Storage device based on biological feature recognition, decryption method and storage medium

Abstract

The invention belongs to the technical field of biological feature recognition, and relates to a storage device based on biological feature recognition, a decryption method and a storage medium. A groove is formed in one end of a storage device body and used for containing a hardware interface and a foldable data line, one end of the foldable data line is connected with the hardware interface, and the other end of the foldable data line extends into the storage device body; the hardware interface is folded and stored in the groove through the foldable data line, and the memory is used for pre-storing recorded fingerprint data and auricle data of a target user; the fingerprint collector is arranged on the storage device body, the ear scanning device is arranged on the storage device body, the processor obtains fingerprint information and auricle information of a target user, compares the fingerprint information with fingerprint data pre-stored in the memory, compares the auricle information with pre-stored auricle data, and sends the fingerprint information and the auricle information to the processor; and opening the access authority of the target user to the storage device after successful comparison. According to the scheme, the security of the storage device is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of biometric identification technology, and more specifically, to a storage device, a decryption method and a storage medium based on biometric identification. Background Art

[0002] USB Key is a hardware device with a USB interface. It has a built-in cryptographic CPU module and a certain amount of storage space to store the user's private key and digital certificate. Existing USB Key technology mainly uses fingerprint recognition technology for biometric identification, but fingerprint recognition technology itself has the risk of being copied, simulated or cracked, thereby reducing the security of USB Key.

[0003] Biometric fusion recognition provides an effective countermeasure for these situations. It integrates the characteristic information of multiple biometrics to eliminate some of the disadvantages of single biometric recognition, improve the recognition performance of the entire system, and achieve high-precision individual identity recognition.

[0004] At present, multi-biometric recognition mainly integrates multiple features such as face, fingerprint, palm print, voice and iris to improve the stability, accuracy and unforgeability of biometric recognition. By integrating multiple biometrics, a more secure identity authentication method can be achieved. However, the selection of biometrics for different application scenarios and the verification and decryption methods have become the difficulties of multi-biometric recognition.

[0005] For example, the invention patent with the authorization announcement number CN109508658B, whose invention name is a multi-biometric joint identification method and device, discloses calculating the similarity between at least two biometric features of the user to be identified and at least two biometric features of a registered user, and generating the similarity corresponding to each of the at least two biometric features; using a genetic algorithm to calculate the preset weighted values ​​corresponding to each of the at least two biometric features; according to the preset weighted values ​​corresponding to each of the at least two biometric features, weighted summing up the similarities corresponding to each of the at least two biometric features, to obtain the final similarity between the user to be identified and the registered user; if the final similarity is greater than the preset similarity threshold, it is determined that the identity recognition of the user to be identified is successful.

[0006] This solution only discloses a method of similarity calculation and weight distribution. However, when the feature extraction of different biometric features is inaccurate, it will have a greater impact on the recognition result, causing problems of inaccurate recognition and low efficiency.

[0007] Therefore, how to solve the problem of poor recognition accuracy in current multi-biometric recognition methods is one of the key research directions. Summary of the invention

[0008] In order to solve the technical problem of poor recognition accuracy in the above-mentioned multi-biometric recognition method, the present invention provides solutions in the following aspects.

[0009] In a first aspect, the present invention provides a storage device based on biometric identification, including a storage device body and a hardware interface, wherein a groove is provided at one end of the storage device body for placing the hardware interface and a foldable data cable, wherein one end of the foldable data cable is connected to the hardware interface, and the other end extends into the interior of the storage device body, and the hardware interface is folded and stored in the groove through the foldable data cable. The storage device also includes: a memory for pre-storing collected fingerprint data and auricle data of a target user; a fingerprint collector, which is arranged on the storage device body for collecting fingerprint information of the target user; an ear scanning device, which is arranged on the storage device body for collecting auricle information of the target user; a processor, which is connected to the fingerprint collector, the ear scanning device, the foldable data cable and the memory, and is used to obtain the fingerprint information and auricle information of the target user, and compare the fingerprint information with the fingerprint data pre-stored in the memory. Compare the auricle information with the pre-stored auricle data, and after the comparison is successful, open the target user's access rights to the storage device, wherein the fingerprint information is compared with the pre-stored fingerprint data in the memory, including: calculating a first similarity between feature points in the fingerprint information and feature points in the fingerprint data, and determining that the fingerprint information matches the pre-stored fingerprint data when the first similarity is greater than a first set value; compare the auricle information with the pre-stored auricle data, including: using Harris corner point detection to determine key feature points in the auricle information, connecting the detected key feature points to form the contour line of the auricle; smoothing the connected contour line, and establishing an ear contour model of the auricle according to the contour line; calculating a second similarity between a feature vector corresponding to the auricle contour model and an auricle feature vector corresponding to the pre-stored auricle data; in response to the second similarity being greater than a second set value, determining that the auricle information matches the pre-stored auricle data.

[0010] According to the solution of the present invention, by setting up dual biometric identification of fingerprint identification and auricle identification in the storage device, the stability and uniqueness of the human auricle are utilized to effectively prevent the risk of single-factor authentication fingerprint being copied, simulated or cracked, thereby greatly improving the security and reliability of using the storage device. At the same time, the groove structure setting for the storage device effectively improves the flexibility of using the storage device, while realizing the hiding of the hardware interface and improving the portability of use.

[0011] Preferably, the processor is connected to the fingerprint collector through a fingerprint recognition module, and is used to extract fingerprint ridge data from the fingerprint information and extract feature points required for fingerprint recognition; the processor is connected to the ear scanning device through a human ear recognition module, and is used to extract auricle feature points from auricle information and connect the auricle feature points to establish an ear contour model.

[0012] Preferably, the storage device further comprises an indicator light, which is connected to the processor and is used to determine whether the certificate information stored in the storage device is read according to a lighting condition.

[0013] According to the solution of the present invention, the use status of the storage device can be more intuitively obtained through the setting of the indicator light, effectively improving the convenience of using the storage device.

[0014] In the second aspect, the present invention also provides a decryption method for a storage device based on biometric identification, which is applied to the storage device based on biometric identification described in the first invention above, including: obtaining fingerprint information and auricle information of a target user; extracting fingerprint ridge data from the fingerprint information, and comparing the fingerprint ridge data with fingerprint data pre-stored in a memory to determine whether the fingerprint information matches the pre-stored fingerprint data, wherein the comparison process is achieved by calculating the similarity between feature points in the fingerprint information and feature points in the fingerprint data; constructing an ear contour model to be identified based on the auricle information, and comparing the feature vector corresponding to the ear contour model with the auricle feature vector corresponding to the pre-stored auricle data to determine whether the auricle information matches the pre-stored auricle data; in response to the fingerprint information matching the pre-stored fingerprint data and the auricle information matching the pre-stored auricle data, opening the target user's access rights to the storage device.

[0015] According to the solution of the present invention, the fingerprint information of the target user is identified and processed to obtain the fingerprint ridge data for fingerprint data matching. At the same time, the auricle information is processed and the auricle feature points are extracted to establish an auricle contour model to realize the auricle recognition function. The accuracy of dual biometric recognition is achieved, and the security of the use of storage devices is effectively improved.

[0016] Preferably, the fingerprint information is compared with the fingerprint data pre-stored in the memory, including: extracting fingerprint ridge data from the fingerprint information of the target user to extract the fingerprint ridge feature points required for fingerprint identification; calculating the first similarity between the fingerprint ridge feature points and the feature points of the pre-stored fingerprint data; in response to the first similarity being greater than a first set value, determining that the fingerprint information matches the pre-stored fingerprint data.

[0017] According to the solution of the present invention, the feature matching process is realized by using similarity calculation, which can perform matching more quickly and achieve efficient recognition.

[0018] Preferably, fingerprint ridge data is extracted from the fingerprint information of the target user to extract the fingerprint ridge feature points required for fingerprint identification, including: segmenting the background area and the effective fingerprint area in the fingerprint information of the target user; using a thinning algorithm to thin the fingerprint ridges in the effective fingerprint area into lines with a single pixel width; determining the starting point, end point and bifurcation point of the ridge in the line as ridge feature points.

[0019] Preferably, the starting point, end point and bifurcation point of the ridge in the line are determined as ridge feature points, including: for the line with a single pixel width, taking any point in the line as the center point, setting a rectangular frame according to a set size, and calculating the gradient of each point in the line portion within the rectangular frame; taking the point whose gradient value is greater than zero as the reserved point, calculating the variance of the gradient of each reserved point in the rectangular frame, wherein the point whose variance is greater than a first threshold is taken as the bifurcation point; calculating the sum of the direction vectors between each reserved point in the rectangular frame and the center point, and taking the point where the sum of the direction vectors is greater than a second threshold as the starting point and / or end point of the ridge.

[0020] According to the solution of the present invention, by extracting the fingerprint ridges and using the gradient and direction vector of each pixel point in the ridge line, the starting point, end point and intersection point in the ridge are determined, thereby realizing the extraction of ridge feature points, achieving accurate matching of fingerprint information, effectively improving the accuracy of the recognition process, and ensuring the security of the storage device.

[0021] Preferably, it also includes: performing weighted calculation on the first similarity and the second score according to the weight of fingerprint recognition and the weight of auricle recognition to obtain a comprehensive score, wherein the weight of fingerprint recognition and the weight of auricle recognition are determined by hierarchical analysis method; in response to the comprehensive score being less than a third set value, issuing an alarm and prompting for re-verification.

[0022] In a third aspect, the present invention further provides a computer-readable storage medium storing program instructions based on biometric recognition, which, when executed by a processor, implements the decryption method described in one or more of the foregoing embodiments.

[0023] The beneficial effects of the present invention are as follows: the present invention uses fingerprint plus human ear biometric identification technology for dual biometric identification, utilizing the stability and uniqueness of the human ear auricle, eliminating the risk of single-authentication fingerprints being copied, simulated or cracked, and greatly improving the security and reliability of using storage devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is a schematic diagram of the external structure of a storage device in a folded state according to an embodiment of the present invention; Figure 2 Schematic diagram of the external structure of the storage device in the use state according to the embodiment of the present invention; Figure 3 is a schematic diagram of the internal structure of a storage device in a folded state according to an embodiment of the present invention; Figure 4 A schematic diagram of the internal structure of a storage device in use according to an embodiment of the present invention; Figure 5 A circuit schematic diagram of a storage device in an embodiment of the present invention; Figure 6 Schematic diagram of data transmission direction of each module in a storage device in an embodiment of the present invention; Figure 7 is a circuit diagram of a CPU module in a processor in an embodiment of the present invention; Figure 8 is a circuit diagram of a fingerprint recognition module in an embodiment of the present invention; Fig. 9 is a circuit diagram of a human ear recognition module in an embodiment of the present invention; Fig.10 is a circuit diagram of a static random access memory in an embodiment of the present invention; Fig.11 is a circuit diagram of an indicator light in an embodiment of the present invention; Fig.12 is a circuit diagram of a power module in an embodiment of the present invention; Fig.13 A flowchart of a decryption method according to an embodiment of the present invention; Fig.14 Flow chart of a method for extracting fingerprint ridge feature points in an embodiment of the present invention; In the accompanying drawings, the list of components represented by each reference numeral is as follows: 1. Upper shell; 2. Lower shell; 3. USB hardware interface; 4. Foldable data cable; 5. CPU module; 6. Static random access memory; 7. Ear recognition module; 8. Fingerprint recognition module; 9. Ear scanning camera; 10. Indicator light; 11. Fingerprint collector. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0027] Figures 1 to 4 Schematic diagrams of storage devices in different states in an embodiment of the present invention are shown in FIG. According to the context of the present invention, the storage device in the present invention is a USB Key. In other embodiments, the storage device can also be used in other devices, such as a mobile hard disk.

[0028] In an embodiment of the present invention, a storage device based on biometric identification is provided, which adopts fingerprint and human ear biometric identification technology to realize dual authentication of fingerprint and human ear biometric identification, and do a good job of biometric identification of login security. The storage device based on biometric identification in the present invention includes a storage device body and a hardware interface, one end of the storage device body is provided with a groove for placing the hardware interface and a foldable data cable, one end of the foldable data cable is connected to the hardware interface, and the other end extends into the storage device body, and the hardware interface is folded and stored in the groove through the foldable data cable. The storage device also includes a memory, a fingerprint collector, an ear scanning device and a processor. The memory can adopt a static random access memory, the ear scanning device adopts an ear scanning camera, and the processor includes a CPU module. The storage device in the present invention takes a USB Key as an example, and the hardware interface is a USB hardware interface.

[0029] Specifically, Figure 1-Figure 4 As shown, the storage device body includes a shell composed of an upper shell 1 and a lower shell 2, and a CPU module 5, a static random access memory 6, a human ear recognition module 7, a fingerprint recognition module 8, an ear scanning camera 9, an indicator light 10 and a fingerprint collector 11 are installed inside the shell. In some embodiments, the shell structure composed of the upper shell 1 and the lower shell 2 can be a rectangular parallelepiped structure, or a cylindrical structure or other structures.

[0030] A groove is provided at one end of the shell, and the groove is used to place the USB hardware interface 3 and the foldable data cable 4. One end of the foldable data cable 4 is connected to the USB hardware interface 3, and the other end of the foldable data cable 4 extends into the interior of the shell and is connected to the CPU module 5. The USB hardware interface 3 is folded and stored in the groove through the foldable data cable 4.

[0031] The upper shell 1 is provided with holes at positions corresponding to the ear scanning camera 9, the indicator light 10 and the fingerprint collector 11, so as to expose the ear scanning camera 9, the indicator light 10 and the fingerprint collector 11, so as to facilitate the collection of biometric features and the bright and dark display of the indicator light 10. The static random access memory 6, the ear recognition module 7, the fingerprint recognition module 8, the indicator light 10 and the USB hardware interface 3 are all electrically connected to the CPU module 5, the ear scanning camera 9 is electrically connected to the ear recognition module 7, and the fingerprint collector 11 is electrically connected to the fingerprint recognition module 8.

[0032] In an application scenario, the fingerprint collector 11 can collect user fingerprint information by pressing the fingerprint. The ear scanning camera 9 collects user auricle information by scanning the human ear contour.

[0033] like Figure 5 As shown, the ear scanning camera 9 is used to collect the ear contour information of the target user (referred to as the auricle information) and upload it to the ear recognition module 7, and the fingerprint collector 11 is used to collect the fingerprint information of the target user and upload it to the fingerprint recognition module 8; the CPU module 5 is used to receive data from the ear recognition module 7 and the fingerprint recognition module 8 respectively, and compare the received data with the stored fingerprint data and auricle data, so as to realize biometric identification and identity authentication.

[0034] Specifically, the USB hardware interface 3 is an interface between the USB Key and the computer, and is used to establish a connection between the USB Key and the computer. The foldable data cable 4 facilitates the collection of fingerprint and auricle data. Identity authentication, digital signature, data encryption and decryption and other functions are mainly realized by connecting to a computer.

[0035] like Figure 6 As shown, the fingerprint collector 11 transmits the collected user fingerprint information to the fingerprint recognition module 8 through the SPI data channel. The fingerprint recognition module 8 recognizes and processes the transmitted user fingerprint information. The CPU module 5 sends a CS chip select signal to the fingerprint recognition module 8 through the socket. After receiving the CS chip select signal, the fingerprint recognition module 8 transmits the processed fingerprint data to the CPU module 5 through the SPI data channel. The CPU module 5 compares the transmitted fingerprint data with the stored data through a program. If the data are consistent, the fingerprint biometric recognition passes. If they are inconsistent, it fails.

[0036] The ear scanning camera 9 transmits the collected auricle information to the ear recognition module 7 through the SPI data channel. The ear recognition module 7 recognizes and processes the transmitted user auricle information. The CPU module 5 sends a CS1 chip select signal to the ear recognition module 7 through the socket. After receiving the CS1 chip select signal, the ear recognition module 7 transmits the processed auricle data to the CPU module 5 through the SPI data channel. The CPU module 5 compares the transmitted auricle data with the stored data through a program. If the data are consistent, the ear biometric recognition passes. If they are inconsistent, it fails.

[0037] like Figure 7 As shown, the CPU module 5 includes a CPU chip U3. The CPU chip U3 is a high-security chip that supports SM2, SM3, and SM4 cryptographic algorithms. The chip is equipped with a COS operating system. Identity confirmation is performed between the digital certificate stored on the storage device USB Key and the server to ensure secure data communication. It can realize the functions of secure storage of sensitive data, non-export of private keys, and signing and encryption completed inside the product's security chip.

[0038] Specifically, the CPU chip U3 can adopt the chip structure of model HS32U2-E. Pin description, MISO SPI: master mode input, slave mode output; MOSI: master mode output, slave mode input; SCK: serial clock; SS: slave mode select; HMISO: master mode input, slave mode output; HMOSI: master mode output, slave mode input; HSCK: serial clock; HSS: slave mode select; TXD: data output; RXD: data input; EBHN: send low byte control (I / O0-I / O7) signal; EBLN: send high byte control (I / O8-I / O15) signal; ECS0N: external memory chip select signal; ECS1N: external memory chip select signal; ECS2N: external memory chip select signal; ECS3N: external memory chip select signal; EREN: external memory read enable signal; EWEN: external memory write enable signal; ED15: External memory data bus; ED14: external memory data bus; ED13: external memory data bus; ED12: external memory data bus; ED11: external memory data bus; ED10: external memory data bus; ED9: external memory data bus; ED8: external memory data bus; ED7: external memory data bus; ED6: external memory data bus; ED5: external memory data bus; ED4: external memory data bus; ED3: external memory data bus; ED2: external memory data bus; ED1: external memory data bus; ED0: external memory data bus; USBVDD: 3.3V power supply; USBDM interface D- differential signal; USBDP interface D+ differential signal; USBGND signal ground; USBR USB interface external resistor signal; USBC USB interface external capacitor signal; VD33_1 is 3.3V power supply; VD33_2 is 3.3V power supply;3V power supply; GND_1 is signal ground; GND_2 is signal ground; GND_3 is signal ground; GND_4 is signal ground; CLKM is clock selection signal; EPM pin is working mode selection; SCCLK is grounded; SCDIO is not connected; SCRST is not connected; RESETN is external reset input signal; RSTO is reset output signal; EINT0 is external interrupt signal; EINT1 is external interrupt signal; EINT2 is external interrupt signal; XTAL is the output terminal of external crystal; EXTAL is the input terminal of external clock / external crystal; EA20 is external memory address bus; EA19 is external memory address bus; EA18 is external memory address bus; EA17 is external memory address bus; External memory address bus; EA16 external memory address bus; EA15 external memory address bus; EA14 external memory address bus; EA13 external memory address bus; EA12 external memory address bus; EA11 external memory address bus; EA10 external memory address bus; EA9 external memory address bus; EA8 external memory address bus; EA7 external memory address bus; EA6 external memory address bus; EA5 external memory address bus; EA4 external memory address bus; EA3 external memory address bus; EA2 external memory address bus; EA1 external memory address bus; EA0 external memory address bus; NC no connection. EA1-EA16 signals are connected to the address output pins A0-A15 of the static random access memory chip through the external memory address bus pins EA1-EA16 of the CPU chip U3. ED0-ED15 signals are connected to the data input / output pins IO0-IO15 of the static random access memory chip through the external memory data bus pins ED0-ED15 of the CPU chip U3. .

[0039] Power-on reset chip U4: Transmits external reset input signal through pin RESETN to ensure that CPU chip U3 is in reset state when powered on or off, and can be reset reliably.

[0040] Crystal oscillator: The output of the external crystal through the pin XTAL is connected to the input of the clock / external crystal provided by EXTAL to provide a frequency signal. For example, a 12MHz crystal oscillator can provide a clock signal.

[0041] USB socket J2: connected to the USBDM pin of the CPU chip U3 through the D- differential signal, and connected to the USBDP pin of the CPU chip U3 through the D+ differential signal.

[0042] like Figure 8As shown, the fingerprint recognition module 8 includes a fingerprint socket CN1, which recognizes and processes the transmitted user fingerprint information, obtains fingerprint ridge data, and extracts the feature points required for fingerprint recognition; wherein, the seventh pin of the fingerprint socket CN1 sends a CS chip select signal. The model of the fingerprint socket CN1 is FPC_CON12, the Pin3 pin of the fingerprint socket CN1 is connected to the clock signal, the Pin5 pin outputs the signal, the Pin6 pin inputs the signal, the Pin7 pin sends a CS chip select signal, the Pin8 pin receives the interrupt signal, and the Pin9 pin sends an interrupt reset signal. The fingerprint socket CN1 is connected to the Pin10, Pin6, Pin8, Pin9, Pin5, and Pin7 pins on the CPU chip U3 through the Pin3, Pin5, Pin6, Pin7, Pin8, and Pin9 pins, respectively, to realize SPI serial communication.

[0043] like Fig. 9 As shown, the human ear recognition module 7 includes a human ear recognition socket CN2, which digitally processes the transmitted user auricle information, calculates the auricle feature points, connects the auricle feature points, establishes an ear contour model, obtains auricle data, and achieves the auricle processing function; wherein, the seventh pin of the human ear recognition socket CN2 sends a CS1 chip select signal. The model of the human ear recognition socket CN2 is FPC_CON12, the Pin3 pin of the human ear recognition socket CN2 is connected to the clock signal, the Pin5 pin outputs the signal, the Pin6 pin inputs the signal, the Pin7 pin sends the CS1 chip select signal, the Pin8 pin receives the interrupt signal, and the Pin9 pin sends the interrupt reset signal. The human ear recognition module socket is connected to the Pin10, Pin6, Pin8, Pin14, Pin26, and Pin7 pins on the CPU chip U3 through the Pin3, Pin5, Pin6, Pin7, Pin8, and Pin9 respectively, to realize SPI serial communication.

[0044] like Fig.10As shown, the static random access memory 6 is a data memory (SRAM, Static Random-Access Memory) extended from the CPU module 5, which is used to store program running data. The model of the static random access memory 6 is IS61LV6416-10TL, and the pin description is: A0-A15 pins are address inputs, IO0-IO15 pins are data input / output, CE pin is chip enable input, OE pin is output enable input, WE pin is write enable input, LB pin is low byte control (I / O0-I / O7), UB pin is high byte control (I / O8-I / O15), NC is not connected, VDD pin is power supply, GND pin is connected to signal ground, EA1-EA16 signals are connected to the external memory address bus pins such as the EA1-EA16 pins of the CPU chip U3 through the address output pins such as A0-A15 of the static random access memory chip. The ED0-ED15 signals are connected to the external memory data bus pins such as the ED0-ED15 pins of the CPU chip U3 through the data input / output pins such as the IO0-IO15 pins of the static random access memory chip.

[0045] like Fig.11 As shown, the indicator light 10 includes a light-emitting diode D4, which is used to determine whether the smart card reader has read the certificate information stored in the storage device USB Key; after the storage device USB Key is plugged in, the light-emitting diode D4 is stably lit, indicating that the smart card reader has read the certificate information of the storage device USB Key; after the storage device USB Key is plugged in, the light-emitting diode D4 is not lit and there is no reaction, indicating that the smart card reader has not read the certificate information of the storage device USB Key. The indicator light 10 is connected to the 3.3V voltage and connected to the Pin13 SS pin of the CPU chip U3. The Pin13 SS pin provides a high frequency, which reaches the light-emitting diode D4 through the resistor R8, and the LED lamp emits light.

[0046] like Fig.12 As shown, it also includes a power module, which includes a power chip U1. After the storage device is plugged into the power supply, a 5V voltage is input, and after passing through the power chip U1, a 3.3V voltage is output to power the CPU module 5, the static random access memory 6, the ear recognition module 7, the fingerprint recognition module 8 and the indicator light 10. The model of the power chip U1 is CL9193A33L5M, the Pin1 pin VIN is connected to the 5V input voltage, the Pin2 pin GND is connected to the signal ground, the Pin3 pin VEN is the power supply enable, the Pin4 pin NC is an empty pin, and the Pin5 pin VOUT outputs a 3V voltage.

[0047] It should be noted that the above embodiments only provide exemplary compositions of storage devices based on biometric identification, and those skilled in the art may also select chips of other types according to actual needs.

[0048] Based on the composition structure of the above storage device, the present invention also provides a decryption method of the storage device based on biometric identification, such as Fig.13 As shown, the following steps are included: In step S1301, the fingerprint information and auricle information of the target user are obtained. Since the above content has described in detail the method of obtaining the fingerprint information and auricle information of the target user, it will not be repeated here.

[0049] At step S1302, fingerprint ridge data is extracted from the fingerprint information, and the fingerprint ridge data is compared with the fingerprint data pre-stored in the memory to determine whether the fingerprint information matches the pre-stored fingerprint data, wherein the comparison process calculates a first similarity between feature points in the fingerprint information and feature points in the fingerprint data, and determines that the fingerprint information matches the pre-stored fingerprint data when the first similarity is greater than a first set value.

[0050] In some embodiments, fingerprint ridge data is extracted from the fingerprint information of the target user to extract fingerprint ridge feature points required for fingerprint identification. A first similarity between the fingerprint ridge feature points and feature points of pre-stored fingerprint data is calculated. In response to the first similarity being greater than a first set value, it is determined that the fingerprint information matches the pre-stored fingerprint data.

[0051] In step S1303, an ear contour model to be identified is constructed based on the auricle information, and a feature vector corresponding to the ear contour model is compared with an auricle feature vector corresponding to the pre-stored auricle data to determine whether the auricle information matches the pre-stored auricle data.

[0052] In some embodiments, Harris corner detection is used to determine key feature points in the auricle information, and the detected key feature points are connected to form the contour line of the auricle. The connected contour line is smoothed, and an ear contour model of the auricle is established based on the contour line. A second similarity between a feature vector corresponding to the auricle contour model and an auricle feature vector corresponding to the pre-stored auricle data is calculated. In response to the second similarity being greater than a second set value, it is determined that the auricle information matches the pre-stored auricle data.

[0053] The similarity calculation can be performed by, for example, calculating the Euclidean distance between feature points or feature vectors, cosine similarity, etc. Harris corner detection to determine key feature points in auricle information is a prior art and will not be described again here.

[0054] In step S1304, in response to the fingerprint information matching the pre-stored fingerprint data and the auricle information matching the pre-stored auricle data, the target user is granted access rights to the storage device.

[0055] Furthermore, the present invention also provides a method for extracting fingerprint ridge feature points. When extracting fingerprint ridge feature points, the background area and the effective fingerprint area in the fingerprint information of the target user are first segmented, and then the fingerprint ridges in the effective fingerprint area are thinned into single-pixel-wide lines using a thinning algorithm, and finally the starting point, end point and bifurcation point of the ridge in the line are determined as ridge feature points.

[0056] When determining the ridge feature points based on the above single-pixel-width lines, the following method can be used: Fig.14 Specifically, at step S1401, for the line with a single pixel width, a rectangular frame is set according to a set size with any point in the line as the center point, and the gradient of each point in the line part within the rectangular frame is calculated.

[0057] In step S1402, points with gradient values ​​greater than zero are taken as reserved points, and the variance of the gradients of the reserved points in the rectangular frame is calculated, wherein the points with variances greater than a first threshold are taken as bifurcation points.

[0058] In step S1403, the sum of the direction vectors between each reserved point in the rectangular frame and the center point is calculated, and the point where the sum of the direction vectors is greater than a second threshold is used as the starting point and / or end point of the ridge line.

[0059] Next, matching will be performed based on the determined ridge feature points to achieve biometric recognition.

[0060] In one embodiment, the fingerprint information verification may be performed first, and then the auricle information verification may be performed after the verification is successful.

[0061] For example, step 1: collect the target user's fingerprint information and ear contour information. Taking the USB Key verification process as an example, for fingerprint data, the fingerprint collector 11 in the USB Key can be used to collect it. For human ear auricle data, the ear camera scanning module in the USB Key can be used to collect it.

[0062] Step 2: Verify the identity of the target user based on the fingerprint information of the target user. If the verification is successful, proceed to step 3, otherwise return to step 1.

[0063] Step 3: Verify the identity of the target user again based on the ear contour information of the target user. If the verification is successful, the target user obtains access rights to the storage device. Otherwise, return to step 1.

[0064] In another embodiment, fingerprint information verification and auricle information verification may be performed separately, and a comprehensive verification may be achieved using the comprehensive score of the two.

[0065] For example, step 1: collect fingerprint information and ear contour information of the target user.

[0066] Step 2: Calculate a first similarity based on the fingerprint information of the target user, and calculate a second similarity based on the auricle information of the target user.

[0067] Step 3: Perform weighted calculation on the first similarity and the second score according to the weight of fingerprint recognition and the weight of auricle recognition to obtain a comprehensive score, wherein the weight of fingerprint recognition and the weight of auricle recognition are determined by hierarchical analysis method.

[0068] Step 4: In response to the comprehensive score being less than the third set value, an alarm is issued and a re-verification prompt is given.

[0069] It should be noted that before verification is implemented, the sensed fingerprint data and auricle data need to be entered in advance in the corresponding storage device. The collected fingerprint and human ear auricle data are stored in a USB Key, and access rights and encryption protection are set; users need to perform fingerprint biometric verification first, and then perform human ear biometric verification after passing the verification. Only when both biometric verifications are passed can the user obtain access rights; fingerprint and human ear auricle data are updated regularly to ensure the security and accuracy of the system.

[0070] Specifically, first, the user's fingerprint and ear data are collected and stored in the USB Key. The fingerprint collector 11 and the ear camera scanning device are needed to collect information, and then the user's fingerprint and auricle features are identified and processed, and the processed fingerprint data and auricle data are stored in the USB Key.

[0071] Second, the data processing flow of fingerprint and ear recognition is designed, which can be implemented in the fingerprint recognition module 8 and the ear recognition module 7. De-noising and smoothing operations are performed on the input fingerprint data and auricle data to reduce noise interference.

[0072] Third, the cryptographic CPU chip runs on the USB Key for identity authentication. When the user inserts the USB Key and authenticates, the device will first perform fingerprint biometrics to verify whether the user's identity is correct. If the authentication is successful, the human ear biometrics will be further confirmed to confirm the user's identity. Only when both biometric authentications are passed can the user obtain access rights.

[0073] Fourth, for unauthorized users, the system will deny their access requests and record relevant information for administrators to conduct auditing and management.

[0074] Fifth, fingerprint and ear data are updated regularly to ensure the security and accuracy of the system. Users can update their identity information by re-collecting fingerprint and ear data.

[0075] It should be noted that the biometric storage device provided by the present invention, i.e., the USB Key of fingerprint and ear recognition, has both sovereign and subordinate roles, and its main purpose is to protect the security of the system and data privacy, and ensure that only authorized users can obtain access rights.

[0076] Sovereignty: The USB Key itself has the ability to authenticate users, that is, the ability to determine whether the user is legitimate. The USB Key authenticates the user through the built-in fingerprint and ear recognition algorithms, and decides whether to grant access rights based on the verification results. Therefore, the USB Key is a major component of the entire system and has the ultimate authentication rights.

[0077] Slave authority: refers to the role of other systems or software used in conjunction with it in the identity authentication process. For example, when using a fingerprint plus ear recognition USB Key in an enterprise internal network, the device needs to be used in conjunction with a related identity authentication system. At this point, the USB Key becomes a slave authority of the system, and its main function is to provide reliable identity authentication results so that other systems can perform further authorization and access management.

[0078] In order to protect the security and data privacy of the system, ensure that only authorized users can obtain access rights, and do a good job in login security biometric identification. The fingerprint USB Key currently available on the market has technical risks. The present invention is a USB Key technology based on fingerprint plus human ear biometric identification. This technology combines fingerprint and human ear biometric identification technology, uses human ear biometric identification technology as the second layer of biometric identification means, realizes dual biometric identification, and uses the stability and uniqueness of the human ear auricle to eliminate the risk of single-authentication fingerprints being copied, simulated or cracked, thereby greatly improving the security and reliability of using USB Key. At the same time, this technology uses a wireless USB interface connection, which is convenient for users to use and can be widely used in various occasions, such as system login, network transactions, etc. Through the application of this technology, the security of important information and data of individuals and enterprises can be effectively protected.

[0079] In the embodiment of the present invention, the USB Key with fingerprint biometric recognition function has similar functions to the present invention. Such a USB Key uses fingerprint recognition technology, based on the standard USB Key, and uses the principle that fingerprint is unique and irreplaceable, and has a built-in hardware fingerprint recognition system to perform biometric recognition. The present invention adds human ear biometric recognition technology to the fingerprint biometric recognition technology. The collection, storage and verification of fingerprints and auricles are completely performed in the USB Key, realizing dual biometric recognition and high security.

[0080] In the embodiment of the present invention, since the human ear biometric identification function is added on the basis of the fingerprint USB Key, the dual biometric identification of fingerprint plus human ear biometric identification technology is realized, and the possibility of two people having the same biometric data is small. Therefore, the risk of fingerprint identification technology itself being copied, simulated or cracked is solved, thereby improving the security of using the USB Key.

[0081] In another aspect of the present invention, a computer-readable storage medium is provided, which stores program instructions based on biometric identification. When the program instructions are executed by a processor, the aforementioned decryption method of the storage device based on biometric identification is implemented.

[0082] The computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present disclosure may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0083] In addition, the terms "first" or "second" used in this specification to refer to numbers or ordinals are only used for descriptive purposes and cannot be understood as explicitly or implicitly indicating relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this specification, the meaning of "plurality" is at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0084] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A storage device based on biometric identification, comprising a storage device body and a hardware interface, It is characterized in that One end of the storage device body is provided with a groove for placing a hardware interface and a foldable data cable, one end of the foldable data cable is connected to the hardware interface, and the other end extends into the storage device body, and the hardware interface is folded and stored in the groove through the foldable data cable, and the storage device further includes: A memory, which is used to pre-store the collected fingerprint data and auricle data of the target user; A fingerprint collector is provided on the storage device body and is used to collect fingerprint information of the target user; An ear scanning device, which is disposed on the storage device body and is used to collect auricle information of the target user; A processor is connected to the fingerprint collector, the ear scanning device, the foldable data cable and the memory, and is used to obtain the fingerprint information and auricle information of the target user, and compare the fingerprint information with the fingerprint data pre-stored in the memory, and compare the auricle information with the pre-stored auricle data, and after the comparison is successful, the target user is granted access to the storage device, wherein the comparison of the fingerprint information with the fingerprint data pre-stored in the memory includes: calculating a first similarity between a feature point in the fingerprint information and a feature point in the fingerprint data, and determining that the fingerprint information matches the pre-stored fingerprint data when the first similarity is greater than a first set value; comparing the auricle information with the pre-stored auricle data includes: Harris corner detection is used to determine the key feature points in the auricle information, and the detected key feature points are connected to form the contour line of the auricle; Smoothing the connected contour lines, and establishing an ear contour model of the auricle according to the contour lines; Calculating a second similarity between a feature vector corresponding to the auricle contour model and an auricle feature vector corresponding to the pre-stored auricle data; In response to the second similarity being greater than the second set value, it is determined that the auricle information matches the pre-stored auricle data.

2. The biometric storage device according to claim 1, It is characterized in that The processor is connected to the fingerprint collector through the fingerprint recognition module, and is used to extract fingerprint ridge data from the fingerprint information and extract the feature points required for fingerprint recognition; the processor is connected to the ear scanning device through the human ear recognition module, and is used to extract auricle feature points from auricle information and connect the auricle feature points to establish an ear contour model.

3. The biometric-based storage device according to claim 1, It is characterized in that The storage device further includes an indicator light, which is connected to the processor and is used to determine whether the certificate information stored in the storage device is read according to a lighting condition.

4. A decryption method for a storage device based on biometric identification, applied to the storage device based on biometric identification according to any one of claims 1 to 3, It is characterized in that include: Obtain the target user's fingerprint information and auricle information; Extracting fingerprint ridge data from the fingerprint information, and comparing the fingerprint ridge data with the fingerprint data pre-stored in the memory to determine whether the fingerprint information matches the pre-stored fingerprint data, wherein the comparison process is achieved by calculating the similarity between the feature points in the fingerprint information and the feature points in the fingerprint data; Constructing an ear contour model to be identified according to the auricle information, and comparing a feature vector corresponding to the ear contour model with an auricle feature vector corresponding to pre-stored auricle data to determine whether the auricle information matches the pre-stored auricle data; In response to the fingerprint information matching the pre-stored fingerprint data and the auricle information matching the pre-stored auricle data, the target user is granted access rights to the storage device.

5. The decryption method of a storage device based on biometric identification according to claim 4, It is characterized in that Compare the fingerprint information with the fingerprint data pre-stored in the memory, including: Extracting fingerprint ridge data from the target user's fingerprint information to extract fingerprint ridge feature points required for fingerprint recognition; Calculating a first similarity between a fingerprint ridge feature point and a feature point of pre-stored fingerprint data; In response to the first similarity being greater than the first set value, it is determined that the fingerprint information matches the pre-stored fingerprint data.

6. The decryption method of a storage device based on biometric identification according to claim 5, It is characterized in that Extract fingerprint ridge data from the target user's fingerprint information to extract fingerprint ridge feature points required for fingerprint recognition, including: Segment the background area and the effective fingerprint area in the fingerprint information of the target user; A thinning algorithm is used to thin the fingerprint ridges in the effective fingerprint area into single-pixel-wide lines; The starting point, end point and bifurcation point of the ridge in the line are determined as the ridge feature points.

7. The decryption method of a storage device based on biometric identification according to claim 6, It is characterized in that Determine the starting point, end point and bifurcation point of the ridge line in the line as the ridge feature points, including: For the line with a single pixel width, taking any point in the line as the center point, setting a rectangular frame according to a set size, and calculating the gradient of each point in the line portion within the rectangular frame; The points whose gradient values ​​are greater than zero are taken as reserved points, and the variance of the gradients of the reserved points in the rectangular frame is calculated, wherein the points whose variances are greater than the first threshold are taken as bifurcation points; The sum of the direction vectors between each reserved point in the rectangular frame and the center point is calculated, and the point where the sum of the direction vectors is greater than the second threshold is used as the starting point and / or end point of the ridge line.

8. The decryption method of a storage device based on biometric identification according to claim 4, It is characterized in that Also includes: The first similarity and the second score are weighted and calculated according to the weight of fingerprint recognition and the weight of auricle recognition to obtain a comprehensive score, wherein the weight of fingerprint recognition and the weight of auricle recognition are determined by a hierarchical analysis method; In response to the comprehensive score being less than the third set value, an alarm is issued and a re-verification prompt is given.

9. A computer-readable storage medium, It is characterized in that It stores program instructions based on biometric identification. When the program instructions are executed by a processor, the decryption method of the storage device based on biometric identification according to any one of claims 4 to 8 is implemented.

Images