TWI754242B - Method, device for evaluating fingerprint quality based on images and electronic device - Google Patents

Abstract

The present disclosure relates to a method, a device for evaluating fingerprint quality based on images and an electronic device. The method includes: taking fingerprint images, removing DC component in the fingerprint image, making a spectrum map of the fingerprint images by changing frequency domain of the fingerprint images to remove the DC component, and calculating a spectral energy map of the fingerprint images according to the spectral map of the fingerprint image, and extracting the fingerprint frequency region characteristics of the spectral energy map, scoring the fingerprint image according to the characteristics of the fingerprint frequency to obtain evaluation results of the fingerprint images. The present disclosure can quickly evaluate quality of fingerprint images, reduce complexity of fingerprint quality assessment calculations, and simplify process of fingerprint quality assessment.

Description

Image-based fingerprint quality assessment method, device and electronic device

The present invention relates to the technical field of image processing, in particular to an image-based fingerprint quality assessment method, device and electronic device.

In the prior art, the image quality evaluation is mainly realized by relying on the image contrast, or by detecting the image vertebral region by binarizing the image, or relying on the number of image samples. However, the method that relies on image contrast or image binarization to detect the image spine region to achieve image fingerprint quality evaluation increases the computational complexity, and depends on the number of image samples to achieve image fingerprint quality evaluation. It is necessary to obtain a large amount of data and training, which makes the fingerprint quality evaluation process too cumbersome.

In view of the above, it is necessary to propose an image-based fingerprint quality assessment method, device and electronic device to reduce the computational complexity of fingerprint quality assessment and simplify the process of fingerprint quality assessment.

A first aspect of the present application provides an image-based fingerprint quality assessment method, the method comprising: collecting a fingerprint image; removing a DC component in the fingerprint image; Perform frequency domain transformation on the fingerprint image with the DC component removed to obtain a spectrogram of the fingerprint image, and calculate a spectral energy map of the fingerprint image according to the spectrogram of the fingerprint image; extract the spectrum The fingerprint frequency region feature in the energy map; the fingerprint image is scored according to the fingerprint frequency region feature to obtain an evaluation result of the fingerprint image.

Preferably, the extracting the fingerprint frequency region feature in the spectral energy map comprises: presetting a frequency domain detection region of the fingerprint image; and extracting the fingerprint frequency region of the spectral energy map in the frequency domain detection region feature.

Preferably, the extracting the fingerprint frequency region feature in the spectral energy map includes: traversing the spectral energy map to extract the energy maximum point in the spectral energy map as the position frequency point f0 and normalizing it. The frequency domain detection area is set as [f0-delta, f0+delta], where delta is an adjustment parameter and the value is 0.1; and the fingerprint frequency area feature of the spectral energy map in the frequency domain detection area is extracted.

Preferably, the removing the DC component in the fingerprint image comprises: removing the fingerprint image by a method of subtracting the mean value of the primitives of the fingerprint image from the primitive value of each primitive point of the fingerprint image DC component in the image.

計算所述指紋圖像中的所有圖元點的圖元均值，其中h為所述指紋圖像在高度上的圖元點個數，w為所述指紋圖像在寬度上的圖元點個數，I(x,y)為所述指紋圖像中的圖元點；及將所述指紋圖像中的每個圖元點的圖元值減去所述指紋圖像的圖元均值以去除所述指紋圖像中的直流分量。 Preferably, the method for removing the DC component in the fingerprint image by subtracting the mean value of the primitives of the fingerprint image from the primitive value of each primitive point of the fingerprint image comprises: according to the formula

Calculate the mean value of primitives of all primitives in the fingerprint image, where h is the number of primitives in the height of the fingerprint image, and w is the number of primitives in the width of the fingerprint image number, I(x, y) is the primitive point in the fingerprint image; and the primitive value of each primitive point in the fingerprint image is subtracted from the primitive mean value of the fingerprint image to obtain The DC component in the fingerprint image is removed.

Preferably, the removing the DC component in the fingerprint image comprises: The DC component in the fingerprint image is removed by high-pass filtering the fingerprint image.

Preferably, performing frequency domain transformation on the fingerprint image with the DC component removed to obtain the spectrogram of the fingerprint image includes: performing fast Fourier transform on the fingerprint image with the DC component removed to obtain the fingerprint Spectrogram of the image.

Preferably, the scoring of the fingerprint image according to the fingerprint frequency region feature to obtain the evaluation result of the fingerprint image includes: searching a scoring relationship table according to the fingerprint frequency region feature to confirm the relationship between the fingerprint frequency region feature and the fingerprint frequency region feature. The corresponding score obtains the evaluation result of the fingerprint image, wherein the score relationship table defines the corresponding relationship between a plurality of different fingerprint frequency region features and a plurality of different scores.

A second aspect of the present application provides an image-based fingerprint quality assessment device, the device includes: a collection module for collecting a fingerprint image; a DC removal module for removing a DC component in the fingerprint image frequency domain transformation module, for carrying out frequency domain transformation to the described fingerprint image of removing the DC component to obtain the spectrogram of the fingerprint image, and calculates the fingerprint image according to the spectrogram of the fingerprint image The feature extraction module is used to extract the fingerprint frequency region feature in the spectrum energy map; the scoring module is used to score the fingerprint image according to the fingerprint frequency region feature to obtain the fingerprint Image evaluation results.

The third party aspect of the present application provides an electronic device, the electronic device includes a processor configured to implement the image-based fingerprint quality assessment method when executing a computer program stored in a memory.

In this case, the frequency domain transformation is performed on the fingerprint image with the DC component removed to obtain the spectral energy map of the fingerprint image, the fingerprint frequency region features in the spectral energy map are extracted, and the fingerprint image is processed according to the fingerprint frequency region features. The evaluation result of the fingerprint image is obtained by scoring, so as to quickly evaluate the quality of the fingerprint image, reduce the computational complexity of fingerprint quality evaluation, and simplify the process of fingerprint quality evaluation.

30: Image-based fingerprint quality assessment device

301: Collection Module

302: DC removal module

303: Frequency Domain Transform Module

304: Feature extraction module

305: Scoring Module

6: Electronic equipment

61: Memory

62: Processor

63: Computer Programs

S11~S15: Steps

FIG. 1 is a flowchart of an image-based fingerprint quality assessment method according to an embodiment of the present invention.

FIG. 2 is a schematic structural diagram of an image-based fingerprint quality assessment apparatus according to an embodiment of the present invention.

FIG. 3 is a schematic diagram of an electronic device in an embodiment of the present invention.

In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments may be combined with each other in the case of no conflict.

In the following description, many specific details are set forth in order to facilitate a full understanding of the present invention, and the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention.

Preferably, the image-based fingerprint quality assessment method of the present invention is applied in one or more electronic devices. The electronic device is a device that can automatically enter the Equipment for performing numerical computation and/or information processing, the hardware of which includes but is not limited to microprocessors, Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), Digital Signal Processor (DSP), embedded devices, etc.

The electronic device may be a computing device such as a desktop computer, a notebook computer, a tablet computer, and a cloud server. The device can interact with the user by means of a keyboard, a mouse, a remote control, a touch pad or a voice control device.

FIG. 1 is a flowchart of an image-based fingerprint quality assessment method according to an embodiment of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

Referring to Figure 1, the image-based fingerprint quality assessment method specifically includes the following steps:

Step S11, collecting a fingerprint image.

In this embodiment, a fingerprint image is collected by a fingerprint sensor. The fingerprint sensor is at least one of an optical fingerprint sensor, a semiconductor capacitive fingerprint sensor, a semiconductor thermal fingerprint sensor, a semiconductor pressure sensitive fingerprint sensor, an ultrasonic fingerprint sensor and a radio frequency fingerprint sensor. A sort of.

Step S12, remove the DC component in the fingerprint image.

計算所述指紋圖像中的所有圖元點的圖元均值，其中h為所述指紋圖像在高度上的圖元點個數，w為所述指紋圖像在寬度上的圖元點個數，I(x,y)為所述指紋圖像中的圖元點；然後將所述指紋圖像中的每個圖元點的圖元值減去所述指紋圖像的圖元均值，如此去除所述指紋圖像中的直流分量。 In this embodiment, the removing the DC component in the fingerprint image includes: removing the fingerprint image by subtracting the average value of the image elements of the fingerprint image from the image element value of each image element point of the fingerprint image. DC component in the image. In the specific implementation, first according to the formula

Calculate the mean value of primitives of all primitives in the fingerprint image, where h is the number of primitives in the height of the fingerprint image, and w is the number of primitives in the width of the fingerprint image number, I(x, y) is the primitive point in the fingerprint image; then subtract the primitive value of each primitive point in the fingerprint image from the primitive mean value of the fingerprint image, This removes the DC component in the fingerprint image.

In another embodiment, the removing the DC component in the fingerprint image comprises: removing the DC component in the fingerprint image by performing high-pass filtering on the fingerprint image. In other implementations, the removing the DC component in the fingerprint image comprises: subtracting the DC component from the fingerprint image mean filtered image of the fingerprint image to remove the DC component in the fingerprint image. In this embodiment, by removing the DC component in the fingerprint image, it can be ensured that the fingerprint frequency information in the fingerprint image occupies the main component of the frequency domain energy spectrum. In this case, all schemes for removing the DC component of the fingerprint image in different forms belong to the scope of protection in this case.

Step S13, performing frequency domain transformation on the fingerprint image with the DC component removed to obtain a spectrogram of the fingerprint image, and calculating a spectral energy map of the fingerprint image according to the spectrogram of the fingerprint image.

In this embodiment, the performing frequency domain transformation on the fingerprint image with the DC component removed to obtain the spectrogram of the fingerprint image includes: performing Fast Fourier Transform (Fast Fourier Transform) on the fingerprint image with the DC component removed. Fourier Transform, FFT) to obtain the spectrogram of the fingerprint image. In another embodiment, the performing frequency domain transformation on the fingerprint image with the DC component removed to obtain the spectrogram of the fingerprint image includes: performing a wavelet transform method on the fingerprint image with the DC component removed to obtain the obtained fingerprint image. The spectrogram of the fingerprint image. In this case, all schemes for obtaining the spectrogram of the fingerprint image by performing frequency domain transformation on the fingerprint image with the DC component removed in different forms belong to the protection category of this case.

In this embodiment, the calculating the spectral energy map of the fingerprint image according to the spectrogram of the image includes: according to the formula E ( x , y )= F ( x , y )˙ F ( x , y ) Calculate the spectral energy map of the fingerprint image, wherein the (x, y) is the coordinates of the primitive points in the fingerprint image, and F(x, y) is the frequency spectrum in the fingerprint image Figure, E(x, y) is the spectral energy map in the fingerprint image.

Step S14, extracting the fingerprint frequency region features in the spectral energy map.

In this embodiment, the extracting the fingerprint frequency region feature in the spectral energy map includes: presetting a frequency domain detection region of the fingerprint image; and extracting the fingerprint of the spectral energy map in the frequency domain detection region Frequency Region Features. In a specific embodiment, the preset frequency domain detection area of the fingerprint image includes: collecting a standard fingerprint image, checking the frequency distribution position of the standard fingerprint image by an image processing tool, and setting the detection standard fingerprint image. The position frequency point is f0, and the fingerprint frequency band area of the standard fingerprint image is set as an oval area; the frequency information of the frequency domain image of the standard fingerprint image is normalized, and the normalized frequency domain image The center of the frequency domain image represents the 0 frequency, away from the frequency domain image The area in the center of the image is a high-frequency area; the frequency domain detection area is set to [f1-delta, f1+delta], where f1 is the position frequency point of the normalized standard fingerprint image, and delta is the adjustment parameter and the value is 0.1. In this embodiment, the adjustment parameter delta can be set according to the principle that the frequency of the ridge and valley of the human fingerprint cannot be infinitely large or infinitely small, but has a certain distribution range. When the adjustment parameter delta is set to 0.1, the frequency domain detection area is determined to cover more than 99% of the user population.

In one embodiment, the extracting the fingerprint frequency region feature in the spectral energy map includes: traversing the spectral energy map to extract the energy maximum point in the spectral energy map as the position frequency point f0 and normalizing it. To be normalized, the frequency domain detection area is set as [f0-delta, f0+delta], so as to obtain the frequency domain detection area in real time, where delta is an adjustment parameter and takes a value of 0.1; and the spectral energy is extracted Figure 2. The fingerprint frequency region features of the detection region in the frequency domain.

In this embodiment, the fingerprint frequency region feature is a feature representing frequency intensity and distribution. In this embodiment, the fingerprint frequency region feature includes at least one of mean, standard deviation, variance, maximum/minimum difference, and entropy. In this case, the fingerprint frequency region features of the fingerprint image are not limited to the mean, standard deviation, variance, maximum/minimum value difference, and entropy, as long as the features that characterize the frequency intensity and distribution in the fingerprint image belong to the protection of this case area.

Step S15, scoring the fingerprint image according to the fingerprint frequency region feature to obtain an evaluation result of the fingerprint image.

In this embodiment, the scoring of the fingerprint image according to the fingerprint frequency region feature to obtain the evaluation result of the fingerprint image includes: searching a scoring relationship table according to the fingerprint frequency region feature to confirm the relationship between the fingerprint frequency and the fingerprint frequency The evaluation result of the fingerprint image is obtained from the scores corresponding to the regional features, wherein the score relationship table defines the corresponding relationship between a plurality of different fingerprint frequency region features and a plurality of different scores. For example, the fingerprint frequency region feature is a standard deviation, and the score relationship table defines a correspondence between a plurality of different standard deviations and a plurality of different scores, and the fingerprint image is evaluated according to the fingerprint frequency region feature. The scoring to obtain the evaluation result of the fingerprint image includes: searching a scoring relationship table according to the standard deviation to confirm that the score corresponding to the standard deviation obtains the evaluation result of the fingerprint image. For another example, the fingerprint frequency region feature is an average value, and the score relationship table defines a plurality of Correspondence between different mean values and a plurality of different scores, the scoring of the fingerprint image according to the fingerprint frequency region feature to obtain the evaluation result of the fingerprint image includes: looking up the score relationship table according to the mean value to confirm The score corresponding to the mean value obtains the evaluation result of the fingerprint image.

In this embodiment, scoring the fingerprint image according to the fingerprint frequency region feature to obtain the evaluation result of the fingerprint image includes: calculating and obtaining the fingerprint according to the fingerprint frequency region feature using a deep learning algorithm image rating.

In this case, the frequency domain transformation is performed on the fingerprint image with the DC component removed to obtain the spectral energy map of the fingerprint image, the fingerprint frequency region features in the spectral energy map are extracted, and the fingerprint image is processed according to the fingerprint frequency region features. The evaluation result of the fingerprint image is obtained by scoring, so as to quickly evaluate the quality of the fingerprint image, reduce the computational complexity of fingerprint quality evaluation, and simplify the process of fingerprint quality evaluation.

FIG. 2 is a structural diagram of an image-based fingerprint quality assessment apparatus 30 according to an embodiment of the present invention. In some embodiments, the image-based fingerprint quality assessment apparatus 30 runs in an electronic device. The image-based fingerprint quality assessment device 30 may include a plurality of functional modules composed of program code segments. The code of each program segment in the image-based fingerprint quality assessment device 30 may be stored in a memory and executed by at least one processor to perform a fingerprint quality assessment function.

In this embodiment, the image-based fingerprint quality assessment device 30 can be divided into a plurality of functional modules according to the functions it performs. Referring to FIG. 2 , the image-based fingerprint quality assessment device 30 may include a collection module 301 , a DC removal module 302 , a frequency domain transformation module 303 , a feature extraction module 304 and a scoring module 305 . The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, and are stored in a memory. In some embodiments, the functions of each module will be described in detail in subsequent embodiments.

The collection module 301 is used to collect fingerprint images.

In this embodiment, the collection module 301 collects a fingerprint image through a fingerprint sensor. The fingerprint sensor is an optical fingerprint sensor, a semiconductor capacitive fingerprint sensor, a semiconductor thermal fingerprint sensor At least one of a sensor, a semiconductor pressure-sensitive fingerprint sensor, an ultrasonic fingerprint sensor, and a radio frequency fingerprint sensor.

The DC removal module 302 removes the DC component in the fingerprint image.

計算所述指紋圖像中的所有圖元點的圖元均值，其中h為所述指紋圖像在高度上的圖元點個數，w為所述指紋圖像在寬度上的圖元點個數，I(x,y)為所述指紋圖像中的圖元點；及將所述指紋圖像中的每個圖元點的圖元值減去所述指紋圖像的圖元均值，如此去除所述指紋圖像中的直流分量。 In this embodiment, the DC removal module 302 removes the DC component in the fingerprint image including: subtracting the mean value of the primitives of the fingerprint image from the primitive value of each primitive point of the fingerprint image method to remove the DC component in the fingerprint image. In a specific implementation manner, the DC removal module 302 follows the formula

Calculate the mean value of primitives of all primitives in the fingerprint image, where h is the number of primitives in the height of the fingerprint image, and w is the number of primitives in the width of the fingerprint image number, I(x, y) is the primitive point in the fingerprint image; and subtract the primitive value of each primitive point in the fingerprint image from the primitive mean value of the fingerprint image, This removes the DC component in the fingerprint image.

In another embodiment, the removing the DC component in the fingerprint image by the DC removing module 302 includes: removing the DC component in the fingerprint image by performing high-pass filtering on the fingerprint image. In other embodiments, the DC removing module 302 removing the DC component in the fingerprint image includes: subtracting the mean filtered image of the fingerprint image from the fingerprint image to remove the DC component in fingerprint images. In this embodiment, by removing the DC component in the fingerprint image, it can be ensured that the fingerprint frequency information in the fingerprint image occupies the main component of the frequency domain energy spectrum. In this case, all schemes for removing the DC component of the fingerprint image in different forms belong to the scope of protection in this case.

The frequency domain transformation module 303 performs frequency domain transformation on the fingerprint image with the DC component removed to obtain a spectrogram of the fingerprint image, and calculates the spectrogram of the fingerprint image according to the spectrogram of the fingerprint image. Spectral energy map.

In this embodiment, the frequency domain transformation module 303 performs frequency domain transformation on the fingerprint image from which the DC component is removed to obtain a spectrogram of the fingerprint image, which includes: performing FFT on the fingerprint image from which the DC component is removed Transform to obtain the spectrogram of the fingerprint image. In another embodiment, the performing frequency domain transformation on the fingerprint image with the DC component removed to obtain the spectrogram of the fingerprint image includes: performing a wavelet transform method on the fingerprint image with the DC component removed to obtain the obtained fingerprint image. The spectrogram of the fingerprint image. In this case, all schemes for obtaining the spectrogram of the fingerprint image by performing frequency domain transformation on the fingerprint image with the DC component removed in different forms belong to the protection category of this case.

In this embodiment, the frequency domain transformation module 303 calculates the spectral energy diagram of the fingerprint image according to the spectrogram of the image, including: according to the formula E ( x , y )= F ( x , y )˙ F ( x , y ) calculates the spectral energy map of the fingerprint image, wherein the (x, y) is the coordinates of the primitive points in the fingerprint image, and F(x, y) is the The spectrogram in the fingerprint image, E(x,y) is the spectrogram in the fingerprint image.

The feature extraction module 304 extracts the fingerprint frequency region features in the spectral energy map.

In this embodiment, the feature extraction module 304 extracting the fingerprint frequency region features in the spectral energy map includes: presetting the frequency domain detection region of the fingerprint image; and extracting the spectral energy map in the frequency domain The domain detects the fingerprint frequency region feature of the region. In a specific embodiment, the feature extraction module 304 presets the frequency domain detection area of the fingerprint image includes: collecting a standard fingerprint image, checking the frequency distribution position of the standard fingerprint image by an image processing tool, and setting detection The position frequency point of the standard fingerprint image is f0, and the fingerprint frequency band area of the standard fingerprint image is set as an ellipse area; the frequency information of the frequency domain image of the standard fingerprint image is normalized, and after the normalization The center of the frequency domain image represents the 0 frequency of the frequency domain image, and the area far from the center of the frequency domain image is the high frequency area; the frequency domain detection area is set to [f1-delta, f1+delta], where , f1 is the position frequency point of the normalized standard fingerprint image, delta is the adjustment parameter and the value is 0.1. In this embodiment, the adjustment parameter delta can be set according to the principle that the frequency of the ridge and valley of the human fingerprint cannot be infinitely large or infinitely small, but has a certain distribution range. When the adjustment parameter delta is set to 0.1, the frequency domain detection area is determined to cover more than 99% of the user population.

In one embodiment, the extracting the fingerprint frequency region feature in the spectral energy map includes: traversing the spectral energy map to extract the energy maximum point in the spectral energy map as the position frequency point f0 and normalizing it. Unification, the frequency domain detection area is set to [f0-delta, f0+delta], from The frequency domain detection area is obtained immediately, wherein delta is an adjustment parameter and the value is 0.1; and the fingerprint frequency area feature of the spectral energy map in the frequency domain detection area is extracted.

In this embodiment, the fingerprint frequency region feature is a feature representing frequency intensity and distribution. In this embodiment, the fingerprint frequency region feature includes at least one of mean, standard deviation, variance, maximum/minimum difference, and entropy. In this case, the fingerprint frequency region features of the fingerprint image are not limited to the mean, standard deviation, variance, maximum/minimum value difference, and entropy, as long as the features that characterize the frequency intensity and distribution in the fingerprint image belong to the protection of this case area.

The scoring module 305 scores the fingerprint image according to the fingerprint frequency region feature to obtain an evaluation result of the fingerprint image.

In this embodiment, the scoring module 305 scores the fingerprint image according to the fingerprint frequency region features to obtain the evaluation result of the fingerprint image, which includes: searching a scoring relationship table according to the fingerprint frequency region features to confirm the The evaluation result of the fingerprint image is obtained from the score corresponding to the fingerprint frequency region feature, wherein the score relationship table defines the correspondence between a plurality of different fingerprint frequency region features and a plurality of different scores. For example, the fingerprint frequency region feature is a standard deviation, and the score relationship table defines the correspondence between a plurality of different standard deviations and a plurality of different scores, and the scoring module 305 evaluates all the scores according to the fingerprint frequency region feature Scoring the fingerprint image to obtain the evaluation result of the fingerprint image includes: searching a scoring relationship table according to the standard deviation to confirm the score corresponding to the standard deviation to obtain the evaluation result of the fingerprint image. For another example, the fingerprint frequency region feature is an average value, and the score relationship table defines a corresponding relationship between a plurality of different average values and a plurality of different scores, and the scoring module 305 evaluates the fingerprint frequency region feature according to the fingerprint frequency region feature. Scoring the fingerprint image to obtain the evaluation result of the fingerprint image includes: searching a scoring relation table according to the mean value to confirm the score corresponding to the mean value to obtain the evaluation result of the fingerprint image.

In this embodiment, scoring the fingerprint image according to the fingerprint frequency region feature to obtain the evaluation result of the fingerprint image includes: calculating and obtaining the fingerprint according to the fingerprint frequency region feature using a deep learning algorithm image rating.

In this case, the frequency domain transformation is performed on the fingerprint image with the DC component removed to obtain the spectral energy map of the fingerprint image, the fingerprint frequency region features in the spectral energy map are extracted, and the fingerprint image is processed according to the fingerprint frequency region features. The evaluation result of the fingerprint image is obtained by scoring, so as to quickly evaluate the quality of the fingerprint image, reduce the computational complexity of fingerprint quality evaluation, and simplify the process of fingerprint quality evaluation.

FIG. 3 is a schematic diagram of an electronic device 6 in an embodiment of the present invention. The electronic device 6 includes a memory 61 , a processor 62 and a computer program 63 stored in the memory 61 and executable on the processor 62 . When the processor 62 executes the computer program 63 , the steps in the above-mentioned embodiment of the image-based fingerprint quality assessment method are implemented, such as steps S11 to S15 shown in FIG. 1 . Alternatively, when the processor 62 executes the computer program 63 , the functions of each module/unit in the above-mentioned embodiment of the image-based fingerprint quality assessment apparatus, such as modules 301 to 305 in FIG. 2 , are implemented.

Exemplarily, the computer program 63 can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 61 and executed by the processor 62 , to complete the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 63 in the electronic device 6 . For example, the computer program 63 can be divided into the acquisition module 301, the DC removal module 302, the frequency domain transformation module 303, the feature extraction module 304 and the scoring module 305 in FIG. 2. For the specific functions of each module, please refer to Example 2.

In this embodiment, the electronic device 6 may be a computing device such as a desktop computer, a notebook, a palmtop computer, a server, and a cloud terminal device. Those skilled in the art can understand that the schematic diagram is only an example of the electronic device 6, and does not constitute a limitation to the electronic device 6, and may include more or less components than the one shown, or combine some components, or different Components such as the electronic device 6 may also include input and output devices, network access devices, bus bars, and the like.

The processor 62 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs) ), on-site programmable gate array Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor 62 can also be any conventional processor, etc. The processor 62 is the control center of the electronic device 6, and uses various interfaces and lines to connect the entire electronic device 6. various parts.

The memory 61 can be used to store the computer programs 63 and/or modules/units, and the processor 62 runs or executes the computer programs and/or modules/units stored in the memory 61, And call the data stored in the memory 61 to realize various functions of the electronic device 6 . The memory 61 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; storage data The area may store data (such as audio data, phone book, etc.) created according to the use of the electronic device 6, and the like. In addition, the memory 61 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (Secure Digital, SD) card, flash memory card (Flash Card), at least one disk memory device, flash memory device, or other volatile solid state memory device.

If the modules/units integrated in the electronic device 6 are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, When the computer program is executed by the processor, the steps of the above method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code may be in the form of original code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-only memory) Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be The requirements of the legislation and patent practice in the jurisdictions may vary as appropriate, for example, in some jurisdictions, under legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunications signals.

In the several embodiments provided by the present invention, it should be understood that the disclosed electronic devices and methods may be implemented in other manners. For example, the above-described electronic device embodiments are only illustrative. For example, the division of the modules is only a logical function division, and other division methods may be used in actual implementation.

In addition, each functional module in each embodiment of the present invention may be integrated in the same processing module, or each module may exist physically alone, or two or more modules may be integrated in the same module. The above-mentioned integrated modules can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, but that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the invention is to be defined by the appended claims rather than the foregoing description, which are therefore intended to fall within the scope of the claims. All changes within the meaning and range of the equivalents of , are included in the present invention. Any reference signs in the claims shall not be construed as limiting the involved claim. Furthermore, it is clear that the word "comprising" does not exclude other modules or steps, and the singular does not exclude the plural. A plurality of modules or electronic devices recited in the electronic device claims can also be realized by one and the same module or electronic device by means of software or hardware. The terms first, second, etc. are used to denote names and do not denote any particular order.

S11~S15: Steps

Claims (9)

An image-based fingerprint quality assessment method, which is improved in that the method includes: collecting a fingerprint image; removing a DC component in the fingerprint image; performing frequency domain transformation on the fingerprint image from which the DC component has been removed to obtain obtaining the spectrogram of the fingerprint image, and calculating the spectrogram of the fingerprint image according to the spectrogram of the fingerprint image; extracting the fingerprint frequency region feature in the spectrogram, including: traversing the spectrum The energy map extracts the energy maximum point in the spectrum energy map as the position frequency point f0 and normalizes it, and sets the frequency domain detection area as [f0-delta, f0+delta], where delta is an adjustment parameter and according to The fingerprint ridge and valley frequency is set; and the fingerprint frequency region feature of the spectral energy map in the frequency domain detection region is extracted; the fingerprint image is scored according to the fingerprint frequency region feature to obtain an evaluation of the fingerprint image. result. The image-based fingerprint quality assessment method according to claim 1, wherein the value of delta is 0.1. The image-based fingerprint quality assessment method according to claim 1, wherein the removing the DC component in the fingerprint image comprises: subtracting a primitive value from each primitive point of the fingerprint image The method of de-averaging the image elements of the fingerprint image removes the DC component in the fingerprint image. The image-based fingerprint quality assessment method according to claim 3, wherein the method of subtracting the mean value of the primitives of the fingerprint image from the primitive value of each primitive point of the fingerprint image Removing the DC component in the fingerprint image includes: according to the formula

Calculate the mean value of primitives of all primitives in the fingerprint image, where h is the number of primitives in the height of the fingerprint image, and w is the number of primitives in the width of the fingerprint image number, I(x, y) is the primitive point in the fingerprint image; and the primitive value of each primitive point in the fingerprint image is subtracted from the primitive mean value of the fingerprint image to obtain The DC component in the fingerprint image is removed. The image-based fingerprint quality assessment method according to claim 1, wherein the removing the DC component in the fingerprint image comprises: removing the DC component in the fingerprint image by performing high-pass filtering on the fingerprint image the direct current component. The image-based fingerprint quality assessment method according to claim 1, wherein the performing frequency domain transformation on the fingerprint image with the DC component removed to obtain the spectrogram of the fingerprint image comprises: removing the DC component The fingerprint image of the component is subjected to fast Fourier transform to obtain a spectrogram of the fingerprint image. The image-based fingerprint quality evaluation method according to claim 1, wherein the obtaining the evaluation result of the fingerprint image by scoring the fingerprint image according to the fingerprint frequency region feature comprises: according to the fingerprint The frequency region feature search score relationship table confirms that the score corresponding to the fingerprint frequency region feature obtains the evaluation result of the fingerprint image, wherein the score relationship table defines a plurality of different fingerprint frequency region features and a plurality of different fingerprint frequency region features. Correspondence of ratings. An image-based fingerprint quality assessment device, which is improved in that the device comprises: a collection module for collecting a fingerprint image; a DC removal module for removing the DC component in the fingerprint image; a frequency domain A transformation module, configured to perform frequency domain transformation on the fingerprint image with the DC component removed to obtain a spectrogram of the fingerprint image, and calculate the spectral energy of the fingerprint image according to the spectrogram of the fingerprint image Figure; feature extraction module, used to extract the fingerprint frequency region features in the spectrum energy map, including: Traverse the spectral energy map to extract the energy maximum point in the spectral energy map as the position frequency point f0 and normalize it, and set the frequency domain detection area as [f0-delta, f0+delta], where delta is Adjusting parameters and setting according to the frequency of fingerprint ridges and valleys; and extracting the fingerprint frequency region features of the spectral energy map in the frequency domain detection region; a scoring module for evaluating the fingerprint image according to the fingerprint frequency region features Scoring is performed to obtain the evaluation result of the fingerprint image. An electronic device, the improvement is that: the electronic device includes a processor, and the processor is configured to implement the image-based fingerprint quality assessment according to any one of claims 1-7 when executing a computer program stored in a memory method.

Images