识别方法、装置、介质及设备
CN114943306A (zh) 意图分类方法、装置、设备及存储介质
CN113822215A (zh) 设备操作指引文件生成方法、装置、电子设备及存储介质
CN112580505A (zh) 网点开关门状态识别方法、装置、电子设备及存储介质
KR101040853B1 (ko) 이차원 바코드를 이용한 하이브리드 서명 검증 방법
CN113988223B (zh) 证件图像识别方法、装置、计算机设备及存储介质
CN113936286B (zh) 图像文本识别方法、装置、计算机设备及存储介质

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: 21920474

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21920474

Country of ref document: EP

Kind code of ref document: A1