Fingerprint identification device and electronic device

Abstract

The present disclosure relates to a kind of fingerprint identification device, electronic equipment, the device includes control module, fingerprint identification module, storage and calculation module and judging module, control module is connected to fingerprint identification module, for controlling the working time of each fingerprint identification component in fingerprint identification module, fingerprint identification module is used to carry out fingerprint image acquisition, output multiple fingerprint signals corresponding to fingerprint image;The storage and calculation module is connected to the fingerprint identification module, multiple weights are stored in the storage and calculation module, the storage and calculation module is used to determine the multiple feature vectors of fingerprint image according to the multiple fingerprint signals and the multiple weights;The judging module is connected to the storage and calculation module, for judging whether fingerprint identification succeeds according to the feature vector.This embodiment of the present disclosure can realize the efficient, low cost of fingerprint image acquisition, and can quickly and accurately realize the determination of the feature vector of fingerprint image and fingerprint matching, with the advantages of low cost, less resource consumption.

Description

Technical Field

[0001] This disclosure relates to the field of fingerprint recognition technology, and in particular to a fingerprint recognition device and electronic device. Background Technology

[0002] Fingerprint recognition technology is one of many biometric identification technologies. Biometric identification technology refers to the use of inherent physiological or behavioral characteristics of the human body to identify an individual. Due to the advantages of biometrics such as convenience and security, biometric technology has broad application prospects in the fields of identity authentication and network security. Available biometric identification technologies include fingerprints, faces, voiceprints, and irises, with fingerprints being the most widely used.

[0003] Currently, the fingerprint feature comparison and matching process in fingerprint recognition technology consumes a lot of resources and time, resulting in low fingerprint recognition efficiency. Summary of the Invention

[0004] According to one aspect of this disclosure, a fingerprint recognition device is provided, the device comprising a control module, a fingerprint recognition module, a storage and processing module, and a judgment module, wherein,

[0005] The control module is connected to the fingerprint recognition module and is used to control the working time of each fingerprint recognition component in the fingerprint recognition module. The fingerprint recognition module is used to acquire fingerprint images and output multiple fingerprint signals corresponding to the fingerprint images.

[0006] The storage and calculation module is connected to the fingerprint recognition module. The storage and calculation module stores multiple weights and is used to determine multiple feature vectors of the fingerprint image based on the multiple fingerprint signals and the multiple weights.

[0007] The judgment module is connected to the storage and calculation module and is used to determine whether fingerprint recognition is successful based on the feature vector.

[0008] In one possible implementation, the determining module is used to:

[0009] If fingerprint recognition is successful, a first control signal is output to the control module, causing the control module to control the fingerprint recognition module to stop fingerprint image acquisition; or

[0010] If fingerprint recognition fails, a second control signal is output to the control module so that the control module controls the fingerprint recognition module to continue acquiring fingerprint images. If fingerprint recognition fails K times consecutively, the first control signal is output to the control module so that the control module controls the fingerprint recognition module to stop acquiring fingerprint images, where K is a positive integer.

[0011] In one possible implementation, the storage and computing module includes a storage unit and a first storage and computing unit, wherein the storage unit is used to store the plurality of fingerprint signals, the first storage and computing unit stores a plurality of weights, and the first storage and computing unit is used to acquire the plurality of fingerprint signals transmitted from the storage unit and determine a plurality of feature vectors of the fingerprint image based on the plurality of fingerprint signals and the plurality of weights.

[0012] In one possible implementation, the first in-memory computing unit includes an in-memory computing array consisting of N rows and M columns of in-memory computing devices. The in-memory computing array stores a weight matrix consisting of the plurality of weights. Each in-memory computing device in the in-memory computing array is used to receive a feature matrix consisting of the plurality of fingerprint signals. The in-memory computing array is used to perform matrix operations and output a feature vector matrix, which includes the plurality of feature vectors.

[0013] In one possible implementation, the judgment module includes a judgment unit and a second storage unit.

[0014] The second in-memory computing unit includes multiple in-memory computing devices. Each in-memory computing device is used to receive a corresponding feature vector, perform logical operations with a preset feature vector stored in the in-memory computing device, and output the operation result. The operation result includes a first value and a second value.

[0015] The judgment unit is used to determine that fingerprint recognition is successful when the number of first values ​​output by each memory computing device is greater than or equal to a first preset number, or when the number of second values ​​output by each memory computing device is less than or equal to a second preset number; otherwise, it determines that fingerprint recognition is unsuccessful, wherein the first preset number is greater than the second preset number.

[0016] In one possible implementation, each of the memory computing devices includes a first transistor, a second transistor, a third transistor, a fourth transistor, and a fifth transistor, wherein,

[0017] The gate of the first transistor receives the control voltage, and the drain of the first transistor receives the power supply voltage. The source of the first transistor, the drain of the second transistor, and the drain of the third transistor are connected to form an output node.

[0018] The gate of the second transistor is used to receive a first voltage signal, and the gate of the third transistor is used to receive a second voltage signal, wherein the first voltage signal and the second voltage signal are opposite values.

[0019] The source of the second transistor is connected to the source of the fourth transistor, and the source of the third transistor is connected to the source of the fifth transistor.

[0020] The gate of the fourth transistor is used to receive the third voltage signal, and the gate of the fifth transistor is used to receive the fourth voltage signal, wherein the third voltage signal and the fourth voltage signal are opposite values.

[0021] The drain of the fourth transistor and the drain of the fifth transistor are grounded.

[0022] In one possible implementation, the control voltage is used for:

[0023] Disconnect the first transistor when the control module controls the fingerprint recognition module to stop fingerprint image acquisition, or...

[0024] The first transistor is turned on when the control module controls the fingerprint recognition module to continuously acquire fingerprint images.

[0025] In one possible implementation, the control module includes a row control unit and a column control unit. The fingerprint recognition module comprises multiple fingerprint recognition components arranged in a multi-row, multi-column fingerprint recognition array. Each fingerprint recognition component includes a photodiode. The operating time includes an exposure time.

[0026] The row control unit and the column control unit are used to output strobe signals to control the exposure time of each fingerprint recognition component.

[0027] According to one aspect of this disclosure, an electronic device is provided, the electronic device including the fingerprint recognition device described above.

[0028] This embodiment controls the working time of each fingerprint recognition component in the fingerprint recognition module through a control module, achieving efficient and low-cost fingerprint image acquisition. The storage and calculation module determines multiple feature vectors of the fingerprint image based on the multiple fingerprint signals and multiple weights. The judgment module determines whether the fingerprint recognition is successful based on the feature vectors. This enables the rapid and accurate determination of the feature vectors of the fingerprint image and fingerprint matching, with the advantages of low cost and low resource consumption.

[0029] In one possible implementation, the electronic device includes any one of a display, smartphone, smartwatch, smart bracelet, tablet, laptop, all-in-one computer, access control device, and electronic door lock.

[0030] This embodiment controls the working time of each fingerprint recognition component in the fingerprint recognition module through a control module, achieving efficient and low-cost fingerprint image acquisition. The storage and calculation module determines multiple feature vectors of the fingerprint image based on the multiple fingerprint signals and multiple weights. The judgment module determines whether the fingerprint recognition is successful based on the feature vectors. This enables the rapid and accurate determination of the feature vectors of the fingerprint image and fingerprint matching, with the advantages of low cost and low resource consumption.

[0031] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0032] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0033] Figure 1 A block diagram of a fingerprint recognition device according to an embodiment of the present disclosure is shown.

[0034] Figure 2 A schematic diagram of a fingerprint recognition device according to an embodiment of the present disclosure is shown.

[0035] Figure 3 A schematic diagram of a memory computing unit according to an embodiment of the present disclosure is shown.

[0036] Figure 4 A flowchart illustrating fingerprint recognition using a fingerprint recognition device according to an embodiment of this disclosure is shown. Detailed Implementation

[0037] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0038] In the description of this disclosure, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0039] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise expressly specified.

[0040] In this disclosure, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this disclosure according to the specific circumstances.

[0041] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0042] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0043] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0044] Please see Figure 1 , Figure 1 A block diagram of a fingerprint recognition device according to an embodiment of the present disclosure is shown.

[0045] like Figure 1 As shown, the device includes a control module 10, a fingerprint recognition module 20, a storage and processing module 30, and a judgment module 40, wherein...

[0046] The control module 10 is connected to the fingerprint recognition module 20 and is used to control the working time of each fingerprint recognition component in the fingerprint recognition module 20. The fingerprint recognition module 20 is used to acquire fingerprint images and output multiple fingerprint signals corresponding to the fingerprint images.

[0047] The storage and calculation module 30 is connected to the fingerprint recognition module 20. The storage and calculation module 30 stores multiple weights and is used to determine multiple feature vectors of the fingerprint image based on the multiple fingerprint signals and the multiple weights.

[0048] The judgment module 40 is connected to the storage and calculation module 30 and is used to determine whether the fingerprint recognition is successful based on the feature vector.

[0049] This embodiment controls the working time of each fingerprint recognition component in the fingerprint recognition module 20 through the control module 10, thereby achieving efficient and low-cost fingerprint image acquisition. The storage and calculation module 30 determines multiple feature vectors of the fingerprint image based on the multiple fingerprint signals and multiple weights. The judgment module 40 judges whether the fingerprint recognition is successful based on the feature vectors. This can quickly and accurately determine the feature vectors of the fingerprint image and perform fingerprint matching, and has the advantages of low cost and low resource consumption.

[0050] This disclosure does not limit the specific implementation of the control module 10, fingerprint recognition module 20, storage and calculation module 30, and judgment module 40. Those skilled in the art can adopt appropriate technical means to implement them according to actual conditions and needs, as long as the corresponding functions can be achieved. In addition, the division of modules is not restrictive. For example, the control module 10, storage and calculation module 30, and judgment module 40 can be combined, such as merging the storage and calculation module 30 and the judgment module 40 into the control module 10. Of course, they can also be further divided into other modules or units, which is not limited in this disclosure.

[0051] In one example, the control module 10 may include processing components, which, exemplary, include, but are not limited to, a single processor, discrete components, or a combination of a processor and discrete components. The processor may include a controller in an electronic device with instruction execution capabilities. The processor may be implemented in any suitable manner, for example, by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components. Within the processor, the executable instructions may be executed by hardware circuitry such as logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Of course, the control module 10 may also include multiple processing components with different functions; the number of processing components is not limited in this embodiment.

[0052] Please see Figure 2 , Figure 2 A schematic diagram of a fingerprint recognition device according to an embodiment of the present disclosure is shown.

[0053] In one example, such as Figure 2 As shown, the fingerprint recognition module 20 may include an array of multiple fingerprint recognition components 210. The fingerprint recognition components 210 may be optical fingerprint components (such as photodiodes) or capacitive fingerprint components, etc.

[0054] In one example, the control module 10 may include a row control unit 100 and a column control unit 110. Each signal output terminal of the row control unit 100 is connected to each fingerprint recognition component 210 in the corresponding row of the array, and each signal output terminal of the column control unit 110 is connected to each fingerprint recognition component 210 in the corresponding column of the array. The row control unit 100 and the column control unit 110 output row control signals and column control signals respectively as selection signals to control the working duration of each fingerprint recognition component 210 in the fingerprint recognition module 20. For example, assuming a touch is detected in a certain area of ​​the touch screen, the row control unit 100 and the column control unit 110 can output row control signals and column control signals respectively to control the working duration of the fingerprint recognition component 210 in that area. The working duration can be the duration for which the row control signals and column control signals select the fingerprint recognition component. During this duration, the selected fingerprint recognition component works and performs signal acquisition. For example, if the fingerprint recognition component 210 is a photodiode, the exposure time of each photodiode in the area can be controlled by the row control signal and the column control signal. This embodiment does not limit the specific working time, and those skilled in the art can set it according to the actual situation and needs.

[0055] In one example, such as Figure 2 As shown, a signal processing module 50 can be set between the fingerprint recognition module 20 and the storage module 30 to perform signal processing on the fingerprint signal collected by the fingerprint recognition module 20. The signal processing module 50 may include multiple signal processing units 510. Each signal processing unit 510 may include a signal amplifier, filter, analog-to-digital converter, etc. The type and implementation method of the signal processing components included in each signal processing unit 510 are not limited in this embodiment. Those skilled in the art can set them according to actual conditions and needs.

[0056] In one possible implementation, such as Figure 2 As shown, the storage and calculation module 30 may include a storage unit 310 and a storage and calculation unit 320. The storage and calculation unit 320 may include a first storage and calculation unit, a second storage and calculation unit, etc. (not shown). The storage unit 310 is used to store the plurality of fingerprint signals. The first storage and calculation unit stores a plurality of weights. The first storage and calculation unit is used to acquire the plurality of fingerprint signals transmitted from the storage unit 310 and determine a plurality of feature vectors of the fingerprint image based on the plurality of fingerprint signals and the plurality of weights.

[0057] In one example, storage unit 310 may include a computer-readable storage medium, which can be a tangible device capable of holding and storing instructions for use by an instruction execution device. A computer-readable storage medium may be, for example—but not limited to—an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), programmable read-only memory (PROM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage medium as used herein is not to be construed as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0058] In one example, the in-memory computing unit 320 can be implemented using a mature in-memory computing chip, or it can employ other specific in-memory computing methods.

[0059] In one possible implementation, the in-memory computing unit 320 may include an in-memory computing array (where N and M are both positive integers) composed of N rows and M columns of in-memory computing devices. This disclosure does not limit the specific implementation of the in-memory computing devices. Those skilled in the art can set them according to actual conditions and needs. The preferred implementation is described below by way of example.

[0060] Please see Figure 3 , Figure 3 A schematic diagram of a storage unit 320 according to an embodiment of the present disclosure is shown.

[0061] For example, such as Figure 3 As shown, the memory computing device may include a first transistor Q1, a second transistor Q2, a third transistor Q3, a fourth transistor Q4, and a fifth transistor Q5, wherein,

[0062] The gate of the first transistor Q1 receives the control voltage Pre, and the drain of the first transistor Q1 receives the power supply voltage VCC. The source of the first transistor Q1, the drain of the second transistor Q2, and the drain of the third transistor Q3 are connected to form an output node.

[0063] The gate of the second transistor Q2 is used to receive a first voltage signal, and the gate of the third transistor Q3 is used to receive a second voltage signal, wherein the first voltage signal and the second voltage signal are opposite values.

[0064] The source of the second transistor Q2 is connected to the source of the fourth transistor Q4, and the source of the third transistor Q3 is connected to the source of the fifth transistor Q5.

[0065] The gate of the fourth transistor Q4 is used to receive the third voltage signal, and the gate of the fifth transistor Q5 is used to receive the fourth voltage signal. The third voltage signal and the fourth voltage signal are opposite values.

[0066] The drain of the fourth transistor Q4 and the drain of the fifth transistor Q5 are grounded.

[0067] For example, the in-memory computing unit 320 may include a first in-memory computing unit. The in-memory computing array of the first in-memory computing unit stores a weight matrix composed of the plurality of weights. Each in-memory computing device in the in-memory computing array is used to receive a feature matrix composed of the plurality of fingerprint signals. The in-memory computing array is used to perform matrix operations and output a feature vector matrix, which includes the plurality of feature vectors. Specifically, after the fingerprint information is collected, the fingerprint signal is stored in the storage unit 310. The first in-memory computing unit stores a pre-trained weight matrix, which includes multiple weights. The fingerprint signal in the storage unit 310 is used as the gate input (second voltage signal [A]) of the third transistor Q3 of each in-memory computing device in the first in-memory computing unit. <0> A <1> ...A <n>Each weight serves as the gate input (fourth voltage signal BL) of the fifth transistor Q5 of each memory device in the first memory unit. <0> BL <1> BL <n>The output node outputs the corresponding feature vector. Each memory-based computing device performs matrix operations to obtain the feature vector for subsequent comparison. In this example, the first voltage signal received by the gate of the second transistor Q2 is the opposite value of the second voltage signal (i.e., the opposite value of the fingerprint signal), and the third voltage signal received by the gate of the fourth transistor Q4 is the opposite value of the fourth voltage signal (i.e., the opposite value of the weights). As an example, suppose the information in the fingerprint signal contains the specific direction of a valley or ridge in the fingerprint. This information is stored in binary form in the storage unit 310. The fingerprint signal is input to the memory-based computing device through the gate of the third transistor Q3. A dot product summation (a characteristic of memory-based chips) with the weights stored in the first memory unit yields a feature vector (a feature value). In addition, information such as the number of feature points and grayscale values ​​at a certain point in the fingerprint, when producted with the weights, can also yield a feature value. These feature values ​​can be combined into a feature vector.

[0068] For example, a feature vector can be a set of numerical values ​​generated during feature extraction to represent a key feature or attribute of an object. In fingerprint recognition, a feature vector is a digital representation of the unique features of a fingerprint image. The generation of these feature vectors involves extracting information about the fingerprint texture, structure, and shape from the fingerprint image, such as minutiae represented by bifurcation points and endpoints, texture orientation, grayscale differences, etc. It should be noted that when a computer performs matrix operations, it represents each element in the matrix as a binary number and uses binary arithmetic instructions to perform multiplication, addition, and other mathematical operations. These binary values ​​are processed to obtain the final result, which may then be converted into a more easily understood decimal or other representation for use by the user or application. However, related technologies store fingerprint signals and weights in memory, and then use a processor to obtain fingerprint signals and weights for matrix operations. This method has low computational efficiency and high requirements for computing and storage resources. The embodiments of this disclosure use a first in-memory unit composed of in-memory computing devices to realize matrix operations between weights and fingerprint signals. Since the first in-memory unit stores a pre-trained weight matrix, it is not necessary to frequently call the data in memory. By utilizing the in-memory computing characteristics of the in-memory computing devices, weight storage and matrix operations can be directly realized, which can greatly reduce storage costs and computing costs, and improve computing efficiency.

[0069] The following is an exemplary description of the preferred implementation method for fingerprint comparison and matching.

[0070] In one possible implementation, the judgment module 40 may include a judgment unit and a second memory unit.

[0071] The second in-memory computing unit may include multiple in-memory computing devices. Each in-memory computing device is used to receive a corresponding feature vector and perform logical operations with a preset feature vector stored in the in-memory computing device, and output the operation result. The operation result includes a first value (e.g., 0) and a second value (e.g., 1). It is assumed that the operation result of 0 indicates that the received feature vector is the same as the preset feature vector stored in the in-memory computing device.

[0072] In one possible implementation, the judgment unit can be used to determine that fingerprint recognition is successful when the number of first values ​​output by each memory computing device is greater than or equal to a first preset number, or when the number of second values ​​output by each memory computing device is less than or equal to a second preset number; otherwise, it can determine that fingerprint recognition fails, wherein the first preset number is greater than the second preset number.

[0073] For example, the judgment unit may include a comparison circuit or be implemented using the aforementioned processing components. The judgment unit is used to compare the number of the first value with a first preset number, or the number of the second value with a second preset number. The specific implementation of the comparison circuit is not limited in the embodiments of this disclosure. Those skilled in the art can adopt appropriate technical means to implement it according to the actual situation and needs.

[0074] The embodiments disclosed herein do not limit the specific size of the first preset number and the second preset number, which can be set by those skilled in the art according to actual conditions and needs.

[0075] In one possible implementation, such as Figure 3 As shown, the memory computing devices in the second memory computing unit include a first transistor Q1, a second transistor Q2, a third transistor Q3, a fourth transistor Q4, and a fifth transistor Q5, wherein,

[0076] The gate of the first transistor Q1 receives the control voltage Pre, and the drain of the first transistor Q1 receives the power supply voltage VCC. The source of the first transistor Q1, the drain of the second transistor Q2, and the drain of the third transistor Q3 are connected to form an output node, which is used to output the calculation result.

[0077] The gate of the second transistor Q2 is used to receive the inverse value of the feature vector, and the gate of the third transistor Q3 is used to receive the feature vector (the second voltage signal [A]). <0> A <1> ...A <n>]),

[0078] The source of the second transistor Q2 is connected to the source of the fourth transistor Q4, and the source of the third transistor Q3 is connected to the source of the fifth transistor Q5.

[0079] The gate of the fourth transistor Q4 is used to receive the opposite value of the preset feature vector, and the gate of the fifth transistor Q5 is used to receive the preset feature vector (the fourth voltage signal BL). <0> BL <1> BL <n>),

[0080] The drain of the fourth transistor Q4 and the drain of the fifth transistor Q5 are grounded.

[0081] In one possible implementation, the control voltage Pre is used for:

[0082] When the control module 10 controls the fingerprint recognition module 20 to stop fingerprint image acquisition, the first transistor Q1 is disconnected, or...

[0083] The first transistor Q1 is turned on when the control module 10 controls the fingerprint recognition module 20 to continuously acquire fingerprint images.

[0084] For example, the control voltage Pre remains active during the comparison calculation, for example, at a low level, and then switches to a high level after the comparison is complete.

[0085] Please refer to Table 1, which shows the numerical comparisons implemented by the memory computing devices.

[0086] Table 1

[0087] 0 0 0 0 1 1 1 1 0 1 0 1

[0088] As can be seen from Table 1, only when the two input data A <n>、BL <n>When they are the same, the output node OUT <n>The output is 0 if the number of outputs is 0, otherwise it is 1. Therefore, the present invention can quickly and efficiently compare the preset feature vector with the feature vector through the memory computing device. Furthermore, by performing threshold judgment through the judgment unit, when the number of outputs of 0 reaches the threshold number (a first preset number), the fingerprint recognition is judged to be successful; otherwise, the recognition fails. This efficiently realizes the data comparison function.

[0089] In one possible implementation, the determining module 40 is further configured to:

[0090] If fingerprint recognition is successful, a first control signal is output to the control module 10, causing the control module 10 to control the fingerprint recognition module 20 to stop fingerprint image acquisition; or

[0091] If fingerprint recognition fails, a second control signal is output to the control module 10, so that the control module 10 controls the fingerprint recognition module 20 to continue fingerprint image acquisition. If fingerprint recognition fails K times consecutively, the first control signal is output to the control module 10, so that the control module 10 controls the fingerprint recognition module 20 to stop fingerprint image acquisition, where K is a positive integer.

[0092] The specific size of K is not limited in the embodiments disclosed herein, and those skilled in the art can set it according to actual conditions and needs.

[0093] In one example, if fingerprint recognition fails K times consecutively, the control module 10 can also issue a prompt message to the user.

[0094] In one possible implementation, at least one of the memory-based computing module 30 and the judgment module 40 in this embodiment of the present disclosure includes a memory-based computing unit 320.

[0095] For example, the storage and calculation module 30 includes a storage and calculation unit 320, while the judgment module 40 does not include a storage and calculation unit 320. In this case, the embodiments of this disclosure utilize the integrated storage and calculation characteristics of the first storage and calculation unit to realize weight storage and matrix operation. The judgment module 40 can be implemented using a processing component. The processing component uses relevant technologies to realize the comparison of feature vectors with preset feature vectors and the judgment of fingerprint recognition.

[0096] For example, the storage module 30 does not include the storage unit 320, while the judgment module 40 includes the storage unit 320. In this case, the embodiments of this disclosure utilize the processing component to implement weight storage and matrix operations using related technologies. The judgment module 40 can be implemented using the second storage unit, which is used to compare the feature vector with the preset feature vector.

[0097] For example, the storage and calculation module 30 includes a storage and calculation unit 320, and the judgment module 40 also includes a storage and calculation unit 320. In this case, the embodiments of this disclosure utilize the integrated storage and calculation characteristics of the first storage and calculation unit to realize weight storage and matrix operation, and use the second storage and calculation unit to realize the comparison of feature vector with preset feature vector, so as to further realize the efficiency of fingerprint recognition.

[0098] The process of fingerprint recognition using the fingerprint recognition device according to the embodiments of this disclosure will be described exemplarily below.

[0099] Figure 4 A flowchart illustrating fingerprint recognition using a fingerprint recognition device according to an embodiment of this disclosure is shown.

[0100] For example, such as Figure 4 As shown, the fingerprint recognition process may include:

[0101] The fingerprint recognition pixel array generates a fingerprint signal based on reflected light, including:

[0102] Light signal acquisition and conversion process: When a finger is pressed on the fingerprint recognition area of ​​the fingerprint recognition module 20, the photodiode in the fingerprint recognition component 210 starts to work. The row control unit 100 and the column control unit 110 determine the exposure time of the photodiode by controlling the row selection signal. After a certain exposure time, the light signal is converted into an electrical signal by the current-to-voltage conversion circuit in the pixel unit and amplified by the voltage amplifier. At this time, the row control unit 100 and the column control unit 110 control the column selection signal to output the amplified signal.

[0103] Analog-to-digital conversion process: The amplified information is converted into a digital signal by an analog-to-digital converter so that it can be stored in the storage unit.

[0104] The storage module (i.e., storage unit) stores fingerprint signal data, including:

[0105] Data storage process: After the analog-to-digital conversion is completed, the digital signal is transmitted to the input line of the storage unit 310 through the connection line. The storage unit here is not limited to DRAM, SRAM, FeRAM, etc.

[0106] The fingerprint feature vector is obtained according to the set algorithm, including:

[0107] The process of obtaining the feature vector: After the data collected in the fingerprint recognition area is amplified, converted into a digital signal and stored, the data is read out and the feature vector is obtained. At this time, the fingerprint feature vector can be obtained by either putting the data into the processing component for calculation in the traditional way, or by taking advantage of the fact that the storage unit 320 is convenient for solving matrix operations (the storage part in the storage module 30 is not limited to DRAM, SRAM, FeRAM, etc.).

[0108] The extracted fingerprint feature vector is compared with the standard fingerprint feature vector, including:

[0109] Comparison Process: The fingerprint feature vector obtained by calculating the feature vector is analyzed and compared with the preset feature vector obtained based on the standard fingerprint data pre-entered by the user. At this point, the two sets of feature vectors can be compared by putting them into the processing component in the traditional way, or the dynamic complementary AND gate truth table in the designed storage unit 320 can be used to perform the final feature vector comparison.

[0110] Determine if fingerprint recognition was successful:

[0111] Threshold judgment process: If the comparison result reaches the set threshold (such as the first preset number), the judgment module 40 will send a signal to the row control unit 100 and the column control unit 110, and the row control unit 100 and the column control unit 110 will stop working, and the fingerprint recognition will be successful; if the two do not meet the conditions for successful fingerprint recognition, the threshold judgment module 40 will send another signal to the row control unit 100 and the column control unit 110, and the row control unit 100 and the column control unit 110 will refresh and start the entire process from the beginning until the fingerprint recognition is successful.

[0112] The feature vector obtained by the above method, that is, by utilizing the intrinsic advantage of the storage unit 320 to efficiently process matrix operations, or by solving the feature vector according to the traditional method, will be used as the comparison data and compared with the reference feature vector obtained by the reference fingerprint data pre-entered by the user. If the comparison threshold is met, the recognition is judged to be successful. If the comparison threshold is not met, the recognition is judged to be failed and the fingerprint data will be collected again in a loop until the maximum number of comparisons is reached, triggering the recognition failure prompt function.

[0113] According to one aspect of this disclosure, an electronic device is provided, the electronic device including the fingerprint recognition device described above.

[0114] In one possible implementation, the electronic device includes any one of a display, smartphone, smartwatch, smart bracelet, tablet, laptop, all-in-one computer, access control device, and electronic door lock.

[0115] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.< / n> < / n> < / n> < / n> < / n> < / n> < / n>

Claims

1. A fingerprint recognition device, characterized in that, The device includes a control module, a fingerprint recognition module, a storage and processing module, and a judgment module, wherein, The control module is connected to the fingerprint recognition module and is used to control the working time of each fingerprint recognition component in the fingerprint recognition module. The fingerprint recognition module is used to acquire fingerprint images and output multiple fingerprint signals corresponding to the fingerprint images. The storage and calculation module is connected to the fingerprint recognition module. The storage and calculation module stores multiple weights and is used to determine multiple feature vectors of the fingerprint image based on the multiple fingerprint signals and the multiple weights. The judgment module is connected to the storage and processing module and is used to determine whether fingerprint recognition is successful based on the feature vector. The storage and processing module includes a storage unit and a first storage and processing unit. The storage unit stores the plurality of fingerprint signals, and the first storage and processing unit stores multiple weights. The first storage and processing unit is used to acquire the plurality of fingerprint signals transmitted from the storage unit and determine multiple feature vectors of the fingerprint image based on the plurality of fingerprint signals and the multiple weights. The first in-memory computing unit includes an in-memory array composed of N rows and M columns of in-memory computing devices. The in-memory array stores a weight matrix composed of the plurality of weights. Each in-memory computing device in the array receives a feature matrix composed of the plurality of fingerprint signals. The in-memory array performs matrix operations and outputs a feature vector matrix, which includes the plurality of feature vectors. Each of the memory computing devices includes a first transistor, a second transistor, a third transistor, a fourth transistor, and a fifth transistor. The gate of the first transistor receives a control voltage, and the drain of the first transistor receives a power supply voltage. The sources of the first transistor, the drains of the second transistor, and the drain of the third transistor are connected as an output node. The gate of the second transistor receives a first voltage signal, and the gate of the third transistor receives a second voltage signal. The first voltage signal and the second voltage signal are opposite values. The source of the second transistor is connected to the source of the fourth transistor, and the source of the third transistor is connected to the source of the fifth transistor. The gate of the fourth transistor receives a third voltage signal, and the gate of the fifth transistor receives a fourth voltage signal. The third voltage signal and the fourth voltage signal are opposite values. The drains of the fourth transistor and the fifth transistor are grounded.

2. The apparatus according to claim 1, characterized in that, The judgment module is used for: If fingerprint recognition is successful, a first control signal is output to the control module, causing the control module to control the fingerprint recognition module to stop fingerprint image acquisition; or If fingerprint recognition fails, a second control signal is output to the control module so that the control module controls the fingerprint recognition module to continue acquiring fingerprint images. If fingerprint recognition fails K times consecutively, the first control signal is output to the control module so that the control module controls the fingerprint recognition module to stop acquiring fingerprint images, where K is a positive integer.

3. The apparatus according to claim 1, characterized in that, The judgment module includes a judgment unit and a second storage and calculation unit. The second in-memory computing unit includes multiple in-memory computing devices. Each in-memory computing device is used to receive a corresponding feature vector, perform logical operations with a preset feature vector stored in the in-memory computing device, and output the operation result. The operation result includes a first value and a second value. The judgment unit is used to determine that fingerprint recognition is successful when the number of first values ​​output by each memory computing device is greater than or equal to a first preset number, or when the number of second values ​​output by each memory computing device is less than or equal to a second preset number; otherwise, it determines that fingerprint recognition is unsuccessful, wherein the first preset number is greater than the second preset number.

4. The apparatus according to claim 1, characterized in that, The control voltage is used for: Disconnect the first transistor when the control module controls the fingerprint recognition module to stop fingerprint image acquisition, or... The first transistor is turned on when the control module controls the fingerprint recognition module to continuously acquire fingerprint images.

5. The apparatus according to claim 1, characterized in that, The control module includes a row control unit and a column control unit. The fingerprint recognition module comprises multiple fingerprint recognition components arranged in a multi-row, multi-column fingerprint recognition array. Each fingerprint recognition component includes a photodiode. The operating time includes the exposure time. The row control unit and the column control unit are used to output strobe signals to control the exposure time of each fingerprint recognition component.

6. An electronic device, characterized in that, The electronic device includes a fingerprint recognition device as described in any one of claims 1 to 5.

7. The electronic device according to claim 6, characterized in that, The electronic device includes any one of a display, smartphone, smartwatch, smart bracelet, tablet, laptop, all-in-one computer, access control device, and electronic door lock.

Images