Embedded system, method and storage medium for processing fingerprint information

Abstract

The present disclosure discloses an embedded system, a method and a non-transitory computer readable storage medium for processing fingerprint information, the embedded system comprising: a processor configured to determine compressible information and non-compressible information in registered fingerprint information, and to perform compression processing on the compressible information; a first storage unit configured to provide an operation space for the processor to perform the compression processing; and a second storage unit configured to store compressed information obtained by compressing the compressible information and the non-compressible information. According to the embedded system of the present disclosure, the operation space required for compression processing can be reduced, and the calculation time of compression operation can be reduced.

Description

TECHNICAL FIELD

[0001] The present disclosure relates generally to the field of fingerprint recognition. More specifically, the present disclosure relates to an embedded system, a method and a non-transitory computer readable storage medium for processing fingerprint information. BACKGROUND

[0002] With the continuous development of information technology, the application range of fingerprint recognition technology is becoming wider and wider. When the fingerprint recognition technology is applied to a mobile platform (such as a mobile phone platform, etc.), it is usually necessary to use the processor and the memory in the mobile platform to perform the operation of fingerprint recognition. However, since a large number of application programs and user permissions are usually installed in the mobile platform, there is a security risk of being attacked in the process of fingerprint recognition based on the mobile platform, which may result in a decrease in the reliability of the fingerprint recognition result.

[0003] Compared with the fingerprint recognition using the mobile phone platform, the embedded system can have an independent processor and storage space to perform independent operation without sharing the processor and the memory in the mobile platform, so if the embedded system can be used for fingerprint recognition, it will be beneficial to improve the security of fingerprint recognition. However, the performance of the processor, the storage capacity of the storage unit and the operation space in the embedded system are much smaller than those in the mobile platform, so it is difficult for the embedded system to apply the fingerprint recognition algorithm in the mobile platform.

[0004] Therefore, there is an urgent need to provide a solution of an embedded system capable of processing fingerprint information. SUMMARY

[0005] In order to at least solve one or more technical problems as mentioned above, the present disclosure proposes an embedded system, a method and a non-transitory computer readable storage medium for processing fingerprint information in various aspects.

[0006] In a first aspect, the present disclosure provides an embedded system for processing fingerprint information, comprising: a processor configured to determine compressible information and non-compressible information in registered fingerprint information, and to perform compression processing on the compressible information; a first storage unit configured to provide an operation space for the processor to perform the compression processing; and a second storage unit configured to store the compressed information obtained by compressing the compressible information and the non-compressible information.

[0007] In some embodiments, the registered fingerprint information comprises feature information of feature points from one or more registered fingerprint images; the embedded system further comprises a fingerprint sensor configured to acquire the registered fingerprint images; and the processor is further configured to determine the compressible information and the non-compressible information in the feature information of each feature point according to the category of the feature information of each feature point in each registered fingerprint image.

[0008] In some embodiments, the processor is further configured to: store the compressible information of the plurality of feature points in the first storage unit in a continuous manner, and perform overall compression on the compressible information stored in the first storage unit in a continuous manner; and / or store the non-compressible information of the plurality of feature points in the second storage unit in a continuous manner.

[0009] In some embodiments, the processor is further configured to: store the compressible information of the plurality of feature points in each of the registered fingerprint images or the compressible information of the plurality of feature points in the plurality of registered fingerprint images in the first storage unit in a continuous manner, and perform overall compression on the compressible information stored in the first storage unit in a continuous manner; and / or store the non-compressible information of the plurality of feature points in each of the registered fingerprint images or the non-compressible information of the plurality of feature points in the plurality of registered fingerprint images in the second storage unit in a continuous manner.

[0010] In some embodiments, the processor is further configured to: store the compressible information of all the feature points in each of the registered fingerprint images or the compressible information of all the feature points in the plurality of registered fingerprint images in the first storage unit in a continuous manner; and / or store the non-compressible information of all the feature points in each of the registered fingerprint images or the non-compressible information of all the feature points in the plurality of registered fingerprint images in the second storage unit in a continuous manner.

[0011] In some embodiments, the fingerprint sensor is further configured to acquire a to-be-compared fingerprint image; and the processor is further configured to: perform decompression on the compressed information in the first storage unit to obtain decompressed information; and perform feature comparison on the to-be-compared fingerprint image according to the decompressed information and the non-compressible information.

[0012] In some embodiments, in performing feature comparison according to the decompressed information and the non-compressible information, the processor is further configured to: according to a category of to-be-compared feature information in the to-be-compared fingerprint image, read the decompressed information of the corresponding category stored in the first storage unit, and / or read the non-compressible information of the corresponding category stored in the second storage unit, so as to compare the to-be-compared fingerprint image with the corresponding category feature information of each feature point in the registered fingerprint image.

[0013] In some embodiments, in response to the non-compressible information being stored in the second storage unit in a continuous manner, the processor is further configured to use a hardware accelerator to read the non-compressible information of the corresponding category.

[0014] In some embodiments, the non-compressed information comprises surrounding information of the feature point; and / or the compressible information comprises at least one of the following categories of feature information: category information of the feature point; position information of the feature point; and direction information of the feature point.

[0015] In some other embodiments, the first storage unit comprises a random access memory, and the second storage unit comprises a flash memory.

[0016] In a second aspect, the present disclosure provides a method for processing fingerprint information, comprising: determining compressible information and non-compressed information in registered fingerprint information; and performing compression processing on the compressible information to obtain compressed compressible information.

[0017] In some embodiments, the registered fingerprint information comprises feature information of feature points from one or more registered fingerprint images; and determining compressible information and non-compressed information in registered fingerprint information comprises: determining the compressible information and the non-compressed information in the feature information of each feature point in each registered fingerprint image according to the category of the feature information of each feature point in each registered fingerprint image.

[0018] In some other embodiments, the method further comprises: continuously storing the compressible information of a plurality of feature points for overall compression of the continuously stored compressible information; and / or continuously storing the non-compressed information of a plurality of feature points.

[0019] In some embodiments, continuously storing the compressible information of a plurality of feature points comprises: continuously storing the compressible information of a plurality of feature points in each registered fingerprint image or the compressible information of a plurality of feature points in a plurality of registered fingerprint images; and / or continuously storing the non-compressed information of a plurality of feature points comprises: continuously storing the non-compressed information of a plurality of feature points in each registered fingerprint image or the non-compressed information of a plurality of feature points in a plurality of registered fingerprint images.

[0020] In yet some other embodiments, the method further comprises: continuously storing the compressible information of all feature points in each registered fingerprint image or the compressible information of all feature points in a plurality of registered fingerprint images; and / or continuously storing the non-compressed information of all feature points in each registered fingerprint image or the non-compressed information of all feature points in a plurality of registered fingerprint images.

[0021] In some embodiments, the method further comprises: performing decompression processing on the compressed information to obtain decompressed information; and performing feature comparison on a to-be-compared fingerprint image according to the decompressed information and the non-compressed information.

[0022] In some embodiments, the feature comparison according to the decompressed information and the non-compressed information comprises: reading the decompressed information of a corresponding category according to a category of the to-be-compared feature information in the to-be-compared fingerprint image, and / or reading the non-compressed information of the corresponding category, so as to compare the to-be-compared fingerprint image with the corresponding category feature information of each feature point in the registered fingerprint image.

[0023] In yet some embodiments, the reading of the non-compressed information of the corresponding category comprises: in response to the non-compressed information being stored in a continuous storage manner, reading the non-compressed information of the corresponding category using a hardware accelerator.

[0024] In some embodiments, the non-compressed information comprises surrounding information of the feature point; and / or the compressible information comprises at least one of the following categories of feature information: category information of the feature point; position information of the feature point; and direction information of the feature point.

[0025] In a third aspect, the present disclosure provides a non-transitory computer-readable storage medium storing a program for processing fingerprint information, which, when executed by a processor, performs the method according to any one of the second aspect of the present disclosure.

[0026] Through the technical solution for processing fingerprint information as provided above, an embedded system is provided in the solution of the present disclosure, by determining the compressible information and the non-compressed information in the registered fingerprint information, and only the compressible information can be compressed without compressing the non-compressed information, not only the storage space required by the registered fingerprint information can be reduced by storing the compressed information in the second storage unit, but also the operation space required by the compression processing and the calculation time of the compression operation can be reduced by reducing the data amount of the compression processing.

[0027] Further, in some embodiments, the compressible information of a plurality of feature points can be stored continuously so as to be compressed as a whole, which is beneficial to improve the compression efficiency. In some other embodiments, the non-compressed information of a plurality of feature points can be stored continuously so as to be read by a hardware accelerator, which is beneficial to improve the reading rate and save the calculation time. BRIEF DESCRIPTION OF DRAWINGS

[0028] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0029] Figure 1 is a schematic block diagram illustrating an embedded system;

[0030] Figure 2 is a schematic block diagram illustrating an embedded system for processing fingerprint information according to an embodiment of the present disclosure;

[0031] Figure 3 is a schematic block diagram illustrating an embedded system according to another embodiment of the present disclosure;

[0032] Figure 4 is a schematic diagram illustrating splitting and storing of registered fingerprint information according to an embodiment of the present disclosure;

[0033] Figure 5 is a schematic diagram illustrating a matching process in the embedded system according to an embodiment of the present disclosure; and

[0034] Figure 6 is a flowchart of a method of processing fingerprint information according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of, rather than all of, the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative effort fall within the scope of the present disclosure.

[0036] It should be understood that the terms "comprise" and "include" used in the specification and claims of the present disclosure indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0037] It should also be understood that the terms used in the specification of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. As used in the specification and claims of the present disclosure, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should be further understood that the term "and / or" used in the specification and claims of the present disclosure means one or more of the associated listed items as well as all possible combinations of the items.

[0038] As used in the specification and claims, the term "if' can be interpreted as meaning "when," or "upon," or "in response to a determination," or "in response to a detection" depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted as meaning "upon a determination" or "in response to a determination" or "upon a detection [of the described condition or event]" or "in response to a detection [of the described condition or event]" depending on the context.

[0039] The present inventor found that, taking a commercially available product as an example, the operation space of the memory used by the mobile phone platform can reach 1024 Kbytes, the frequency of the processor can reach 1.2 GHz, and the storage capacity of the storage unit used for storing data can reach 280 Kbytes; the operation space of the memory used by the embedded platform is only 256 Kbytes, the frequency of the processor is only 200 MHz, and the storage capacity of the storage unit capable of storing data is only 20 Kbytes. In comparison, the hardware performance of the mobile phone platform is several times higher than that of the embedded system. Limited by the performance of the embedded platform, only low-computing operations and storage of less data can be performed.

[0040] Based on this, in the embedded system, the fingerprint registration data used as the fingerprint comparison reference can be compressed and then stored in the storage unit in the embedded system, so as to reduce the storage space required by the fingerprint registration data. The fingerprint registration data can include fingerprint feature information from one or more registration fingerprint images. When fingerprint comparison is needed, the compressed data needs to be taken out from the storage unit, decompressed, and then used for comparison operation with the to-be-compared fingerprint data, so as to determine whether the to-be-compared fingerprint data passes the verification. The to-be-compared fingerprint data can include fingerprint feature information of a to-be-compared fingerprint image. For ease of understanding, the following will be described in combination with Figure 1 .

[0041] Figure 1 is a schematic block diagram showing an embedded system. As Figure 1As shown in FIG. 1, the embedded system can include a memory 110, a storage unit 120, and a processor (not shown), wherein the storage unit 120 can be configured to store compressed fingerprint registration data. In the operation space of the memory 110, the operation space consumed by the following is mainly consumed: the generation algorithm 111 for generating the received to-be-compared fingerprint image into to-be-compared fingerprint data 112; the space occupied by the generated to-be-compared fingerprint data 112; the operation space consumed by the compression of the fingerprint registration data or the decompression of the compressed data stored in the storage unit 120, i.e., the operation space consumed by the processor executing the compression / decompression algorithm 113; the space occupied by the loaded decompressed fingerprint registration data 114; and the operation space of the comparison algorithm 115 running when the fingerprint registration data 114 and the to-be-compared fingerprint data 112 are compared.

[0042] Based on the above findings, the present disclosure provides a brand-new solution by distinguishing the compressible information and the non-compressible information in the registration fingerprint information to at least save the operation space and operation time consumed by executing the compression / decompression algorithm. The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0043] Figure 2 FIG. 1 is a schematic block diagram showing an embedded system for processing fingerprint information according to an embodiment of the present disclosure. As shown in FIG. 1, the embedded system for processing fingerprint information 100 can include a processor 110, a first storage unit 120, and a second storage unit 130, wherein the processor 110 can be configured to: determine compressible information and non-compressible information in registration fingerprint information; and perform compression processing on the compressible information; the first storage unit 120 can be configured to provide operation space for the processor 110 to perform the compression processing; and the second storage unit 130 can be configured to store compressed information obtained by compressing the compressible information and the non-compressible information. Figure 2

[0044] In some embodiments, the processor 210 can include a micro control unit (MCU) or the like. In other embodiments, the registration fingerprint information can include one or more registration fingerprint images. In yet other embodiments, the registration fingerprint information can include feature information (or fingerprint feature information) from one or more registration fingerprint images. The feature information can be extracted from the registration fingerprint images by, for example, the generation algorithm 111 shown in FIG. 1. The generation algorithm can be implemented by using existing algorithms such as Haar-like features algorithm or future implementable algorithms, which are not limited herein. Figure 1

[0045] ​​The compressible information described above can include information with a relatively high compression ratio. The non-compressible information described above can include information with a relatively low compression ratio and / or information that is not compressible. Information that is not compressible refers to information that cannot reduce the data capacity after compression. Generally, the higher the statistical similarity, the higher the repetition rate and the stronger the regularity of the information, the higher the compression ratio. Therefore, the division of the compressible information and the non-compressible information can be performed according to the statistical characteristics of the registered fingerprint information.

[0046] In the embedded system 200 according to the embodiments of the present disclosure, the processor 210 can perform compression processing only on the compressible information in the first storage unit 220 without performing compression processing on the non-compressible information. Since the amount of calculation consumed in performing compression processing increases with the amount of information before compression regardless of whether the information is suitable for compression, and the calculation time consumed in performing compression processing is also related to the amount of information before compression, compared to compressing all of the fingerprint registration information, performing compression processing only on the compressible information in the registered fingerprint information according to the embodiments of the present disclosure can effectively reduce the amount of data to be compressed, thereby reducing the calculation time and the amount of calculation space consumed by the processor 210 in performing compression processing in the first storage unit 220. In some embodiments, considering the requirements for the integrity and correctness of the fingerprint information, the compression processing can be non-destructive compression (or lossless compression), such as non-destructive compression processing performed using compression algorithms such as Huffman coding or Arithmetic coding. In other embodiments, the first storage unit 220 can include, for example, a random access memory, and the second storage unit 230 can include, for example, a flash memory.

[0047] The above description is combined with Figure 2 The embedded system according to the embodiments of the present disclosure is described exemplarily. It can be understood that the above description is exemplary and not limiting, for example, the embedded system according to the embodiments of the present disclosure can not be limited to only including a processor, a first storage unit and a second storage unit, but can also include other devices, which will be described below in combination with Figure 3 The above description is combined with

[0048] Figure 3 is a schematic block diagram showing an embedded system according to another embodiment of the present disclosure. As Figure 3As shown in FIG. 3, the embedded system 300 can include a processor 210, a first storage unit 220, a second storage unit 230, and a fingerprint sensor 310, wherein the fingerprint sensor 310 can be configured to collect a registered fingerprint image. In some embodiments, the registered fingerprint information can include feature information of feature points from one or more registered fingerprint images, and the processor 210 can be further configured to determine compressible information and non-compressible information in the feature information of each feature point according to a category of the feature information of each feature point in each registered fingerprint image.

[0049] The feature points described above are feature points of a fingerprint in a registered fingerprint image, or can be referred to as feature points of a fingerprint ridge. Each registered fingerprint image can be composed of a group of feature points. In some embodiments, the category of the feature information can include one or more of, for example, category information of the feature points, position information of the feature points, direction information of the feature points, and surrounding information of the feature points. In some embodiments, the category information of the feature points can include information that the feature points belong to a peak category or a valley category. In other embodiments, the position information of the feature points can include absolute position information and / or relative position information of the feature points in the registered fingerprint image. In yet other embodiments, the absolute position information can include coordinate position information, such as horizontal coordinate and vertical coordinate. In some embodiments, the relative position information can include relative position information of a current feature point relative to other feature points.

[0050] In some embodiments, the direction information of the feature points can include gradient direction information of the feature points. In other embodiments, the direction information of the feature points can have a value range of 0°-359°. In yet other embodiments, the surrounding information of the feature points can include description information of the surroundings of the feature points. For example, in some embodiments, the surrounding information of the feature points can include gray scale distribution information of the surroundings of the feature points.

[0051] According to the statistical characteristics of the above categories, it can be determined that the feature information of each category belongs to compressible information or non-compressible information. For example, the category information of the feature points, the position information of the feature points, and the direction information of the feature points all belong to information with a small value range and a small number of possible values, have a limited number of options, and have high repeatability. For example, the category information of the feature points generally includes two categories, the position information of the feature points generally includes a limited number of coordinate values (for example, 200 X-axis coordinates and 200 Y-axis coordinates), and the direction information of the feature points generally includes 360 direction information represented by integers, all of which have statistical regularity. Therefore, in some embodiments, the compressible information can include at least one of the following categories of feature information: the category information of the feature points; the position information of the feature points; and the direction information of the feature points.

[0052] For example, the surrounding information of a feature point is different for each feature point. Suppose the surrounding information describes the grayscale contrast between the feature point itself and its four surrounding directions. Since the grayscale contrast between each feature point and one of its surrounding directions will have two possibilities, each feature point will have 2... 4 There are 2 possible grayscale contrast relationships; if the surrounding information describes the grayscale contrast relationship with the surrounding twelve directions, then each feature point will have 2 12 There are several possible grayscale contrast relationships. Alternatively, assuming the surrounding information describes the grayscale information in four directions around the feature point, and when each grayscale information is recorded using 8 bits, then each grayscale information can have 2... 8 If there are two ways of representation, then each feature point will have 2 12 There are 2 possible grayscale distributions, but when describing twelve directions, each feature point will have 2 20 There are numerous possible grayscale distributions, and the information options increase exponentially. The more detailed the description of the surrounding information, the more combinations of information there are, potentially reaching tens of thousands. This amount of information is enormous and statistically lacks clear regularity and repetition, resulting in low compression ratios, or even incompressibility. Therefore, in some embodiments, the surrounding information of the feature point can be defined as uncompressible information for segmentation and differentiation from the aforementioned compressible information.

[0053] The above combination Figure 3 An embedded system and a method for determining compressible and uncompressible information according to another embodiment of this disclosure have been described exemplarily. It is understood that the above description is exemplary and not limiting. For example, uncompressible information may not be limited to only including information surrounding the feature points; in other embodiments, it may also include, for example, header information. The header information may include descriptive information such as the number of feature points in the registered fingerprint image and the default information length of each category of feature information. In some embodiments, the processor 210 may determine the category of feature information for each feature point based on the number of feature points provided by the header information and the default information length of each category of feature information. Since the header information contains relatively little information, and uncompressed header information allows the processor to easily determine the number of feature points and other information to be obtained after decompression during decompression processing, it can be determined as uncompressible information in the registered fingerprint information to save the cost of compression operations.

[0054] Figure 4 This is a schematic diagram illustrating the segmentation and storage of registered fingerprint information according to an embodiment of this disclosure. Figure 4As shown in FIG. 4, the processor in the embedded system according to the embodiments of the present disclosure can be further configured to: store the compressible information of the plurality of feature points continuously in the first storage unit, and perform overall compression on the continuously stored compressible information in the first storage unit; and / or store the non-compressible information of the plurality of feature points continuously in the second storage unit.

[0055] Specifically, as shown in FIG. 5, each feature point in each registered fingerprint image 410 can be first divided into compressible information and non-compressible information, for example, feature point 10 can be divided into compressible information 11 and non-compressible information 12, feature point 20 can be divided into compressible information 21 and non-compressible information 22, and so on, and feature point n0 can be divided into compressible information n1 and non-compressible information n2. Feature point n0 represents the nth feature point in the registered fingerprint image 410, and the value of n can be determined according to the number of feature points in the registered fingerprint image in the actual scene. Figure 4

[0056] Then, the plurality of compressible information 11, 21, … n1 can be stored continuously in the first storage unit, and in this continuous storage state, the plurality of compressible information can be regarded as a piece of data and be overall compressed in the first storage unit. Compared with individually compressing each compressible information of each feature point, overall compression of the compressible information of the plurality of feature points can be performed at a lower additional cost, thereby improving the compression efficiency.

[0057] As shown in FIG. 6, the plurality of non-compressible information 12, 22, … n2 can also be stored continuously in the second storage unit, so as to facilitate subsequent reading and operation. Further, after the plurality of continuously stored compressible information is overall compressed in the first storage unit, the compressed information obtained after the overall compression can be stored in the second storage unit. Figure 4 In some embodiments, the plurality of feature points in each registered fingerprint image can be all the feature points 10-n0 in each registered fingerprint image 410 as shown in the figure, that is, the compressible information of all the feature points in each registered fingerprint image can be stored continuously in the first storage unit, so that the processor can perform overall compression operation on the compressible information of all the feature points in the first storage unit as a piece of data; and / or the non-compressible information of all the feature points in each registered fingerprint image can be stored continuously in the second storage unit.

[0058]

[0059] ​​In other embodiments, the multiple feature points in each registered fingerprint image may include a subset of feature points in each registered fingerprint image. For example, the compressible information of a subset of feature points in the registered fingerprint image can be stored continuously and compressed as a whole, while the compressible information of another subset of feature points can be compressed separately without reordering their positions. In still other embodiments, all feature points in the registered fingerprint image can be divided into multiple groups, each group including one or more feature points, and the compressible information of the feature points in each group can be stored continuously and compressed as a whole on a group-by-group basis; and / or the uncompressed information of the feature points in each group can be stored continuously. In other application scenarios, the compressible information of the feature points in each group can be stored continuously and compressed as a whole on a group-by-group basis, while the uncompressed information of all feature points can be stored continuously.

[0060] Furthermore, the information storage and / or compression of feature points can be performed not only on a per-file-image-410 basis, but also on multiple feature points across multiple file-images. In other embodiments, the multiple feature points across multiple file-images may include a subset or all of the feature points, or all feature points across multiple file-images may be divided into multiple groups, and the compressible information of the subset, all, or each group of feature points may be continuously stored in a first storage unit, and the continuously stored compressible information may be compressed as a whole in the first storage unit; and / or the uncompressed information of the subset, all, or each group of feature points across multiple file-images may be continuously stored in a second storage unit.

[0061] The above combination Figure 4 The continuous storage and overall compression of compressible information according to the embodiments of this disclosure have been described exemplary. It is understood that, compared to not storing all compressible information of all feature points continuously, the continuous storage and overall compression of a portion of the compressible information of feature points, or continuous storage and compression in groups, will have better compression efficiency. Compared to the continuous storage and overall compression of a portion of the compressible information of feature points, or compression in groups, the continuous storage and overall compression of all compressible information of feature points will have better compression efficiency. Furthermore, the embedded system according to the embodiments of this disclosure can not only improve computing performance by continuously storing compressible information and compressing it as a whole, but also help to further save computing space in the first storage unit for uncompressed information stored in the second storage unit during subsequent fingerprint comparison. The following will be combined with Figure 5 Please provide an explanation.

[0062] Figure 5is a schematic diagram showing a matching process in an embedded system according to embodiments of the present disclosure. As shown in Figure 5 As shown in Figure 3 An embedded system as shown in

[0063] When the embedded system receives the to-be-matched fingerprint image, a fingerprint matching process can be performed. Specifically, after the aforementioned processor divides the registered fingerprint information into compressible information and non-compressible information, and stores the non-compressible information 502 and the compressed information 501 obtained by compressing the compressible information in the second storage unit 230, the processor can be further configured to: perform decompression processing 503 on the compressed information 501 in the first storage unit 220 to obtain decompressed information 504; and perform feature matching 506 on the to-be-matched fingerprint image according to the decompressed information 504 and the non-compressible information 502 stored in the second storage unit 230. Figure 5

[0064] The decompression processing 503 described above is equivalent to a restoration processing on the compressed information 501, and the decompressed information 504 is equivalent to the restored compressible information. Compared with compressing and decompressing all the registered fingerprint information, since the compressed information 501 in the embodiments of the present disclosure does not include the non-compressible information 502, the processing time and operation space of the decompression processing 503 can be saved; and since the decompressed information 504 does not include the non-compressible information 502, the storage space occupied by the decompressed information 504 in the first storage unit 220 can be saved.

[0065] In some embodiments, when performing feature matching 506 according to the decompressed information 504 and the non-compressible information 502, the processor can combine the decompressed information 504 and the non-compressible information 502, i.e., combine the feature information belonging to the same feature point in the restored compressible information and the non-compressible information 502 to restore the registered fingerprint information, and then perform matching between the to-be-matched feature information 505 and the restored registered fingerprint information by using a fingerprint matching algorithm (for example, a fingerprint matching algorithm based on detail feature points).

[0066] ​In some embodiments, the category of the to-be-compared feature information 505 can include one or more of species information of a feature point, position information of a feature point, direction information of a feature point, and surrounding information of a feature point. In the process of comparing the to-be-compared feature point of the to-be-compared fingerprint image with the feature points of one or more registered fingerprint images, the corresponding category of the decompressed information 504 and / or the non-compressed information 502 of the feature points of the registered fingerprint image can be read according to the category of the to-be-compared feature information 505 of the to-be-compared feature point, so as to determine whether the registered fingerprint image and the to-be-compared fingerprint image are successfully compared with respect to the corresponding feature points of the to-be-compared fingerprint image.

[0067] In some embodiments, the category of the to-be-compared feature information 505 can include one or more of species information of a feature point, position information of a feature point, direction information of a feature point, and surrounding information of a feature point. In the process of comparing the to-be-compared feature point of the to-be-compared fingerprint image with the feature points of one or more registered fingerprint images, the corresponding category of the decompressed information 504 and / or the non-compressed information 502 of the feature points of the registered fingerprint image can be read according to the category of the to-be-compared feature information 505 of the to-be-compared feature point, so as to determine whether the registered fingerprint image and the to-be-compared fingerprint image are successfully compared with respect to the corresponding feature points of the to-be-compared fingerprint image.

[0068] In some application scenarios, in response to the category of the to-be-compared feature information 505 of the current to-be-compared feature point being at least one of species information of a feature point, position information of a feature point, and direction information of a feature point, the corresponding category of the information of the feature points in the decompressed information 504 stored in the first storage unit 220 can be read for comparison. In other application scenarios, in response to the category of the to-be-compared feature information 505 of the current to-be-compared feature point being surrounding information of a feature point, the non-compressed information 502 stored in the second storage unit 230 can be read for comparison.

[0069] In yet some application scenarios, in response to the category of the to-be-compared feature information 505 of the current to-be-compared feature point being the category information of the feature point, the position information of the feature point, the direction information of the feature point, and the surrounding information of the feature point, the information of the corresponding category of any feature point in the decompressed information 504 stored in the first storage unit 220 and the non-compressed information 502 of the same feature point stored in the second storage unit 230 can be read, and the information of the corresponding category of the feature point in the read decompressed information 504 is compared with the category information, the position information, and the direction information of the to-be-compared feature point, and the non-compressed information 502 of the same feature point is compared with the surrounding information of the feature point in the to-be-compared feature information 505, to determine the degree of coincidence between the read information of the feature point and the feature information of the current to-be-compared feature point. Then, the information of the corresponding category of other feature points in the decompressed information 504 and the non-compressed information 502 of the corresponding other feature points stored in the second storage unit 230 can be read, to determine the degree of coincidence between the feature information of the read other feature points and the feature information of the current to-be-compared feature point.

[0070] In some embodiments, the to-be-compared feature information 505 of each to-be-compared feature point in the to-be-compared fingerprint image can be compared with the decompressed information 504 and / or the non-compressed information 502 of all or a plurality of feature points, to determine the degree of coincidence between each to-be-compared feature point in the to-be-compared fingerprint image and each feature point in the registered fingerprint image, to facilitate further determination of whether the to-be-compared fingerprint image passes the verification.

[0071] In the above process, since the reading is performed according to the category of the to-be-compared feature information 505, the decompressed information 504 and the non-compressed information 502 do not need to be combined in the first storage unit 220, thereby saving the storage space required for loading the non-compressed information 502 in the first storage unit 220, and facilitating further improvement of the performance of the embedded system.

[0072] In yet some embodiments, the processor can be further configured to, in response to the non-compressed information 502 being stored in the second storage unit 230 in a continuous storage manner, use a hardware accelerator to read the non-compressed information 502 of the corresponding category. It can be understood that, when the non-compressed information 502 is stored in a continuous storage manner, the hardware accelerator of the processor can be used to accelerate the reading and operation, so that the hardware acceleration function can be exerted while saving the operation space of the first storage unit 220, and the operation load of the processor is reduced. Compared with the scheme of compressing and decompressing all the registered fingerprint information, the technical scheme of the embedded system according to the embodiments of the present disclosure can make full use of the hardware function, and help to greatly improve the system performance.

[0073] The above is described in combination withFigure 5 The process of fingerprint comparison of the embedded system according to the embodiments of the present disclosure is exemplarily described. It can be understood that the embedded system according to the embodiments of the present disclosure can not only improve the operation performance of the registration information compression stage by splitting the compressible information and the non-compressible information, but also improve the operation speed and performance of the system in the fingerprint comparison stage, so that the system can better implement the processing of the fingerprint information.

[0074] Further, the present disclosure also provides, in a second aspect, a method for processing fingerprint information, which will be described below in combination with Figure 6 . Figure 6 is a flow chart illustrating a method for processing fingerprint information according to the embodiments of the present disclosure. As shown in Figure 6 , the method 600 can include: in step 601, the compressible information and the non-compressible information in the registration fingerprint information can be determined; and in step 602, the compressible information can be compressed to obtain the compressed compressible information.

[0075] In some embodiments, the registration fingerprint information includes feature information of feature points from one or more registration fingerprint images; and the determination of the compressible information and the non-compressible information in the registration fingerprint information can include: determining the compressible information and the non-compressible information in the feature information of each feature point according to the category of the feature information of each feature point in each registration fingerprint image.

[0076] In other embodiments, the method 600 can further include: continuously storing the compressible information of the plurality of feature points to compress the continuously stored compressible information as a whole; and / or continuously storing the non-compressible information of the plurality of feature points.

[0077] In some embodiments, the continuously storing the compressible information of the plurality of feature points can include: continuously storing the compressible information of the plurality of feature points in each registration fingerprint image or the compressible information of the plurality of feature points in the plurality of registration fingerprint images; and / or the continuously storing the non-compressible information of the plurality of feature points can include: continuously storing the non-compressible information of the plurality of feature points in each registration fingerprint image or the non-compressible information of the plurality of feature points in the plurality of registration fingerprint images.

[0078] In yet other embodiments, the method 600 can further include: continuously storing the compressible information of all feature points in each registration fingerprint image or the compressible information of all feature points in the plurality of registration fingerprint images; and / or continuously storing the non-compressible information of all feature points in each registration fingerprint image or the non-compressible information of all feature points in the plurality of registration fingerprint images.

[0079] In some embodiments, the method 600 can further include decompressing the compressed information to obtain decompressed information, and performing feature comparison on the to-be-compared fingerprint image according to the decompressed information and the uncompressed information.

[0080] In some other embodiments, performing feature comparison according to the decompressed information and the uncompressed information can include reading the decompressed information of a corresponding category and / or reading the uncompressed information of a corresponding category according to the category of the to-be-compared feature information in the to-be-compared fingerprint image, so as to compare the to-be-compared fingerprint image with the corresponding category feature information of each feature point in the registered fingerprint image.

[0081] In yet some other embodiments, reading the uncompressed information of a corresponding category can include using a hardware accelerator to read the uncompressed information of a corresponding category in response to the uncompressed information being stored in a continuous storage manner.

[0082] In some embodiments, the uncompressed information can include surrounding information of a feature point, and / or the compressible information can include at least one of the following categories of feature information: category information of a feature point; position information of a feature point; and direction information of a feature point.

[0083] The method according to the embodiments of the present disclosure has been described in detail in the foregoing in combination with the embedded system, and thus will not be described here again.

[0084] Through the foregoing description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software necessary universal hardware platforms, and of course can also be implemented by hardware. Those skilled in the art can understand that the foregoing description of the embodiments in combination with the embedded system is only used to illustrate the principles of the embodiments, and thus the embodiments can be implemented in various manners. Figures 1-6 All or part of the steps of the described embodiments can be completed by program instruction related hardware, and the foregoing program instruction can be stored in a non-transient computer readable medium, which stores a program for processing fingerprint information, and when the program is run by a processor, steps including the foregoing method embodiments can be executed.

[0085] A non-transitory computer-readable medium can be, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of non-transitory computer-readable media include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), a static random access memory (SRAM), a digital versatile disc (DVD), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. Any of such non-transitory computer storage media can be part of a device or accessible or connectable thereto. Any applications or modules described herein can be implemented using computer-readable / executable instructions stored or otherwise held by such non-transitory computer-readable media.

[0086] Through the above description of the technical solutions and multiple embodiments of the embedded system and method for processing fingerprint information of the present disclosure, it can be understood by those skilled in the art that the embedded system of the present disclosure can distinguish between compressible information and non-compressible information in the registered fingerprint information, and perform differentiated processing procedures, which can be beneficial to reduce the space occupation of the first storage unit, and further beneficial to improve the processing performance of the system. In some embodiments, the embedded system of the present disclosure can read the decompressed information and / or non-compressed information of the corresponding category according to the category of the feature information to be compared, which can be helpful to further improve the operation speed and efficiency during fingerprint comparison.

[0087] It can also be understood that the embedded system of the present disclosure can be directly applied to devices without computing functions, so that they can have fingerprint recognition functions, such as being applied to vehicles, door handles, access control systems, external keyboards, etc. It can also be understood that the embedded system of the present disclosure can also be applied to devices with computing functions, such as computers, mobile devices, etc. Since the embedded system of the present disclosure can independently and efficiently complete the storage of registered fingerprint data and fingerprint recognition operations, etc., it can not need to share the processors and memories of other devices, etc., so that it can be easily integrated with other devices, and can ensure the security and reliability of the fingerprint information processing process, and has good application prospects.

[0088] While several embodiments of the disclosure have been shown and described herein, it is to be understood that the embodiments are merely exemplary. Numerous changes, substitutions and equivalents can occur to those skilled in the art without departing from the spirit and scope of the disclosure. It should be understood that various alternatives to the embodiments of the disclosure described herein can be employed in practicing the disclosure. It is intended that the following claims define the scope of the disclosure and that methods equivalent to those shown and described herein can be utilized without departing from the spirit and scope of the disclosure.

Claims

1. An embedded system for processing fingerprint information, comprising: a processor configured to: determine compressible information and non-compressible information in enrolled fingerprint information; and perform compression processing on the compressible information; a first storage unit configured to provide an operation space for the processor to perform the compression processing; and a second storage unit configured to store the non-compressible information and compressed information obtained by compressing the compressible information. wherein the enrolled fingerprint information comprises feature information of feature points from one or more enrolled fingerprint images; the embedded system further comprises: a fingerprint sensor configured to acquire the enrolled fingerprint images; and the processor is further configured to: determine the compressible information and the non-compressible information in the feature information of each feature point according to a category of the feature information of each feature point in each enrolled fingerprint image.

2. The embedded system according to claim 1, wherein the processor is further configured to: store the compressible information of a plurality of feature points consecutively in the first storage unit and perform overall compression on the consecutively stored compressible information in the first storage unit; and / or store the non-compressible information of a plurality of feature points consecutively in the second storage unit.

3. The embedded system according to claim 2, wherein the processor is further configured to: store the compressible information of a plurality of feature points in each enrolled fingerprint image or the compressible information of a plurality of feature points in a plurality of enrolled fingerprint images consecutively in the first storage unit and perform overall compression on the consecutively stored compressible information in the first storage unit; and / or store the non-compressible information of a plurality of feature points in each enrolled fingerprint image or the non-compressible information of a plurality of feature points in a plurality of enrolled fingerprint images consecutively in the second storage unit.

4. The embedded system according to claim 3, wherein the processor is further configured to: store the compressible information of all feature points in each enrolled fingerprint image or the compressible information of all feature points in a plurality of enrolled fingerprint images consecutively in the first storage unit; and / or store the non-compressible information of all feature points in each enrolled fingerprint image or the non-compressible information of all feature points in a plurality of enrolled fingerprint images consecutively in the second storage unit.

5. The embedded system according to any one of claims 1-4, wherein: the fingerprint sensor is further configured to acquire a to-be-compared fingerprint image; and the processor is further configured to: perform decompression processing on the compressed information in the first storage unit to obtain decompressed information; and perform feature comparison on the to-be-compared fingerprint image according to the decompressed information and the non-compressible information.

6. The embedded system according to claim 5, wherein when performing feature comparison according to the decompressed information and the non-compressible information, the processor is further configured to: ​ ​ ​ According to a category of the to-be-compared feature information in the to-be-compared fingerprint image, reading the decompression information of the corresponding category stored in the first storage unit, and / or reading the non-compression information of the corresponding category stored in the second storage unit, so as to compare the to-be-compared fingerprint image with the corresponding category feature information of each feature point in the registered fingerprint image.

7. The embedded system of claim 6, wherein the processor is further configured to: read the non-compression information of the corresponding category using a hardware accelerator in response to the non-compression information being stored in the second storage unit in a continuous storage manner.

8. The embedded system according to any of claims 1-4, wherein, the non-compression information comprises surrounding information of the feature point; and / or the compressible information comprises at least one of the following categories of feature information: category information of the feature point; position information of the feature point; and direction information of the feature point.

9. The embedded system of claim 1, wherein the first storage unit comprises a random access memory, the second storage unit comprises a flash memory.

10. A method for processing fingerprint information, comprising: determining compressible information and non-compression information in registered fingerprint information; and performing compression processing on the compressible information to obtain compressed compression information; wherein the registered fingerprint information comprises feature information of feature points from one or more registered fingerprint images; and determining the compressible information and the non-compression information in the registered fingerprint information comprises: determining the compressible information and the non-compression information in the feature information of each feature point according to the category of the feature information of each feature point in each registered fingerprint image.

11. The method of claim 10, further comprising: continuously storing the compressible information of a plurality of feature points to perform overall compression on the continuously stored compressible information; and / or continuously storing the non-compression information of a plurality of feature points.

12. The method of claim 11, wherein continuously storing the compressible information of a plurality of feature points comprises: continuously storing the compressible information of a plurality of feature points in each registered fingerprint image or the compressible information of a plurality of feature points in a plurality of registered fingerprint images; and / or continuously storing the non-compression information of a plurality of feature points comprises: continuously storing the non-compression information of a plurality of feature points in each registered fingerprint image or the non-compression information of a plurality of feature points in a plurality of registered fingerprint images.

13. The method of claim 12, further comprising: continuously storing the compressible information of all feature points in each registered fingerprint image or the compressible information of all feature points in a plurality of registered fingerprint images; and / or continuously storing the non-compression information of all feature points in each registered fingerprint image or the non-compression information of all feature points in a plurality of registered fingerprint images.

14. The method of any one of claims 10-13, further comprising: performing decompression processing on the compression information to obtain decompression information; and performing feature comparison on a to-be-compared fingerprint image according to the decompression information and the non-compression information. ​ ​ ​ 15. The method of claim 14, wherein performing feature matching according to decompressed information and non-decompressed information comprises: reading, according to a category of feature information to be matched in a to-be-matched fingerprint image, decompressed information of the corresponding category and / or non-decompressed information of the corresponding category, so as to match the to-be-matched fingerprint image with corresponding category feature information of each feature point in the registered fingerprint image.

16. The method of claim 15, wherein reading non-decompressed information of the corresponding category comprises: reading, in response to the non-decompressed information being stored in a continuous storage manner, non-decompressed information of the corresponding category using a hardware accelerator.

17. The method of any one of claims 10-13, wherein, the non-decompressed information comprises surrounding information of a feature point; and / or the decompressible information comprises at least one of the following categories of feature information: species information of a feature point; position information of a feature point; and direction information of a feature point.

18. A non-transitory computer-readable storage medium storing a program for processing fingerprint information, which, when executed by a processor, performs the method according to any one of claims 10-17.

Images