Method and apparatus for generating fingerprint image to be recognized

Abstract

The embodiments of the present disclosure relate to the technical field of ultrasonic fingerprint recognition. Provided are a method and apparatus for generating a fingerprint image to be recognized. A particular embodiment of the method comprises: collecting a fingerprint image of the fingerprint of a finger; using a first feature of the fingerprint image to match a target background image of the fingerprint image from a background image library, wherein the first feature of the fingerprint image is at least one of a signal time-of-flight of an ultrasonic signal generating the fingerprint image, a signal transmission frequency of the ultrasonic signal generating the fingerprint image, or a collection time for the fingerprint image; and performing subtraction on the fingerprint image and the target background image, so as to obtain a fingerprint image to be recognized of the fingerprint of the finger. The embodiment can improve the fingerprint recognition accuracy in various recognition scenarios.

Description

[0001] A Method and Apparatus for Generating a Fingerprint Image to be Identified. This application claims priority to a Chinese application filed with the China Patent Office on February 8, 2024, with application number 202410177930.8, entitled "A Method and Apparatus for Generating a Fingerprint Image to be Identified," the entire contents of which are incorporated herein by reference. Technical Field: This disclosure relates to the field of ultrasonic fingerprint recognition technology, and more particularly to a method and apparatus for generating a fingerprint image to be identified. Background: To improve the security of various devices, protect user privacy, and provide user convenience, fingerprint recognition-based unlocking technology has been widely used in various fields, including but not limited to personal devices such as smartphones and tablets, as well as everyday devices such as access control, attendance, daily consumption, and financial transaction verification. In existing fingerprint unlocking systems, the device controls a finger-level recognition device to transmit an ultrasonic signal to a fingerprint collection area. After the user presses on the finger-level collection area, the device controls the finger-level recognition device to process the ultrasonic echo signal to identify the user's finger. Because the signal data is a mixed image consisting of finger-level signals and background signals, background removal is required to obtain a finger-level image. However, since the background signal image used in ultrasonic fingerprint processing is pre-collected, there is a significant time interval between the mixed image obtained by the user's finger press. This results in significant differences in the acquisition conditions of the mixed image and the background image, leading to significant interference from the background removal process. Consequently, the resulting finger-level image accuracy is low, resulting in low finger-level recognition accuracy, and frequent unauthorized recognition and unlocking failures. In view of this, embodiments of the present disclosure provide a method and apparatus for generating a finger-level image to be identified. This method addresses the problem of significant interference from background removal due to the significant differences in acquisition conditions between the background image and the signal image, resulting in low accuracy of the resulting finger-level image and recognition accuracy, and frequent unauthorized recognition and unlocking failures.To achieve the above-mentioned objectives, according to one aspect of the present disclosure, a method for generating a finger-level image to be identified is provided, comprising: collecting a fingerprint image of a finger fingerprint; matching a target background image of the fingerprint image with a first feature of the fingerprint image from a background image library; wherein the first feature of the finger-level image is at least one of a signal flight time of an ultrasonic signal used to generate the finger image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, or an acquisition time of the finger-level image; and subtracting the finger-level image from the target background image to obtain a fingerprint image of the finger fingerprint to be identified. According to another aspect of the present disclosure, a device for generating a fingerprint image to be identified is provided, comprising: an acquisition module for acquiring a fingerprint image of a finger; a matching module for matching the fingerprint image with a target background image from a background image library using a first feature of the fingerprint image; wherein the first feature of the fingerprint image is at least one of the signal flight time of the ultrasonic signal used to generate the fingerprint image, the signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, or the acquisition time of the fingerprint image; and a data processing module for subtracting the fingerprint image from the target background image to obtain the fingerprint image to be identified. According to yet another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing a program, wherein the program includes instructions that, when executed by the processor, cause the processor to perform the method for generating the fingerprint image to be identified. According to yet another aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions cause the computer to perform the method for generating the fingerprint image to be identified.One or more technical solutions provided in the embodiments of the present application utilize a pre-established background image library. When processing a fingerprint image containing a mixed signal, the target background image is selected based on the signal transmission frequency, signal flight time, and fingerprint image acquisition time to obtain the target background image that most closely matches the various parameter characteristics of the mixed signal. The fingerprint image and the target background image are then subtracted to obtain a finger-level signal with a good signal-to-noise ratio. This reduces the difference between the background signal during mixed signal acquisition and the background signal used for background removal, avoids signal interference from background removal, improves the accuracy of finger-level images, and thereby improves the accuracy of finger recognition in various recognition scenarios. This prevents the frequent occurrence of illegal finger recognition and unlocking failures, resulting in a technical effect of greater convenience for users in finger-level recognition and subsequent operations such as unlocking and consumption.BRIEF DESCRIPTION OF THE DRAWINGS In the following description of exemplary embodiments in conjunction with the accompanying drawings, more details, features and advantages of the present disclosure are disclosed, in which: FIG1 shows a flow chart of a method for generating a fingerprint image to be identified according to an exemplary embodiment of the present disclosure; FIG2 shows a schematic diagram of a terminal device according to an exemplary embodiment of the present disclosure; FIG3 (a) shows a schematic diagram of a background image library according to an exemplary embodiment of the present disclosure; FIG3 (b) shows a schematic diagram of a sub-image library according to the first exemplary embodiment of the present disclosure; FIG3 (c) shows a schematic diagram of a sub-image library according to the second exemplary embodiment of the present disclosure; FIG3 (d) shows a schematic diagram of a sub-image library according to the third exemplary embodiment of the present disclosure; FIG3 (e) shows a schematic diagram of a sub-image library according to the fourth exemplary embodiment of the present disclosure; FIG4 shows a flow chart of a target background image matching method according to the first exemplary embodiment of the present disclosure; FIG5 shows a flow chart of a method for determining a target background image using a weighted comparison method according to an exemplary embodiment of the present disclosure; FIG6 shows a flow chart of a method for determining image similarity according to an exemplary embodiment of the present disclosure; FIG7 shows a flow chart of a method for determining a target background image using a peak signal-to-noise ratio comparison method according to an exemplary embodiment of the present disclosure; FIG8 shows a flow chart of a target background image matching method according to the second exemplary embodiment of the present disclosure; Figure 9 shows a flowchart of a method for collecting background images to be stored according to a first exemplary embodiment of the present disclosure; Figure 10 shows a flowchart of a method for collecting background images to be stored according to a second exemplary embodiment of the present disclosure; Figure 11 shows a flowchart of a method for storing background images to be stored according to an exemplary embodiment of the present disclosure; Figure 12 shows a flowchart of a method for storing background images to be stored according to an exemplary embodiment of the present disclosure; Figure 13 shows a schematic block diagram of an apparatus for generating a fingerprint image to be identified according to an exemplary embodiment of the present disclosure; and Figure 14 shows a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure.It should be understood that the figures and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure. It should be understood that the various steps described in the method embodiments of this disclosure may be performed in a different order and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit illustrated steps. The scope of this disclosure is not limited in this respect. As used herein, the term "including" and its variations are open-ended, meaning "including but not limited to." The term "based on" means "based, at least in part, on." The term "in an embodiment of the present disclosure" means "at least one embodiment," and the term "another exemplary embodiment" means "at least one additional embodiment." Definitions of other terms are provided below. It should be noted that terms such as "first" and "second" in this disclosure are used solely to distinguish between different devices, modules, or units and are not intended to limit the order or interdependence of the functions performed by these devices, modules, or units. It should be noted that the modifiers "one" and "multiple" mentioned in this disclosure are illustrative and non-restrictive. Those skilled in the art should understand that, unless the context clearly indicates otherwise, they should be understood to mean "one or more." The names of the messages or information exchanged between the multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of these messages or information. Common background subtraction methods include using background images with different reflectivities to eliminate finger-level image interference and multiple gain adjustment calculations to remove background noise. The former is applicable to optical finger-level recognition, and the latter is applicable to capacitive finger-level recognition. Neither method is applicable to ultrasonic finger-level recognition. In existing ultrasonic fingerprint recognition, the ultrasonic echo signal includes both background and fingerprint signals. During processing, the background signal must be removed, retaining only the finger-level image corresponding to the fingerprint signal for fingerprint recognition. The ultrasonic fingerprint reader collects background signals after each press and after the user's finger leaves the fingerprint collection area. The collected signals are then stored and used for background removal the next time the user presses the fingerprint. Therefore, the background signals used for background removal each time the user presses the fingerprint are usually those collected after the previous press.For this reason, on the one hand, since there is no background signal during the first press, the initial finger-level recognition of each new user is bound to fail. On the other hand, due to the long interval between the background signal and the mixed signal, various parameters of the device to be unlocked may have changed. For example, the large temperature difference between indoors and outdoors in summer and winter leads to different signal collection temperatures and changes in the transmission frequency of the ultrasonic signal. These changes can cause the acoustic properties of the ultrasonic fingerprint identifier's various acoustic layers (upper electrode, lower electrode, piezoelectric layer, protective layer, adhesive layer, integrated chip), film, and screen to change, leading to changes in the background signal. For example, replacing components such as the film and screen can cause changes in the ultrasonic signal's signal flight time at the same transmission frequency, which can also cause changes in the background signal. This can lead to a significant difference between the background signal collected during mixed signal collection and the background signal collected during background subtraction, causing significant interference to background subtraction. In summary, this results in a low accuracy fingerprint image obtained through background removal, which in turn reduces the accuracy of finger-level recognition. This can lead to frequent unauthorized recognition and unlocking failures, forcing users to repeatedly operate and unlock their devices, causing significant inconvenience. The following describes the solution of the present disclosure with reference to the accompanying drawings. Figure 1 shows a flowchart of a method for generating a fingerprint image to be recognized according to an exemplary embodiment of the present disclosure. As shown in Figure 1, the method for generating a fingerprint image to be recognized includes the following steps: In the embodiments of the present disclosure, the method for generating a fingerprint image to be recognized can be executed by any fingerprint recognition chip or device. The following uses finger-level recognition on a terminal device as an example to illustrate the implementation process of the method for generating a fingerprint image to be recognized. Furthermore, the disclosed method for generating a fingerprint image to be identified is performed by a system-on-chip (SoC) of an electronic device. As shown in FIG2 , the electronic device includes an electronic device screen, a SoC, an ultrasonic fingerprint sensor, a temperature sensor, and the like. The ultrasonic fingerprint sensor includes multiple acoustic layers, including a drive circuit, a protective layer, an upper electrode, a piezoelectric layer, a lower electrode, an integrated chip, and an interconnect layer. Step 101: Capture a fingerprint image of a finger.In the disclosed embodiment, the system chip transmits the ultrasonic signal's transmission frequency to the ultrasonic fingerprint identifier. The ultrasonic fingerprint identifier transmits the ultrasonic signal at the transmission frequency to the electronic device screen. When a user's finger touches the fingerprint acquisition area on the electronic device screen, a recognition command is issued to the ultrasonic fingerprint identifier. The ultrasonic fingerprint identifier then collects the ultrasonic echo signal, generates a fingerprint image of the user's finger, and returns it to the system chip. The fingerprint image is a superposition of the fingerprint signal and background signal. Alternatively, the ultrasonic fingerprint identifier can directly return the ultrasonic echo signal data to the system chip, which performs digital conversion and other processing to generate a fingerprint image of the user's finger. The processing method can be selected based on actual needs. Step 102: Use the first feature of the fingerprint image to match a target background image for the fingerprint image from a background image library. The first feature of the fingerprint image is at least one of the signal flight time of the ultrasonic signal used to generate the fingerprint image, the signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, or the acquisition time of the fingerprint image. In the disclosed embodiments, the first characteristic of a finger-level image is described as the flight time of the ultrasonic signal used to generate the finger-level image, the transmission frequency of the ultrasonic signal used to generate the fingerprint image, or the acquisition time of the finger-level image. The fingerprint image is represented by Rcrw. The image data of the fingerprint image Rcrw is stored in a matrix format of the grayscale values ​​of all pixels. The fingerprint image Raw includes X*P pixels, and the image data of the fingerprint image Raw is stored in a matrix format of the grayscale values ​​of all pixels. Furthermore, in one embodiment of the present disclosure, the image features of a finger-level image include a first feature, a second feature, a third feature, and a fourth feature. The first feature, the second feature, the third feature, and the fourth feature are each different and are one of the following four: the signal flight time of the ultrasonic signal used to generate the finger-level image, the signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, the acquisition time of the fingerprint image, and the grayscale value matrix of the fingerprint image. The signal flight time refers to the time difference between the transmission time of the ultrasonic signal and the reception time of the ultrasonic echo signal corresponding to the generation of the finger-level image; the signal transmission frequency refers to the operating frequency of the ultrasonic signal corresponding to the generation of the finger-level image; and the acquisition time refers to the timestamp when the finger-level image is generated. Alternatively, in another embodiment of the present disclosure, the image features of the sub-library include a first feature, a second feature, a third feature, a fourth feature, and a fifth feature. The first feature, the second feature, the third feature, the fourth feature, and the fifth feature are each different and are one of the following five: the signal flight time of the ultrasonic signal used to generate the fingerprint image, the signal transmission frequency of the ultrasonic signal used to generate the finger-level image, the acquisition time of the finger-level image, the acquisition temperature of the environment in which the electronic device used to generate the finger-level image is located, and the grayscale value matrix of the finger-level image. The acquisition temperature refers to the temperature of the environment in which the electronic device is located when the finger-level image is acquired. In the embodiment of the present disclosure, as shown in FIG3 (a), the background image library 300 includes multiple sub-libraries 301. Each sub-library 301 can accommodate one or more background images. The maximum number of background images that each sub-library 301 can accommodate—that is, the sub-library capacity—can be the same or different and can be selectively set according to the actual recognition scenario. For example, the sub-library capacity is 10 to 25 images, and the seventh background image in the sub-library is Sase ; Indicates that the image data of the background image Base, is stored in the form of a matrix of grayscale values ​​of all pixels. Assume that the background image Base, includes X*P pixels, and the image data of the background image Base, is stored in the form of a grayscale value matrix G^ of all pixels. Y Furthermore, in one embodiment of the present disclosure, the image features of the sub-image library include a first feature, a second feature, a third feature, and a fourth feature. The first feature, the second feature, the third feature, and the fourth feature are different. Each sub-image library can be distinguished based on the feature value of one or more image features of each background image in the background image library. For example, as shown in FIG3 (b), each sub-image library can be distinguished based on the feature value of the first feature of each background image; for another example, as shown in FIG3 (c), each sub-image library can be distinguished based on the feature value of the first feature and the second feature; for another example, as shown in FIG3 (d), each sub-image library can be distinguished based on the feature value of the first feature, the second feature, and the third feature. Specifically, the first feature, the second feature, the third feature, and the fourth feature are each one of the following four: the signal flight time of the ultrasonic signal generating each background image in the sub-image library, the signal transmission frequency of the ultrasonic signal generating each background image in the sub-image library, the acquisition time of each background image in the sub-image library, and the grayscale value matrix of each background image in the sub-image library. The signal transmission frequency refers to the operating frequency of the ultrasonic signal corresponding to the background image generation, and the image features of the sub-image library are represented by the signal transmission frequency fi; the signal flight time refers to the time difference between the transmission time of the ultrasonic signal and the reception time of the ultrasonic echo signal when the background image is generated, and the image features of the sub-image library are represented by the signal flight time flyti; the acquisition time refers to the timestamp when the background image is generated, and the image features of the sub-image library are represented by the time interval ti of the acquisition time. Furthermore, each sub-image library is distinguished by the feature value of a first feature, where the first feature of a sub-image library can be the signal flight time, the signal transmission frequency, or the acquisition time. As shown in FIG4 , the target background image matching method of the first embodiment of the present disclosure includes the following steps: Step 401: Compare the first feature of the finger-level image with the first feature of the sub-image library to determine a first target sub-image library, where the feature value of the first feature of the fingerprint image is equal to or falls within the feature value of the first feature of the first target sub-image library. In the disclosed embodiment, the system chip compares the first feature of the fingerprint image with the first feature of the sub-image library, and determines a first target sub-image library in which the feature value of the first feature of the fingerprint image is equal to the feature value of the first feature of the sub-image library, or in which the feature value of the first feature of the fingerprint image falls within the feature value of the first feature of the sub-image library, thereby locating the first target sub-image library.Furthermore, the characteristic value of the first feature of the finger-level image is a single point value. For example, the signal flight time of the finger-level image is 1150 ns, the signal transmission frequency is 11.1 MHz, and the acquisition time is 2023.10.29-21:52:28. The feature value of the first feature of the first target sub-image library can be a single point value or an interval value. When the first feature is the signal flight time, the feature value of the first feature is a single point value or an interval value, for example, the first feature of the sub-image library flyt5=1100ns, or the first feature of the sub-image library flyt7=[1100ns, 1149ns]. When the first feature is the signal transmission frequency, the feature value of the first feature is a single point value, for example, the first features of the sub-image library fi=11.1MHz, f2=12.5MHz. When the first feature is the acquisition time, the feature value of the first feature is an interval value, for example, the first feature of the sub-image library t8=[2023.10.29-21:26:29, 2023.10.29-22:26:28]. Step 402: Determine whether the number of images in the first target sub-image library is one. If so, go to step 403; if not, go to step 404. In the disclosed embodiment, the system chip determines whether the number of images in the first target sub-library located based on the first feature is one. Step 403: Determine the background image in the first target sub-library as the target background image. In the disclosed embodiment, if the first target sub-library contains only one image, the system chip uses the remaining background image in the first target sub-library as the target background image. Step 404: Compare the second feature of the fingerprint image with the second feature of the background images in the first target sub-library to determine the first target background image. In the disclosed embodiment, if the first target sub-library contains multiple images, the system chip continues to compare the feature value of the second feature of the fingerprint image with the feature values ​​of the second features of multiple background images in the first target sub-library to determine one or more first target background images. The condition satisfied by the first target background image in step 404 is that the characteristic value of the second feature of the finger-level image is equal to or falls within the characteristic value of the second feature of the first target background image. In this embodiment, the first target background image that meets the condition is selected from the background images of the first target sub-image library, wherein the characteristic value of the second feature of the first target background image can be a certain value or a range of values.Step 405: Determine whether the first target background image contains only one image. If so, proceed to step 406; if not, proceed to step 407. In the disclosed embodiment, the system chip determines whether the first target background image located based on the second feature contains only one image. Step 406: Determine the first target background image as the target background image. In the disclosed embodiment, if the first target background image contains only one image, the system chip uses the first target background image as the target background image. Step 407: Compare the third feature of the fingerprint image with the third feature of the first target background image to determine the second target background image. In the disclosed embodiment, if the first target background image contains multiple images, the feature value of the third feature of the fingerprint image is further compared with the feature values ​​of the third features of multiple first target background images to determine one or more second target background images. In step 407, the second target background image satisfies the following conditions: the characteristic value of the third feature of the fingerprint image is equal to or falls within the characteristic value of the third feature of the second target background image. In this embodiment, a second target background image that meets these conditions is selected from the first target background image. The characteristic value of the third feature of the second target background image can be a single value or a range of values. In step 408, it is determined whether the second target background image contains only one image. If so, the process proceeds to step 409; if not, the process proceeds to step 410. In this embodiment, the system chip determines whether the second target background image located based on the third feature contains only one image. In step 409, the second target background image is determined as the target background image. In this embodiment, if the second target background image contains only one image, the system chip uses the second target background image as the target background image. In step 410, the fourth feature of the fingerprint image is compared with the fourth feature of the second target background image to determine the third target background image. In the embodiment of the present disclosure, when there are multiple second target background images, the feature value of the fourth feature of the finger-level image is continuously compared with the feature values ​​of the fourth feature of the multiple second target background images to determine one or more third target background images.In step 410, the third target background image satisfies the following conditions: the characteristic value of the fourth feature of the fingerprint image is equal to or falls within the characteristic value of the fourth feature of the third target background image. In this embodiment, a third target background image that meets this condition is selected from the second target background image. The characteristic value of the fourth feature of the third target background image can be a single value or a range of values. In step 411, it is determined whether there is only one third target background image. If so, the process proceeds to step 412; if not, the process proceeds to step 413. In this embodiment, the system chip determines whether there is only one third target background image located based on the fourth feature. In step 412, the system chip determines that the third target background image is the target background image. In this embodiment, if there is only one third target background image, the system chip selects the third target background image as the target background image. In step 413, the system chip determines the target background image from the multiple third target background images using a weighted comparison method or a peak signal-to-noise ratio comparison method. In an embodiment of the present disclosure, when the second feature is a grayscale value matrix, comparing the second feature of the fingerprint image with the second feature of the background images in the first target sub-image library to determine the first target background image includes calculating image similarity between the grayscale value matrix of the fingerprint image and the grayscale value matrices of each background image in the first target sub-image library, and determining the background image corresponding to the minimum value of the image similarity as the first target background image. When the third feature is a grayscale value matrix, comparing the third feature of the fingerprint image with the third feature of the first target background image to determine the second target background image includes calculating image similarity between the grayscale value matrix of the fingerprint image and the grayscale value matrix of the first target background image, and determining the first target background image corresponding to the minimum value of the image similarity as the second target background image. When the fourth feature is a grayscale value matrix, comparing the fourth feature of the fingerprint image with the fourth feature of the second target background image to determine the third target background image includes calculating image similarity between the grayscale value matrix of the fingerprint image and the grayscale value matrix of the second target background image, and determining the second target background image corresponding to the minimum value of the image similarity as the third target background image. In the embodiment of the present disclosure, when there are multiple third target background images, the system chip determines the target background image from the multiple third target background images using a weight comparison method or a peak signal-to-noise ratio comparison method.Furthermore, as shown in FIG5 , the method for determining a target background image using a weight comparison method disclosed herein includes the following steps: Step 501: Determine whether the characteristic values ​​of each feature of multiple third target background images are the same. If so, proceed to Step 502; if not, proceed to Step 503. Step 502: Determine the image weight of each third target background image based on the inverse of the number of images in the multiple third target background images. In an embodiment of the present disclosure, if the characteristic values ​​of each feature of multiple third target background images are the same, the image weight of each third target background image can be determined using an average weight method. It should be noted that the grayscale value matrices of multiple background images are generally different. In some embodiments, the characteristic values ​​of each feature of multiple third target background images can be the same when one or more of the following conditions are met: the signal flight time, the signal transmission frequency, the acquisition time, or the acquisition temperature are the same. Since the sum of the image weights of the multiple third target background images is 1, the image weights of each third target background image are evenly distributed by dividing the sum by the number of images in the multiple third target background images. That is, the image weight of each third target background image is the reciprocal of the number of images. Specifically, the number of images in the multiple third target background images is counted, and the reciprocal of the counted number of images is calculated as the image weight of each third target background image. For example, if there are five third target background images, the image weight of each third target background image is 0.2. Step 503: One or more target features are selected from the various features in the sub-image library. In this embodiment, if the feature values ​​of the multiple third target background images differ, one or more of the image features are selected as target features for calculating the image weight of each third target background image. Furthermore, the target features are preferentially selected from image features with different feature values ​​in the multiple third target background images. For example, if the signal transmission frequency and acquisition time of the multiple third target background images differ, the target features are determined to be the signal transmission frequency ε and the acquisition time t. Step 504: Determine an image weight of each of the third target background images according to a plurality of target feature distances between the target feature of the finger-level image and the target features of the plurality of third target background images.Step 5041: Calculate multiple target feature distances between the feature values ​​of the target feature of the finger-level image and the feature values ​​of the target features of the plurality of third target background images. In the disclosed embodiment, for example, the feature values ​​of the target feature of the finger-level image Raw are fRaw and tRaw, and the third target background image 5ase. 3 / The characteristic values ​​of the target feature are fB3i and tB3i, and the target feature distances between the fingerprint image and the second target background image are \f Raw -f B3i I. \t Raw -t B3j 1. Step 5042: normalize the target feature distance. In the embodiment of the present disclosure, for example, the normalized result of each target feature distance is: Step 5043: Perform an exponential transformation on the normalized result, and use the inverse of the exponential transformation result to determine the image weight of each of the third target background images. In the disclosed embodiment, the exponential transformation is performed in a sub-period manner. For example, the exponential transformation results of the normalized result are @y @y . Further, based on the inverse of the exponential transformation result, the index-level image Raw and the third target background image 5ase are determined. 3 / The feature similarity of the target feature is, for example, feature similarity = (black) + (black) + 1. In another embodiment, the target feature can also be a gray value matrix, which refers to the gray value matrix of the night image Raw and the first (020) is used to represent the grayscale values ​​of the fingerprint image Raw and the third target background image Base3. Each third target background image 5ase 3 / Image weights, for example, each third target background image 5ase 3 / The image weight w of . 3i = —with one o

[0002] E1 5 3 / Step 505: Perform a weighted calculation on the grayscale value matrices of the plurality of third target background images, based on the image weight of each third target background image. In the disclosed embodiment, the weighting algorithm for the weighted calculation can be selectively set as needed. For example, the weighting algorithm may be linear weighting. The weighted result of the weighted calculation performed by the system chip on the M third target background images is shown in the following equation (1): In the above formula (1), 5ase 3 / For the first, the gray value matrix of all pixels of the third target background image; You is the third target background image 5ase 3 / Image weight of .

[0003] 〃 is the third target background image 5ase 3 / The number of z = 1, 2, 3, -> A / o Step 506: The weighted result of the weighted calculation is used as the target background image. In the embodiment of the present disclosure, the system chip uses the weighted result of step 505 as the target background image. final As the target background image of the fingerprint image. Since the influence of multiple third background images is taken into account, noise interference can be reduced. Further, or, the system chip can search the background image library and the weighted result Sase according to the image similarity. fi u n nH ai1 The most similar background image is used as the target background image of the finger-level image. Furthermore, as shown in FIG6, the image similarity determination method of the present disclosure includes the following steps: In the embodiment of the present disclosure, the image similarity determination method of the present disclosure is used to determine the image similarity of a first image and a second image. Step 601, based on the grayscale values ​​of each pixel of the first image and the second image, respectively calculate the average grayscale value of all pixels of the first image, the average grayscale value of all pixels of the second image, and the covariance of the first image and the second image to obtain a first average value and a second average value. In the embodiment of the present disclosure, the first image is image A, including N pixels, and the image A has Image B includes N pixels. The grayscale value of each pixel in the grayscale value matrix of image B is represented by B. Accordingly, the first average value and the second average value are expressed as follows (2): Step 602: Calculate a first variance of the grayscale values ​​of pixels of the first image and a second variance of the grayscale values ​​of pixels of the second image. Step 603: Determine the covariance of the first and second images based on the grayscale values ​​of each pixel in the first and second images. Step 6031: Expand the grayscale value matrices of the first and second images into a first converted grayscale value matrix and a second converted grayscale value matrix, respectively. In the embodiment of the present disclosure, the grayscale value matrices, including the grayscale values ​​of all pixels in the first and second images, are expanded into one dimension to obtain the first converted grayscale value matrix and the second converted grayscale value matrix. Step 6032: Calculate the covariance of the first and second converted grayscale value matrices as the covariance of the first and second images. In the embodiment of the present disclosure, calculate the covariance of the first and second converted grayscale value matrices as the covariance SB of the first and second images. Step 604: Select constant coefficients 1 and 2, and determine the first and second constants based on the square of the product of the grayscale value variation range of each pixel in the first and second images and the constant coefficients 1 and 2, respectively. In the embodiment of the present disclosure, the constant coefficient 1 is represented by , and the constant coefficient 2 is represented by . According to the maximum value max (A) of all pixels of the first image and the second image, / ,B / The difference between the minimum value min(A″B′) and the minimum value min(A″B′) determines the variation range £. It should be noted that the constant coefficients 1 and 2 can be selectively set according to the grayscale value range of the fingerprint recognition scenario. Step 605: Determine the image similarity between the first image and the second image using the first average value, the second average value, the covariance, the first variance, the second variance, the first constant, and the second constant. Formula (3) shows: In the above formula (3), the value range of SA.B is [0, 1]. In the disclosed embodiments, the disclosed method for determining image similarity can be used in scenarios such as searching for the background image most similar to the weighted result from a background image library, subsequent storage, and image similarity determination for matching a target background image. This method can be used to determine the similarity between two images, thereby achieving image matching and storage, ensuring the clarity of the background image for fingerprint recognition, and improving fingerprint recognition accuracy. In the disclosed embodiments, the disclosed method for determining the target background image using a weighted comparison method utilizes the image weights of multiple images and determines the weighted result as the target background image based on the grayscale values ​​of the pixels. Even if multiple background images are ultimately selected based on various image parameters, the target background image with the acoustic characteristics closest to the fingerprint image can still be determined based on the weighted result, thereby accurately separating the fingerprint image for fingerprint recognition. Alternatively, as shown in FIG7 , the disclosed method for determining a target background image using a peak signal-to-noise ratio comparison method includes the following steps: Step 701: Calculate multiple peak signal-to-noise ratios between a plurality of third target background images and the fingerprint-level image based on the grayscale values ​​of each pixel. Step 7011: For each third target background image, calculate the mean square difference between the third target background image and the fingerprint-level image based on the grayscale values ​​of each pixel in the third target background image and the fingerprint image. In the disclosed embodiment, the third target background image 5ase 3z The mean square error of the fingerprint image Raw is shown in the following formula (4): Ra Bamboo Step 7012: Logarithmically transform the ratio of the maximum grayscale value of the pixel points in the fingerprint image to the mean square error to obtain the peak signal-to-noise ratio of the third target background image and the finger-level image. 3; Compared with the peak of the raw night image In the above formula (3), PSNR B3I R The higher the value, the higher the third target background image BasQ 3l The closer to the fingerprint image R2, the better; PSNR B3j R The lower it is, the better the third target background image Sase 3z Compared with fingerprint Step 702: The third target background image corresponding to the minimum value among the multiple peak signal-to-noise ratios is used as the target background image. In the embodiment of the present disclosure, the peak signal-to-noise ratio (PSNR) between the multiple third target background images and the fingerprint image Raw is used as the target background image. B3l RThe target background image is determined by taking the minimum value of . In the disclosed embodiment, the disclosed method for determining the target background image using the peak signal-to-noise ratio comparison method can determine the target background image closest to the finger-level image from multiple third target background images. Subsequently, the target background image with the acoustic response characteristics closest to the image parameters of the finger-level image can be used to accurately separate the fingerprint signal. This can reduce background signal noise, improve the clarity of the separated finger-level image, and thereby enhance fingerprint-level recognition accuracy. In the disclosed embodiment, the target background image matching method of the first embodiment of the disclosed embodiment uses signal flight time, signal transmission frequency, or acquisition time as the first feature, and performs step-by-step matching from the background image library until the target background image for the finger-level image is determined. This can improve the matching efficiency and accuracy of the target background image for the finger-level image, thereby enhancing the recognition efficiency and accuracy of fingerprints. Alternatively, in another embodiment of the present disclosure, the image features of the sub-image library include a first feature, a second feature, a third feature, a fourth feature and a fifth feature, and the first feature, the second feature, the third feature, the fourth feature and the fifth feature are different from each other. Each sub-image library can be distinguished according to the feature values ​​of one or more image features of each background image in the background image library. For example, as shown in Figure 3 (b), each sub-image library can be distinguished according to the feature value of the first feature of each background image; for another example, as shown in Figure 3 (c), each sub-image library can be distinguished according to the feature values ​​of the first feature and the second feature; for another example, as shown in Figure 3 (d), each sub-image library can be distinguished according to the feature values ​​of the first feature, the second feature and the third feature; for another example, as shown in Figure 3 (e), each sub-image library can be distinguished according to the feature values ​​of the first feature, the second feature, the third feature and the fourth feature. Specifically, the first, second, third, fourth, and fifth features are each one of the following: the signal flight time of the ultrasonic signal used to generate each background image in the sub-image library; the signal transmission frequency of the ultrasonic signal used to generate each background image in the sub-image library; the acquisition time of each background image in the sub-image library; the acquisition temperature of the environment in which the electronic device used to generate each background image in the sub-image library is located; and the grayscale value matrix of each background image in the sub-image library. The acquisition temperature refers to the temperature of the environment in which the electronic device was located when the background image was acquired. The image features of the sub-image library are represented by the acquisition temperature Ti.Furthermore, each sub-image library is distinguished by the feature values ​​of a first feature and a second feature. The first feature and the second feature of the sub-image library are two of signal flight time, signal transmission frequency, acquisition time, and acquisition temperature. As shown in FIG8 , the target background image matching method of the second embodiment of the present disclosure includes the following steps: Step 801: Compare the first and second features of the fingerprint-level image with the first and second features of the sub-image library to determine a first target sub-image library; the feature value of the first feature of the fingerprint-level image is equal to or falls within the feature value of the first feature of the first target sub-image library, and the second feature of the fingerprint image is equal to or falls within the feature value of the second feature of the first target sub-image library. In this embodiment of the present disclosure, the system chip compares the first feature of the fingerprint image with the first feature of the sub-image library, and the second feature of the fingerprint image with the second feature of the sub-image library, to determine a first target sub-image library in which the feature value of the first feature of the fingerprint image is equal to or falls within the feature value of the first feature of the sub-image library, and the feature value of the first feature of the fingerprint image is equal to or falls within the feature value of the first feature of the sub-image library, thereby locating the first target sub-image library. Step 802: Determine whether the first target sub-library contains only one image. If so, proceed to step 803; if not, proceed to step 804. In the disclosed embodiment, the system chip determines whether the first target sub-library, located based on the first and second features, contains only one image. Step 803: Determine whether the background image in the first target sub-library is the target background image. In the disclosed embodiment, if the first target sub-library contains only one image, the system chip uses the remaining background image in the first target sub-library as the target background image. Step 804: Compare the third feature of the finger-level image with the third feature of the background images in the first target sub-library to determine the first target background image. In step 804, the first target background image satisfies the condition that the third feature of the finger-level image is equal to or falls within the feature value of the third feature of the first target background image. In this embodiment, the first target background image that meets the condition is selected from the background images in the first target sub-library. The feature value of the third feature of the first target background image can be a certain value or a range.In this embodiment, if the first target sub-library contains multiple images, the feature value of the third feature of the fingerprint image is compared with the feature values ​​of the third feature of multiple background images in the first target sub-library to determine one or more first target background images. Step 805 determines whether the first target background image contains only one image. If so, the process proceeds to step 806; if not, the process proceeds to step 807. In this embodiment, the system chip determines whether the first target background image located based on the third feature contains only one image. Step 806 determines that the first target background image is the target background image. In this embodiment, if the first target background image contains only one image, the system chip uses the first target background image as the target background image. Step 807 compares the fourth feature of the fingerprint image with the fourth feature of the first target background image to determine the second target background image. In this embodiment, if there are multiple first target background images, the feature value of the fourth feature of the fingerprint image is compared with the feature values ​​of the fourth features of the multiple first target background images to determine one or more second target background images. In step 807, the second target background image satisfies the condition that the fourth feature of the fingerprint image is equal to or falls within the feature value of the fourth feature of the second target background image. In this embodiment, a second target background image that meets this condition is selected from the first target background images. The feature value of the fourth feature of the second target background image can be within a certain value or range. Step 808 determines whether there is only one second target background image. If so, the process proceeds to step 809; if not, the process proceeds to step 810. In this embodiment, the system chip determines whether there is only one second target background image located based on the fourth feature. Step 809 determines that the second target background image is the target background image. In this embodiment, if there is only one second target background image, the system chip uses the second target background image as the target background image. Step 810: Compare the fifth feature of the finger-level image with the fifth feature of the second target background image to determine a third target background image. In this embodiment, if there are multiple second target background images, the feature value of the fifth feature of the finger-level image is further compared with the feature values ​​of the fifth features of the multiple second target background images to determine one or more third target background images.In step 810, the third target background image satisfies the condition that the fifth feature of the finger-level image is equal to or falls within the feature value of the fifth feature of the third target background image. In this embodiment, a third target background image that meets this condition is selected from the second target background image. The feature value of the fifth feature of the third target background image can be a certain value or range. Step 811 determines whether the third target background image has one image. If so, the process proceeds to step 812; if not, the process proceeds to step 813. In this embodiment, the system chip determines whether the third target background image located based on the fifth feature has one image. Step 812 determines that the third target background image is the target background image. In this embodiment, if the third target background image has only one image, the system chip selects the third target background image as the target background image. Step 813 determines the target background image from the multiple third target background images using a weighted comparison method or a peak signal-to-noise ratio comparison method. In the disclosed embodiment, when the third feature is a grayscale value matrix, comparing the third feature of the fingerprint image with the third feature of the background images in the first target sub-library to determine the first target background image includes: calculating image similarity between the grayscale value matrix of the fingerprint image and the grayscale value matrices of each background image in the first target sub-library; the background image in the first target sub-library with the minimum image similarity value is determined as the first target background image. When the fourth feature is a grayscale value matrix, comparing the fourth feature of the fingerprint image with the fourth feature of the first target background image to determine the second target background image includes: calculating image similarity between the grayscale value matrix of the fingerprint image and the grayscale value matrix of the first target background image; the first target background image corresponding to the minimum image similarity value is determined as the second target background image. When the fifth feature is a grayscale value matrix, comparing the fifth feature of the fingerprint image with the fifth feature of the second target background image to determine the third target background image includes calculating image similarity between the grayscale value matrix of the fingerprint image and the grayscale value matrix of the second target background image, and determining the second target background image with the minimum image similarity as the third target background image. In the embodiment of the present disclosure, when there are multiple third target background images, the system chip uses a weighted comparison method or a peak signal-to-noise ratio comparison method to determine the target background image from the multiple third target background images.In the disclosed embodiment, the target background image matching method of the second embodiment of the present disclosure utilizes two of the following features: signal flight time, signal transmission frequency, acquisition time, and acquisition temperature as the first and second features. This avoids the occurrence of recognition failures caused by excessive matching of background images based solely on acquisition temperature. By combining multiple features to progressively match the target background image, the matching efficiency and accuracy of the fingerprint image can be improved, thereby improving the efficiency and accuracy of fingerprint recognition. In the disclosed embodiment, the acoustic impedance of the various layers of material in the ultrasonic fingerprint reader varies with the environment in which the terminal device is located, resulting in varying penetration strength of the ultrasonic signal. This results in varying image clarity of background images acquired at different signal transmission frequencies. Similarly, varying film thickness, screen thickness, acoustic layer thickness, etc., can result in varying recognition paths for the ultrasonic signal, resulting in varying image clarity of background images acquired at different signal flight times. In other words, the signal transmission frequency and signal flight time significantly influence the image clarity of the background image. During fingerprint-level recognition, to improve fingerprint recognition efficiency and accuracy, signal flight time and signal transmission frequency, which have a significant impact on background image clarity, are preferably used as the first and second features. Accordingly, the first feature is signal flight time, and the second feature is signal transmission frequency, or vice versa. Furthermore, the closer the acquisition time to the fingerprint-level image, the closer the acquired background image is to the response parameters of the fingerprint image. Therefore, the acquisition time is preferably the third feature. In the disclosed embodiment, when generating a background image library, to avoid interference from various acquisition conditions on fingerprint recognition, various signal transmission frequencies are set under different environmental conditions to acquire background images to be stored. Furthermore, various signal flight times are set under different film thicknesses, screen thicknesses, and material thicknesses to construct the background image library. Consequently, during fingerprint-level recognition, signal transmission frequency and signal flight time can be preferentially selected as the first and second features, allowing for rapid matching of target background images from the background image library that most closely match the acquisition conditions of the fingerprint-level image, thereby improving fingerprint-level recognition efficiency and accuracy. Furthermore, as shown in FIG9 , the method for collecting background images to be stored in the first embodiment of the present disclosure includes the following steps: Step 901: Setting the collection transmission frequency under different environmental conditions.In the disclosed embodiments, environmental conditions include geographic location, ambient temperature, ambient brightness, ambient humidity, ambient pressure, rain, snow, fog, and interference from other electromagnetic devices. These conditions can be configured as needed to improve the coverage of the background images to be stored, ensuring a diverse collection of background images to be stored, and enabling accurate finger-level recognition of electronic devices under various environmental conditions. For example, geographic location can be captured using multiple longitude and latitude coordinates with significant differences in longitude and latitude. Ambient temperature can be manually altered (e.g., by increasing the temperature) or vary with geographic location, so multiple temperature values ​​with a wide span and increasing in increments according to a preset step size can be captured. Ambient brightness can be altered (e.g., by occlusion) or vary with geographic location, so multiple brightness values ​​with a wide span and increasing in increments according to a preset step size can be captured. The acquisition and transmission frequencies can be selectively set to different levels as needed. After the acquisition personnel configure the system chip, the system chip controls the ultrasonic fingerprint level identifier to acquire data at each acquisition and transmission frequency. For example, acquisition and transmission frequencies include f1 = 11.1 MHz and f2 = 12.5 MHz. Step 902: When the electronic device is placed under various environmental conditions, a first acquisition instruction for each of the acquisition and transmission frequencies is issued to the ultrasonic fingerprint level identifier. In the disclosed embodiment, after the environmental conditions and acquisition and transmission frequencies are set, the acquisition personnel place the electronic device under the various environmental conditions. The system chip generates a first acquisition instruction based on the acquisition and transmission frequencies set by the acquisition personnel and issues it to the ultrasonic fingerprint level identifier. In response to the first acquisition instruction, the ultrasonic fingerprint identifier controls the driver circuit to transmit ultrasonic signals through the piezoelectric layer toward the electronic device screen at each acquisition and transmission frequency. The ultrasonic fingerprint level identifier's integrated chip then acquires the ultrasonic echo signals to generate a background image to be stored. Step 903: Receive multiple background images to be stored returned by the ultrasonic fingerprint identifier, where the signal transmission frequency of the background images to be stored is the acquisition and transmission frequency. In an embodiment of the present disclosure, a system chip receives images of the pending entry background image returned by an ultrasonic finger night detector under different environmental conditions and at different acquisition and transmission frequencies. The signal transmission frequency of the pending entry background image is the acquisition and transmission frequency. As shown in FIG10 , the method for acquiring the pending entry background image in the second embodiment of the present disclosure includes the following steps: Step 1001: Setting the acquisition flight time under different thickness conditions.In the disclosed embodiment, thickness conditions include the thickness of the terminal screen, the thickness of the terminal film, and the thickness of each acoustic layer of the ultrasonic fingerprint reader. These conditions can be varied as needed to improve the coverage of the background image to be stored, thereby ensuring a diverse collection of background images to be stored and enabling accurate fingerprint recognition for the terminal device under various thickness conditions. For example, various terminal screen thicknesses, films of different materials or thicknesses, and acoustic layers of different materials or thicknesses can be selected. The acquisition flight time can be selectively set to different levels as needed. After the acquisition personnel configure the terminal chip, the terminal chip controls the ultrasonic fingerprint reader to collect data according to various acquisition flight times, such as ti = 1100ns, t2 = 1150ns, and t3 = 1200ns. In step 1002, when the terminal device meets various thickness conditions, a second acquisition instruction for each acquisition flight time is issued to the ultrasonic fingerprint reader. In this embodiment, after the thickness conditions and acquisition flight time are set, the acquisition personnel selects terminal devices with different screen thicknesses and replaces different films and acoustic layers for the terminal devices. Under various thickness conditions, the terminal chip generates a second acquisition instruction based on the various acquisition flight times set by the acquisition personnel and sends it to the ultrasonic fingerprint reader. In response to the second acquisition instruction, the ultrasonic fingerprint reader controls the driver circuit to transmit ultrasonic signals through the piezoelectric layer to the terminal screen according to the respective acquisition flight times. The integrated chip of the ultrasonic fingerprint reader then acquires the ultrasonic echo signals and generates a background image to be stored. Step 1003: Receive multiple background images to be stored returned by the ultrasonic fingerprint reader. The signal flight time of each background image to be stored is the acquisition flight time. In this embodiment, the terminal chip receives the acquired background images to be stored under different thickness conditions and different acquisition flight times returned by the ultrasonic fingerprint reader. The signal flight time of each background image to be stored is the acquisition flight time. In the disclosed embodiments, the disclosed method for collecting background images to be stored is used to set different collection conditions to collect background images to be stored. Subsequently, a background image library containing diverse background images can be constructed. This provides a basis for selecting a target background image that most closely matches the response characteristics of a fingerprint image, avoids background interference caused by different collection conditions, reduces background image noise, improves finger-level recognition accuracy, and ensures accurate finger-level recognition.Furthermore, the disclosed method can be executed periodically to update the background image data in real time, ensuring accurate finger-level recognition. Furthermore, when constructing a background image library using the background images to be stored collected using the method for collecting background images to be stored, similar to the method for matching target background images from a background image library, a sub-library is first determined based on the first feature. Then, based on whether the sub-library is full and whether existing background images in the sub-library overlap with the background image to be stored, a determination is made as to whether the background image to be stored should be stored. This process is repeated to determine a background image library using the background images to be stored collected using the method for collecting background images to be stored. As shown in FIG11 , the method for storing background images to be stored includes the following steps: Step 1101: Receive the background image to be stored. Step 1102: Match the background image to be stored to a second target sub-library from the background image library based on the first feature of each sub-library, and store the background image to be stored in the second target sub-library. In an embodiment of the present disclosure, the system chip matches a target sub-library for a background image to be stored in the background image library based on the first feature, and stores the background image to be stored in the target sub-library. Furthermore, as shown in FIG12 , the method for storing background images to be stored in the present disclosure includes the following steps: Step 1201: Calculating image similarity between the background image to be stored and each background image in the target sub-library. In an embodiment of the present disclosure, the image similarity between the background image to be stored and each background image in the target sub-library is calculated using the image similarity determination method disclosed in the present disclosure. Step 1202: Determine whether the image similarity exceeds a preset similarity threshold. If so, proceed to step 1203; if not, proceed to step 1204. In step 1203, background images exceeding the preset similarity threshold are deleted and the background image to be stored is added to the target sub-library. In the disclosed embodiment, if the image similarity between the background image and the background image to be stored exceeds a preset similarity threshold, it indicates that a duplicate image of the background image to be stored exists in the target sub-library. Therefore, the duplicate image is deleted and the background image to be stored is stored in the target sub-library. Furthermore, if the image similarity between the background image and the background image to be stored exceeds a preset similarity threshold, the background image to be stored may be rejected and the storage result for the background image to be stored may be determined as storage failure.Step 1204 determines whether the number of images in the target sub-library equals the sub-library capacity. If so, the process proceeds to step 1205; if not, the process proceeds to step 1207. In this embodiment, if the image similarity between the background image and the background image to be added does not exceed a preset similarity threshold, the process determines whether the target sub-library is full. Step 1205 selects the target sub-library for background images to be deleted that meet the deletion criteria. In this embodiment, if the number of images in the target sub-library equals the sub-library capacity, this indicates that the target sub-library is full. Therefore, some images need to be deleted to free up space for the background images to be added, ensuring real-time updates of the background image library. Deletion conditions may include the earliest entry time, the latest entry time, the earliest acquisition time, the latest acquisition time, the most concentrated distribution of image features other than the first feature, the most concentrated distribution of image features other than the first and second features, and the greatest image similarity to the background image to be stored. For example, the first and second features of a sub-library may be the signal flight time and signal transmission frequency, respectively, and the image features other than the first and second features may include the acquisition time and temperature. The deletion condition may be the most concentrated acquisition temperature and / or the most concentrated acquisition time. Step 1206: Delete the background image to be deleted from the target sub-library, and decrement the number of images in the target sub-library. Step 1207: Add the background image to be stored to the target sub-library. In this embodiment of the present disclosure, if the number of images in the target sub-library is not equal to the sub-library capacity, indicating that the sub-library can accommodate the new image, the background image to be stored may be directly added to the target sub-library. Alternatively, after deleting the background image to be deleted from the target sub-library, the background image to be stored is added to the target sub-library. Step 1208: The number of images in the target sub-library is incremented. In this embodiment, after adding the background image to be stored to the target sub-library, the number of images in the target sub-library is incremented. In this embodiment, the disclosed method for storing background images to be stored determines whether to directly store the background image to be stored or to first delete a portion of existing background images to free up memory before adding the background image to the target sub-library, depending on whether the target sub-library is full. This allows for flexible adaptation to the fingerprint recognition environment to update the background image library, matching the target background image with the closest matching parameter characteristics to the fingerprint image, ensuring accurate background signal removal and finger-level signal recognition, and improving finger-level recognition accuracy.Step 103: Subtract the fingerprint image from the target background image to obtain a to-be-identified fingerprint image of the finger level. In the disclosed embodiment, the system chip subtracts the fingerprint image from the target background image to obtain a to-be-identified fingerprint image containing only accurate fingerprint level signals. This is used in subsequent scenarios such as unlocking and payment, improving fingerprint recognition efficiency and ensuring accuracy. Furthermore, because the background image library is pre-generated, even for the user's first press, an accurate target background image can be recommended for the fingerprint image. After subtraction, a clean to-be-identified fingerprint signal is obtained to accurately identify the finger level. Furthermore, because the background image library is continuously updated, the parameter characteristics of various background images obtained from the background image library can be infinitely close to the mixed signal, significantly reducing the difference between the background signal of the target background image and the background signal in the mixed signal. This reduces signal interference from background removal, resulting in a highly accurate to-be-identified fingerprint image. This, in turn, improves fingerprint recognition accuracy, avoids the frequent occurrence of unauthorized recognition and unlock failures, and enhances user convenience in various scenarios. In the disclosed embodiments, the disclosed method for generating finger-level images can avoid background signal interference caused by environmental and thickness variations in ultrasonic signals. In any finger-level recognition environment, the target background image that most closely matches the fingerprint image's response characteristics can be selected from a background image library based on signal transmission frequency, signal flight time, and / or acquisition time to accurately separate the fingerprint signal. This eliminates initial recognition failures caused by the inability to perform differential identification due to the absence of a background image. Background signal noise interference is significantly reduced, resulting in clear and precise fingerprint images and high recognition accuracy. This prevents frequent unauthorized recognition and unlocking failures, improving user convenience and success rates in various scenarios such as finger-level unlocking and payment. Figure 13 is a schematic diagram of the main modules of a device for generating fingerprint images to be recognized according to an embodiment of the disclosed embodiment. As shown in Figure 13, the disclosed device 1300 for generating fingerprint images to be recognized includes: an acquisition module 1301 for acquiring a finger-level fingerprint image in response to a recognition instruction issued by a user's finger touch. Matching module 1302 is configured to use the signal flight time and signal transmission frequency of the finger-level image to match the target background image of the fingerprint paper image from a background image library. Data processing module 1303 is configured to perform a subtraction between the fingerprint image and the target background image to obtain a finger-level image of the finger.The exemplary embodiments of the present disclosure further provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor. When executed by the at least one processor, the computer program causes the electronic device to perform a method according to an embodiment of the present disclosure. The exemplary embodiments of the present disclosure further provide a non-transitory computer-readable storage medium storing the computer program. When executed by a computer processor, the computer program causes the computer to perform a method according to an embodiment of the present disclosure. The exemplary embodiments of the present disclosure further provide a computer program product comprising the computer program. When executed by a computer processor, the computer program causes the computer to perform a method according to an embodiment of the present disclosure. Referring to FIG. 14 , a block diagram of an electronic device 1400 that can serve as a server or client of the present disclosure will now be described. This is an example of a hardware device that can be applied to various aspects of the present disclosure. The term "electronic device" is intended to refer to various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. An electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components, their connections and relationships, and their functions shown herein are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein. As shown in FIG14 , electronic device 1400 includes a computing unit 1401, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 1402 or loaded from a storage unit 1408 into a random access memory (RAM) 1403. RAM 1403 may also store various programs and data required for the operation of device 1400. Computing unit 1401, ROM 1402, and RAM 1403 are interconnected via a bus 1404.An input / output (I / O) interface 1405 is also connected to bus 1404. Multiple components within electronic device 1400 are connected to I / O interface 1405, including an input unit 1406, an output unit 1407, a storage unit 1408, and a communication unit 1409. Input unit 1406 can be any type of device capable of inputting information into electronic device 1400. Input unit 1406 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 1407 can be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 1408 may include, but is not limited to, a magnetic disk or an optical disk. The communication unit 1409 allows the electronic device 1400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like. The computing unit 1401 may be various general-purpose and / or specialized processing components having processing and computing capabilities. Some examples of the computing unit 1401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1401 performs the various methods and processes described above. For example, in some embodiments, the methods of Figures 1 and 4 to 12 may be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 1408. In some embodiments, part or all of the computer program may be loaded and / or installed into the electronic device 1400 via the ROM 1402 and / or the communication unit 1409. In some embodiments, the computing unit 1401 may be configured to perform the methods of Figures 1 and 4 to 12 in any other appropriate manner (e.g., by means of firmware). The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages.These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server. In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or apparatus (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor. To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer.Other types of devices may also be used to provide user interaction; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and user input may be received in any form (including acoustic input, voice input, or tactile input). The systems and techniques described herein may be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected via any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet. A computer system may include clients and servers. The clients and servers are generally remote from each other and typically interact via a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

Claims

29 Claims 1. A method for generating a fingerprint image to be identified, characterized in that: include: Collect a fingerprint image of a finger fingerprint; use the first feature of the finger-level image to match the target background image of the finger-level image from a background image library; wherein the first feature of the fingerprint image is at least one of the signal flight time of the ultrasonic signal that generates the finger-level image, the signal transmission frequency of the ultrasonic signal that generates the finger-level image, or the acquisition time of the fingerprint image; subtract the fingerprint image from the target background image to obtain the finger-level image to be identified of the finger.

2. The generation method according to claim 1, characterized in that The background image library includes multiple sub-libraries, and the multiple sub-libraries are distinguished by the feature value of a first feature. The first feature of the sub-library is the signal flight time of the ultrasonic signal that generates the background image in the sub-library, the signal transmission frequency of the ultrasonic signal that generates the background image in the sub-library, or the acquisition time of the background image in the sub-library. Matching the target background image of the fingerprint image from the background image library using the first feature of the finger-level image includes: comparing the first feature of the finger-level image with the first feature of the sub-library to determine a first target sub-library, wherein the feature value of the first feature of the fingerprint image is equal to or falls within the feature value of the first feature of the first target sub-library; determining whether the first target sub-library has one image; if the first target sub-library has one image, the background image in the first target sub-library is the target background image; if the first target sub-library has multiple images, comparing the second feature of the finger-level image with the second feature of the background images in the first target sub-library to determine the first target background image; the feature value of the second feature of the fingerprint image is equal to or falls within the feature value of the second feature of the first target background image; wherein The second feature of the finger-level image is one of a signal flight time of an ultrasonic signal used to generate the fingerprint image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, an acquisition time of the fingerprint image, and a grayscale value matrix of the fingerprint image; the second feature of the background image is one of a signal flight time of an ultrasonic signal used to generate the fingerprint image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, an acquisition time of the fingerprint image, and a grayscale value matrix of the fingerprint image, and the second feature is different from the first feature; when the number of the first target background image is one, the first target background image is determined to be the target background image; 30. When there are multiple images of the first target background image, a third feature of the fingerprint image is compared with the third feature of the first target background image to determine a second target background image; a feature value of the third feature of the fingerprint image is equal to or falls within the feature value of the third feature of the second target background image; wherein the third feature of the fingerprint image is one of a signal flight time of an ultrasonic signal used to generate the fingerprint image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, an acquisition time of the fingerprint image, and a grayscale value matrix of the fingerprint image; and the third feature of the first target background image is one of a signal flight time of an ultrasonic signal used to generate the first target background image, a signal transmission frequency of the ultrasonic signal used to generate the first target background image, an acquisition time of the first target background image, and a grayscale value matrix of the first target background image, and the third feature is different from the first feature and the second feature; when there is only one image of the second target background image, the second target background image is determined to be the target background image; when there are multiple images of the second target background image, a fourth feature of the fingerprint image is compared with the fourth feature of the second target background image to determine a third target background image; The characteristic value of the fourth feature of the fingerprint image is equal to or falls within the characteristic value of the fourth feature of the third target background image; wherein the fourth feature of the finger-level image is one of the signal flight time of the ultrasonic signal generating the finger-level image, the signal transmission frequency of the ultrasonic signal generating the fingerprint image, the acquisition time of the fingerprint image, and the grayscale value matrix of the finger-level image; the fourth feature of the second target background image is one of the signal flight time of the ultrasonic signal generating the second target background image, the signal transmission frequency of the ultrasonic signal generating the second target background image, the acquisition time of the second target background image, and the grayscale value matrix of the second target background image, and the fourth feature is different from the first feature, the second feature, and the third feature; when there is only one third target background image, the third target background image is determined to be the target background image; when there are multiple third target background images, the target background image is determined from the multiple third target background images using a weighted comparison method or a peak signal-to-noise ratio comparison method.

3. The generation method according to claim 2, characterized in that In the case where the second feature is a gray value matrix, comparing the second feature of the fingerprint image with the second feature of the background images in the first target sub-image library to determine the first target background image includes: calculating the gray value matrix of the fingerprint image and the gray value matrix of each background image in the first target sub-image library; wherein, when the third feature is a gray value matrix, the comparing the third feature of the finger-level image with the third feature of the first target background image to determine the second target background image comprises: calculating the image similarity between the gray value matrix of the fingerprint image and the gray value matrix of the first target background image, and determining the second target background image according to the minimum value of the image similarity; and wherein, when the fourth feature is a gray value matrix, the comparing the fourth feature of the finger-level image with the fourth feature of the second target background image to determine the third target background image comprises: calculating the image similarity between the gray value matrix of the fingerprint image and the gray value matrix of the second target background image, and determining the third target background image according to the minimum value of the image similarity.

4. The generation method according to claim 2, characterized in that The first feature is signal flight time, and the second feature is signal transmission frequency, or the first feature is signal transmission frequency, and the second feature is signal flight time.

5. The generation method according to claim 1, characterized in that The background image library includes multiple sub-libraries, and the multiple sub-libraries are distinguished by feature values of a first feature and a second feature. The first feature and the second feature of the sub-library are two of the signal flight time of the ultrasonic signal that generates the background image in the sub-library, the signal transmission frequency of the ultrasonic signal that generates the background image in the sub-library, the acquisition time of the background image in the sub-library, and the acquisition temperature of the environment in which the electronic device that generates the background image in the sub-library is located.

6. The generation method according to claim 5, characterized in that The first feature and the second feature of the finger-level image are two of the signal flight time of the ultrasonic signal generating the fingerprint image, the signal transmission frequency of the ultrasonic signal generating the fingerprint image, the acquisition time of the finger-level image, or the acquisition temperature of the environment in which the electronic device generating the fingerprint image is located; the use of the first feature of the finger-level image to match the target background image of the fingerprint image from the background image library includes: respectively comparing the first feature and the second feature of the finger-level image with the first feature and the second feature of the sub-image library to determine a first target sub-image library; the first feature of the finger-level image is equal to or falls within the feature value of the first feature of the first target sub-image library, and the second feature of the finger-level image is matched with the target background image of the fingerprint image from the background image library. determining whether the first target sub-library has one image; if the first target sub-library has one image, the background image in the first target sub-library is the target background image; if the first target sub-library has multiple images, comparing the third feature of the finger-level image with the third feature of the background images in the first target sub-library to determine the first target background image; the third feature of the finger-level image is equal to or falls within the feature value of the third feature of the first target background image; wherein the third feature of the fingerprint image is one of the signal flight time of the ultrasonic signal generating the finger-level image, the signal transmission frequency of the ultrasonic signal generating the fingerprint image, the acquisition time of the finger-level image, the acquisition temperature of the finger-level image, and the grayscale value matrix of the fingerprint image; the third feature of the background image is one of the signal flight time of the ultrasonic signal generating the background image, the signal transmission frequency of the ultrasonic signal generating the background image, the acquisition time of the background image, the acquisition temperature of the background image, and the grayscale value matrix of the background image, and the third feature is different from the first and second features; When there is only one target background image, the first target background image is determined to be the target background image; when there are multiple first target background images, a fourth feature of the finger-level image is compared with the fourth feature of the first target background image to determine a second target background image; the fourth feature of the finger-level image is equal to or falls within the feature value of the fourth feature of the second target background image; wherein the fourth feature of the finger-level image is one of a signal flight time of an ultrasonic signal used to generate the finger-level image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, an acquisition time of the finger-level image, an acquisition temperature of the finger-level image, and a grayscale value matrix of the finger-level image; the fourth feature of the first target background image is one of a signal flight time of an ultrasonic signal used to generate the first target background image, a signal transmission frequency of the ultrasonic signal used to generate the first target background image, an acquisition time of the first target background image, an acquisition temperature of the first target background image, and a grayscale value matrix of the first target background image, and the fourth feature is different from the first feature, the second feature, and the third feature;When the number of the second target background image is one, the second target background image is determined to be the target background image. When the number of the second target background image is multiple, the fifth feature of the finger-level image is compared with the fifth feature of the second target background image to determine the third target background image. The fifth feature of the finger-level image is equal to or falls within the feature value of the fifth feature of the third target background image. The fifth feature of the finger-level image is the ultrasonic signal used to generate the finger-level image. 33, the signal flight time of the ultrasonic signal used to generate the finger-level image, the acquisition time of the fingerprint image, the acquisition temperature of the fingerprint image, and the grayscale value matrix of the fingerprint image; the fifth feature of the second target background image is one of the signal flight time of the ultrasonic signal used to generate the second target background image, the signal emission frequency of the ultrasonic signal used to generate the second target background image, the acquisition time of the second target background image, the acquisition temperature of the second target background image, and the grayscale value matrix of the second target background image, and the fifth feature is different from the first feature, the second feature, the third feature, and the fourth feature; when there is only one third target background image, the third target background image is determined as the target background image; when there are multiple third target background images, the target background image is determined from the multiple third target background images using a weighted comparison method or a peak signal-to-noise ratio comparison method.

7. The generation method according to claim 6, characterized in that: In a case where the third feature is a gray value matrix, the comparing the third feature of the finger-level image with the third feature of the background images in the first target sub-image library to determine the first target background image includes: calculating image similarity between the gray value matrix of the finger-level image and the gray value matrices of each background image in the first target sub-image library, and determining the first target background image based on the minimum value of the image similarities; In a case where the fourth feature is a gray value matrix, the comparing the fourth feature of the finger-level image with the fourth feature of the first target background image to determine the second target background image includes: calculating image similarity between the gray value matrix of the finger-level image and the gray value matrix of the first target background image, and determining the second target background image based on the minimum value of the image similarity; In a case where the fifth feature is a gray value matrix, the comparing the fifth feature of the finger-level image with the fifth feature of the second target background image to determine the third target background image includes: calculating image similarity between the gray value matrix of the fingerprint image and the gray value matrix of the second target background image, and determining the third target background image based on the minimum value of the image similarity.

8. The generation method according to any one of claims 3, 6 to 7, characterized in that: described 34. Calculating the image similarity between the grayscale value matrix of the finger-level image and the grayscale value matrix of each background image in the first target sub-library, the first target background image, or the second target background image, including: for each background image in the first target sub-library, the first target background image, or the second target background image, respectively calculating the average value of the matrix elements in the grayscale value matrix of the finger-level image and the background image, respectively obtaining a first average value and a second average value, calculating a first variance of the matrix elements in the grayscale value matrix of the finger-level image and a second variance of the matrix elements in the grayscale value matrix of the background image; expanding the grayscale value matrices of the finger-level image and the background image into a one-dimensional first conversion grayscale value matrix and a second conversion grayscale value matrix, and calculating the covariance of the first conversion grayscale value matrix and the second conversion grayscale value matrix; selecting a constant coefficient one and a constant coefficient two, and determining a first constant and a second constant according to the square of the maximum difference between the grayscale values of each matrix element in the fingerprint image and the background image and the product of the constant coefficient one and the constant coefficient two; using the first average value, The image similarity between the finger-level image and the background image is determined by using the second mean, the covariance, the first variance, the second variance, the first constant, and the second constant.

9. The generation method according to claim 2 or 6, characterized in that Determining the target background image from the plurality of third target background images using a weight comparison method includes: selecting one or more target features from each feature of the sub-image library, and determining an image weight of each of the third target background images based on a plurality of target feature distances between the target feature of the finger-level image and the target features of the plurality of third target background images; the target feature of the finger-level image is a signal flight time of an ultrasonic signal used to generate the fingerprint image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, an acquisition time of the finger-level image, a grayscale value matrix of the finger-level image, or an acquisition temperature of an environment in which an electronic device used to generate the fingerprint image is located; and the target feature of the third target background image is a signal flight time of an ultrasonic signal used to generate the third target background image, a signal transmission frequency of the ultrasonic signal used to generate the third target background image, an acquisition time of the third target background image, a grayscale value matrix of the third target background image, or an acquisition temperature of an environment in which an electronic device used to generate the third target background image is located; and performing weighted calculation on the grayscale value matrices of the plurality of third target background images according to the image weight of each third target background image.

35. The weighted result of the weighted calculation is used as the target background image.

10. The generation method according to claim 2 or 6, characterized in that The method of determining the target background image from the plurality of third target background images by using a peak signal-to-noise ratio comparison method includes: calculating, for each third target background image, a mean square difference between the third target background image and the finger-level image based on the grayscale values of each pixel in the third target background image and the finger-level image; performing a logarithmic transformation on the ratio of the maximum grayscale value of the pixel in the fingerprint image to the mean square difference to obtain a peak signal-to-noise ratio between the third target background image and the finger-level image; and using the third target background image corresponding to the minimum value among the plurality of peak signal-to-noise ratios as the target background image.

11. The generation method according to claim 1, characterized in that The background image library includes multiple sub-libraries, and the multiple sub-libraries are distinguished by the characteristic value of the first feature. The first feature of the sub-library is the signal flight time of the ultrasonic signal that generates the background image in the sub-library, the signal transmission frequency of the ultrasonic signal that generates the background image in the sub-library, or the acquisition time of the background image in the sub-library; Generating the background image library includes: collecting background images to be stored under different environmental conditions and thickness conditions; the thickness condition includes at least one of film thickness, screen thickness, and acoustic layer thickness; and the environmental conditions include at least one of geographic location, ambient temperature, ambient brightness, ambient humidity, and ambient air pressure; matching the background images to be stored with a second target sub-library from the background image library based on the first feature of each sub-library, and storing the background images to be stored in the second target sub-library.

12. The generation method according to claim 5, characterized in that Generating the background image library includes: collecting background images to be stored under different environmental conditions and thickness conditions; the thickness condition includes at least one of film thickness, screen thickness, and acoustic layer thickness; and the environmental conditions include at least one of geographic location, ambient temperature, ambient brightness, ambient humidity, and ambient air pressure; matching the background images to be stored with a second target sub-library from the background image library based on the first and second characteristics of each sub-library, and storing the background images to be stored in the second target sub-library.

13. The generation method according to claim 11 or 12, characterized in that: The step of storing the background image to be stored in the second target sub-image library includes:

36. Determine whether the image similarity between the background image to be stored and each background image in the second target sub-library exceeds a preset similarity threshold; if the similarity exceeds the preset similarity threshold, delete the background image that exceeds the preset similarity threshold, add a collection time to the background image to be stored, and store it in the second target sub-library.

14. The generation method according to claim 13, characterized in that When the preset similarity threshold is not exceeded, the method further includes: determining whether the number of images in the second target sub-library is equal to the sub-library capacity; and when the number of images in the second target sub-library is equal to the sub-library capacity, screening the background images to be deleted in the second target sub-library that meet the deletion conditions; deleting the background images to be deleted from the second target sub-library, adding the background images to be stored to the second target sub-library, and adjusting the number of images in the second target sub-library.

15. The generation method according to claim 14, characterized in that In the case that the number of images in the second target sub-library is less than the capacity of the sub-library, the background image to be stored is added to the second target sub-library, and the number of images in the second target sub-library is increased.

16. A device for generating a finger-level image to be identified, characterized in that: include: An acquisition module is configured to acquire a fingerprint image of a finger fingerprint; a matching module is configured to match a target background image of the finger-level image with a first feature of the finger-level image from a background image library; wherein the first feature of the finger-level image is at least one of a signal flight time of an ultrasonic signal used to generate the finger-level image, a signal transmission frequency of the ultrasonic signal used to generate the fingerprint image, or an acquisition time of the finger-level image; and a data processing module is configured to subtract the finger-level image from the target background image to obtain a finger-level image of the finger fingerprint to be identified.

17. An electronic device, comprising: processor; and a memory storing a program, wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the method for generating a finger-level image to be identified according to any one of claims 1-15.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method for generating a fingerprint image to be identified according to any one of claims 1 to 15.

Images