TWI818496B - Fingerprint recognition method, fingerprint module, and electronic device - Google Patents
Fingerprint recognition method, fingerprint module, and electronic device Download PDFInfo
- Publication number
- TWI818496B TWI818496B TW111112899A TW111112899A TWI818496B TW I818496 B TWI818496 B TW I818496B TW 111112899 A TW111112899 A TW 111112899A TW 111112899 A TW111112899 A TW 111112899A TW I818496 B TWI818496 B TW I818496B
- Authority
- TW
- Taiwan
- Prior art keywords
- fingerprint image
- template
- fingerprint
- image
- template fingerprint
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000006731 degradation reaction Methods 0.000 claims abstract description 43
- 230000015556 catabolic process Effects 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000003062 neural network model Methods 0.000 claims description 23
- 238000012795 verification Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 description 16
- 238000012549 training Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Landscapes
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Input (AREA)
Abstract
Description
本申請涉及指紋識別技術領域,尤其涉及一種指紋識別方法、指紋模組及電子設備。 The present application relates to the field of fingerprint identification technology, and in particular to a fingerprint identification method, fingerprint module and electronic device.
現如今,指紋驗證是智慧手機、個人電腦等智慧電子設備較為常用的用戶身份驗證方式,可應用在電子設備的解鎖、支付、登錄等應用場景。指紋識別的成功率是衡量指紋識別演算法優劣的重要指標,而在指紋識別的場景中,指紋模組容易受雜訊和外部環境的影響,例如,用戶手指經常沾有灰塵、水、污漬等異物,導致採集的指紋圖像品質較差,進而降低指紋匹配成功率。較為常用的方法是對採集的指紋圖像進行增強,然而,圖像增強在降低雜訊干擾的影響的同時,也會對圖像中指紋的細節造成損壞,進而導致指紋匹配成功率的降低。 Nowadays, fingerprint verification is a commonly used user identity verification method for smart electronic devices such as smartphones and personal computers. It can be used in application scenarios such as unlocking, payment, and login of electronic devices. The success rate of fingerprint recognition is an important indicator to measure the quality of fingerprint recognition algorithms. In fingerprint recognition scenarios, fingerprint modules are easily affected by noise and external environments. For example, users’ fingers are often stained with dust, water, stains, etc. Foreign objects cause poor quality of the collected fingerprint images, thereby reducing the success rate of fingerprint matching. A more commonly used method is to enhance the collected fingerprint images. However, while image enhancement reduces the impact of noise interference, it will also damage the details of the fingerprints in the image, thereby reducing the success rate of fingerprint matching.
有鑑於此,有必要提供一種指紋識別方法、指紋模組及電子設備,以解決上述指紋模組容易受雜訊和外部環境的影響而導致採集的指紋圖像品質較差,進而降低指紋匹配成功率的技術問題。 In view of this, it is necessary to provide a fingerprint identification method, fingerprint module and electronic equipment to solve the problem that the above fingerprint module is easily affected by noise and external environment, resulting in poor quality of collected fingerprint images, thereby reducing the success rate of fingerprint matching. technical issues.
本申請提供一種指紋識別方法,所述方法包括: 獲取用戶的至少一第一範本指紋圖像;對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像;獲取待識別的指紋圖像,基於所述至少一第一範本指紋圖像和所述至少一第二範本指紋圖像對所述待識別的指紋圖像進行驗證。 This application provides a fingerprint identification method, which method includes: Obtain at least one first template fingerprint image of the user; perform degradation processing on the first template fingerprint image to obtain at least a second template fingerprint image; obtain the fingerprint image to be identified, based on the at least one first template fingerprint image The template fingerprint image and the at least one second template fingerprint image verify the fingerprint image to be recognized.
可選地,所述獲取用戶的至少一第一範本指紋圖像包括:在錄入範本指紋時,採集用戶的至少一個手指的指紋,生成所述至少一第一範本指紋圖像。 Optionally, the obtaining at least one first template fingerprint image of the user includes: collecting the fingerprint of at least one finger of the user when entering the template fingerprint, and generating the at least one first template fingerprint image.
可選地,所述獲取用戶的至少一個第一範本指紋圖像包括:在指紋驗證時,採集用戶的至少一個手指的指紋,生成所述至少一個手指的指紋圖像;對所述指紋圖像進行識別,判斷所述指紋圖像是否與所述至少一第一範本指紋圖像匹配;若確定所述指紋圖像與所述至少一範本指紋圖像匹配,將所述指紋圖像作為所述第一範本指紋圖像。 Optionally, obtaining at least one first template fingerprint image of the user includes: during fingerprint verification, collecting the fingerprint of at least one finger of the user and generating a fingerprint image of the at least one finger; Perform identification to determine whether the fingerprint image matches the at least one first template fingerprint image; if it is determined that the fingerprint image matches the at least one template fingerprint image, use the fingerprint image as the The first template fingerprint image.
可選地,所述對所述第一範本指紋圖像進行退化處理包括:基於模糊退化模型對所述第一範本指紋圖像進行退化處理,計算所述第一範本指紋圖像中每個圖元點周圍預設數量的圖元點的圖元平均值,將所述圖元點的圖元值替換為所述圖元平均值。 Optionally, performing degradation processing on the first template fingerprint image includes: performing degradation processing on the first template fingerprint image based on a fuzzy degradation model, and calculating each image in the first template fingerprint image. The primitive average value of a preset number of primitive points around the primitive point is used to replace the primitive value of the primitive point with the primitive average value.
可選地,所述對所述第一範本指紋圖像進行退化處理包括:基於隨機雜訊退化模型對所述第一範本指紋圖像進行退化處理,設置雜訊的數值範圍,將所述數值範圍內的雜訊隨機地疊加至所述第一範本指紋圖像。 Optionally, performing degradation processing on the first template fingerprint image includes: performing degradation processing on the first template fingerprint image based on a random noise degradation model, setting a numerical range of noise, and converting the numerical value into Noise within the range is randomly superimposed on the first template fingerprint image.
可選地,對所述第一範本指紋圖像進行退化處理包括: 將所述第一範本指紋圖像輸入訓練好的神經網路模型,藉由所述訓練好的神經網路模型對所述第一範本指紋圖像進行退化處理。 Optionally, performing degradation processing on the first template fingerprint image includes: The first template fingerprint image is input into a trained neural network model, and the first template fingerprint image is degraded through the trained neural network model.
可選地,所述對所述第一範本指紋圖像進行退化處理包括:每種圖像退化模型對所述第一範本指紋圖像進行退化處理,以得到預設數量的第二範本指紋圖像。 Optionally, performing degradation processing on the first template fingerprint image includes: performing degradation processing on the first template fingerprint image using each image degradation model to obtain a preset number of second template fingerprint images. picture.
可選地,所述基於所述至少一第一範本指紋圖像和所述至少一第二範本指紋圖像對所述待識別的指紋圖像進行驗證包括:判斷所述待識別的指紋圖像是否與所述至少一第一範本指紋圖像和所述至少一第二範本指紋圖像中的至少一範本指紋圖像匹配;若確定所述待識別的指紋圖像與所述至少一個第一範本指紋圖像和所述至少一個第二範本指紋圖像中的至少一範本指紋圖像匹配,確定所述待識別的指紋圖像通過驗證;或若確定所述待識別的指紋圖像與所述至少一個第一範本指紋圖像和所述至少一個第二範本指紋圖像中的所有範本指紋圖像都不匹配,確定所述待識別的指紋圖像驗證失敗。 Optionally, the verification of the fingerprint image to be identified based on the at least one first template fingerprint image and the at least one second template fingerprint image includes: determining the fingerprint image to be identified. Whether it matches at least one of the at least one first template fingerprint image and the at least one second template fingerprint image; if it is determined that the fingerprint image to be identified matches the at least one first template fingerprint image. The template fingerprint image matches at least one of the at least one second template fingerprint image, and it is determined that the fingerprint image to be identified passes the verification; or if it is determined that the fingerprint image to be identified matches the fingerprint image to be identified, If all the template fingerprint images in the at least one first template fingerprint image and the at least one second template fingerprint image do not match, it is determined that the verification of the fingerprint image to be identified fails.
本申請還提供一種指紋模組,用於執行上述的指紋識別方法。 This application also provides a fingerprint module for performing the above fingerprint identification method.
本申請還提供一種電子設備,包括:處理器;以及記憶體,所述記憶體中存儲有複數個程式模組,所述複數個程式模組由所述處理器載入並執行上述的指紋識別方法。 This application also provides an electronic device, including: a processor; and a memory. A plurality of program modules are stored in the memory. The plurality of program modules are loaded by the processor and execute the above-mentioned fingerprint recognition. method.
本申請的指紋識別方法、指紋模組及電子設備藉由對電子設備中的範本指紋圖像進行退化處理,在擴充範本指紋圖像的同時,類比品質較差的指紋圖像,如此,在指紋識別的過程中,即使由於受到雜訊和外部環境的影響 導致採集的指紋圖像品質較差,也可以匹配成功,從而提高指紋匹配成功率,提升用戶體驗。 The fingerprint identification method, fingerprint module and electronic device of the present application perform degradation processing on the template fingerprint image in the electronic device to expand the template fingerprint image and at the same time compare the fingerprint image with poor quality. In this way, in fingerprint recognition In the process, even if it is affected by noise and external environment As a result, the quality of the collected fingerprint images is poor, but the matching can still be successful, thereby improving the success rate of fingerprint matching and improving user experience.
1:電子設備 1: Electronic equipment
10:處理器 10: Processor
20:記憶體 20:Memory
30:電腦程式 30:Computer program
40:指紋模組 40:Fingerprint module
2:伺服器 2:Server
S201-S203:步驟 S201-S203: Steps
圖1是本申請較佳實施方式提供的指紋識別方法的應用環境架構示意圖。 Figure 1 is a schematic diagram of the application environment architecture of the fingerprint identification method provided by the preferred embodiment of the present application.
圖2是本申請較佳實施方式提供的指紋識別方法的流程圖。 Figure 2 is a flow chart of the fingerprint identification method provided by the preferred embodiment of the present application.
圖3是本申請較佳實施方式提供的第一範本指紋圖像和經過模糊退化處理的第二範本指紋圖像的示意圖。 Figure 3 is a schematic diagram of a first template fingerprint image and a second template fingerprint image that has been subjected to blur degradation processing provided by the preferred embodiment of the present application.
圖4是本申請較佳實施方式提供的第一範本指紋圖像和經過隨機雜訊退化處理的第二範本指紋圖像的示意圖。 FIG. 4 is a schematic diagram of the first template fingerprint image and the second template fingerprint image that have undergone random noise degradation processing provided by the preferred embodiment of the present application.
圖5是本申請較佳實施方式提供的電子設備的結構示意圖。 Figure 5 is a schematic structural diagram of an electronic device provided by a preferred embodiment of the present application.
為了能夠更清楚地理解本申請的上述目的、特徵和優點,下面結合附圖和具體實施例對本申請進行詳細描述。需要說明的是,在不衝突的情況下,本申請的實施例及實施例中的特徵可以相互組合。 In order to more clearly understand the above objects, features and advantages of the present application, the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, as long as there is no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.
在下面的描述中闡述了很多具體細節以便於充分理解本申請,所描述的實施例僅僅是本申請一部分實施例,而不是全部的實施例。基於本申請中的實施例,本領域普通技術人員在沒有做出創造性勞動前提下所獲得的所有其他實施例,都屬於本申請保護的範圍。 Many specific details are set forth in the following description to facilitate a full understanding of the present application. The described embodiments are only some, rather than all, of the embodiments of the present application. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.
除非另有定義,本文所使用的所有的技術和科學術語與屬於本申請的技術領域的技術人員通常理解的含義相同。本文中在本申請的說明書中所使用的術語只是為了描述具體的實施例的目的,不是旨在於限制本申請。 Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing specific embodiments only and is not intended to limit the application.
請參閱圖1所示,為本申請較佳實施方式提供的指紋識別方法的應用環境架構示意圖。 Please refer to FIG. 1 , which is a schematic diagram of the application environment architecture of the fingerprint identification method provided by the preferred embodiment of the present application.
本申請中的指紋識別方法應用在電子設備1中,所述電子設備1可以與至少一個伺服器2藉由網路建立通信連接。所述網路可以是有線網路,也可以是無線網路,例如無線電、無線保真(Wireless Fidelity,WIFI)、蜂窩、衛星、廣播等。蜂窩網路可以是4G網路或5G網路。
The fingerprint identification method in this application is applied to an electronic device 1. The electronic device 1 can establish a communication connection with at least one
所述電子設備1可以為安裝有指紋識別程式的電子設備,例如智慧手機、個人電腦、伺服器等,其中,所述伺服器可以是單一的伺服器、伺服器集群等。所述伺服器2可以是單一的伺服器、伺服器集群等。
The electronic device 1 may be an electronic device installed with a fingerprint recognition program, such as a smart phone, a personal computer, a server, etc., wherein the server may be a single server, a server cluster, etc. The
請參閱圖2所示,為本申請較佳實施方式提供的指紋識別方法的流程圖。根據不同的需求,所述流程圖中步驟的順序可以改變,某些步驟可以省略。 Please refer to Figure 2, which is a flow chart of a fingerprint identification method provided in a preferred embodiment of the present application. According to different needs, the order of steps in the flow chart can be changed, and some steps can be omitted.
S201,獲取用戶的至少一第一範本指紋圖像。 S201. Obtain at least one first template fingerprint image of the user.
在一實施方式中,獲取用戶的至少一個第一範本指紋圖像包括:在錄入範本指紋時,採集用戶的至少一個手指的指紋,生成所述至少一第一範本指紋圖像。 In one embodiment, obtaining at least one first template fingerprint image of the user includes: collecting the fingerprint of at least one finger of the user when entering the template fingerprint, and generating the at least one first template fingerprint image.
例如,在用戶使用新買的電子設備時,需要在開機後錄入範本指紋,或者在用戶需要增加可進行指紋驗證的手指時,可以使用手指觸摸指紋模組,指紋模組採集所述用戶的至少一個手指的指紋,並生成所述至少一第一指紋圖像。 For example, when a user uses a newly purchased electronic device, he or she needs to enter a template fingerprint after turning it on, or when the user needs to add a finger that can be used for fingerprint verification, the user can use the finger to touch the fingerprint module, and the fingerprint module collects at least one of the user's fingerprints. a fingerprint of a finger, and generate the at least one first fingerprint image.
在一實施方式中,獲取用戶的至少一個第一範本指紋圖像還包括:在指紋驗證時,採集用戶的至少一個手指的指紋,生成所述至少一個手指的指紋圖像,對所述指紋圖像進行識別,判斷所述指紋圖像是否與所述至少一 第一範本指紋圖像匹配,若確定所述指紋圖像與所述至少一範本指紋圖像匹配,將所述指紋圖像作為所述第一範本指紋圖像。 In one embodiment, obtaining at least one first template fingerprint image of the user further includes: during fingerprint verification, collecting the fingerprint of at least one finger of the user, generating a fingerprint image of the at least one finger, and analyzing the fingerprint image. to identify the fingerprint image and determine whether the fingerprint image matches the at least one The first template fingerprint image matches. If it is determined that the fingerprint image matches the at least one template fingerprint image, the fingerprint image is used as the first template fingerprint image.
需要說明的是,在指紋驗證的過程中,用戶的手指受到外部環境的影響,容易沾上灰塵、水、污漬等異物,如果在手指沾有異物的情況下,手指指紋圖像仍然能夠與範本指紋圖像匹配,說明所述手指指紋圖像可以作為範本指紋圖像,如此,後續指紋模組在採集到同樣沾有異物的手指指紋圖像時,可以提高指紋圖像的匹配成功率。 It should be noted that during the fingerprint verification process, the user's fingers are affected by the external environment and are easily stained with dust, water, stains and other foreign matter. If the fingers are stained with foreign matter, the fingerprint image can still match the template. Fingerprint image matching indicates that the finger fingerprint image can be used as a template fingerprint image. In this way, when the subsequent fingerprint module collects finger fingerprint images that are also stained with foreign matter, the success rate of fingerprint image matching can be improved.
在另一實施方式中,獲取用戶的至少一個第一範本指紋圖像可以包括:從電子設備的記憶體中獲取預先錄入的範本指紋圖像,作為所述第一範本指紋圖像。 In another embodiment, obtaining at least one first template fingerprint image of the user may include: obtaining a pre-entered template fingerprint image from a memory of the electronic device as the first template fingerprint image.
在另一實施方式中,獲取用戶的至少一個第一範本指紋圖像可以包括:藉由網路從雲端伺服器獲取範本指紋圖像,作為所述第一範本指紋圖像。需要說明的是,用戶可以將舊電子設備中錄入的範本指紋圖像上傳至雲端伺服器,如此,在使用新的電子設備時,可以使用電子設備從雲端伺服器下載獲取所述範本指紋圖像,無需用戶重複錄入範本指紋圖像,同時避免範本資料的流失。 In another embodiment, obtaining at least one first template fingerprint image of the user may include: obtaining the template fingerprint image from a cloud server through the network as the first template fingerprint image. It should be noted that the user can upload the template fingerprint image recorded in the old electronic device to the cloud server. In this way, when using the new electronic device, the electronic device can be used to download and obtain the template fingerprint image from the cloud server. , there is no need for users to repeatedly enter template fingerprint images, and the loss of template data is avoided.
S202,對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像。 S202: Perform degradation processing on the first template fingerprint image to obtain at least one second template fingerprint image.
在一實施方式中,對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像包括:基於模糊退化模型對所述第一範本指紋圖像進行均值模糊的退化處理,得到至少一第二範本指紋圖像。 In one embodiment, performing degradation processing on the first template fingerprint image to obtain at least one second template fingerprint image includes: performing mean fuzzy degradation processing on the first template fingerprint image based on a fuzzy degradation model, At least one second template fingerprint image is obtained.
具體地,計算所述第一範本指紋圖像中每個圖元點周圍預設數量的圖元點的圖元平均值,將所述圖元點的圖元值替換為所述圖元平均值,從而得到至少一第二範本指紋圖像。其中,所述預設數量為x*x。可選地,x為3。請 參閱圖3所示,為均值模糊處理前的第一範本指紋圖像和均值模糊處理後的第二範本指紋圖像。 Specifically, calculate the primitive average value of a preset number of primitive points around each primitive point in the first template fingerprint image, and replace the primitive value of the primitive point with the primitive average value , thereby obtaining at least one second template fingerprint image. Wherein, the preset number is x*x. Optionally, x is 3. please Refer to Figure 3, which shows the first template fingerprint image before mean blur processing and the second template fingerprint image after mean blur processing.
在一實施方式中,對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像還包括:基於隨機雜訊退化模型對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像。 In one embodiment, performing degradation processing on the first template fingerprint image to obtain at least one second template fingerprint image further includes: performing degradation processing on the first template fingerprint image based on a random noise degradation model, At least one second template fingerprint image is obtained.
具體地,設置雜訊的數值範圍,將所述數值範圍內的雜訊隨機地疊加至所述第一範本指紋圖像,從而得到至少一第二範本指紋圖像。在一實施方式中,所述雜訊的數值範圍可以是圖元值範圍,藉由設置雜訊的最大圖元值和最小圖元值得到所述雜訊的數值範圍,然將隨機的圖元值疊加至所述第一範本指紋圖像。在另一實施方式中,所述雜訊(信噪比)的數值範圍也可以是分貝值範圍。請參閱圖4所示,為隨機雜訊處理前的第一範本指紋圖像和隨機雜訊處理後的第二範本指紋圖像。 Specifically, a numerical range of noise is set, and noise within the numerical range is randomly superimposed on the first template fingerprint image, thereby obtaining at least one second template fingerprint image. In one implementation, the numerical range of the noise can be a range of primitive values. The numerical range of the noise can be obtained by setting the maximum primitive value and the minimum primitive value of the noise, and then random primitives are value is superimposed onto the first template fingerprint image. In another embodiment, the numerical range of the noise (signal-to-noise ratio) may also be a decibel value range. Please refer to Figure 4, which shows the first template fingerprint image before random noise processing and the second template fingerprint image after random noise processing.
在一實施方式中,對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像包括:將所述第一範本指紋圖像輸入訓練好的神經網路模型,藉由所述訓練好的神經網路模型對所述第一範本指紋圖像進行退化處理。 In one embodiment, performing degradation processing on the first template fingerprint image to obtain at least one second template fingerprint image includes: inputting the first template fingerprint image into a trained neural network model, by The trained neural network model performs degradation processing on the first template fingerprint image.
在一實施方式中,藉由訓練資料集對一神經網路模型進行深度學習訓練,使所述神經網路模型學習從高品質到低品質的退化過程以及學習低品質圖像的特徵分佈。其中,所述訓練資料集包括複數個高品質指紋圖像和複數個低品質指紋圖像。可選地,可以藉由網路從伺服器獲取所述訓練資料集。在其他實施方式中,也可以接收用戶多次錄入的未沾有異物的指紋圖像和沾有異物的指紋圖像,將未沾有異物的複數個指紋圖像作為所述訓練資料集中的高品質指紋圖像,將沾有異物的複數個指紋圖像作為所述訓練資料集中的低品質指紋圖像。 In one embodiment, a neural network model is trained by deep learning using a training data set, so that the neural network model learns the degradation process from high quality to low quality and learns the feature distribution of low quality images. Wherein, the training data set includes a plurality of high-quality fingerprint images and a plurality of low-quality fingerprint images. Optionally, the training data set can be obtained from a server through the network. In other embodiments, it is also possible to receive fingerprint images that are not stained with foreign matter and fingerprint images that are stained with foreign matter that have been entered multiple times by the user, and use the plurality of fingerprint images that are not stained with foreign matter as high-level results in the training data set. For high-quality fingerprint images, multiple fingerprint images stained with foreign matter are used as low-quality fingerprint images in the training data set.
在一實施方式中,所述神經網路模型為卷積神經網路模型,所述神經網路模型的參數包括卷積層參數、權重、學習率、反覆運算次數等,所述卷積層參數包括卷積層數量、卷積核大小、卷積步長及填充層數。所述神經網路模型的卷積神經網路的骨幹絡可以採用AlexNet、VGG16、GoogleNet、ResNet、DenseNet、MobileNets、Ghosnet等網路模型。 In one embodiment, the neural network model is a convolutional neural network model. The parameters of the neural network model include convolution layer parameters, weights, learning rates, number of iterations, etc. The convolution layer parameters include convolution layer parameters. The number of layers, convolution kernel size, convolution step size and number of filling layers. The backbone network of the convolutional neural network of the neural network model can adopt network models such as AlexNet, VGG16, GoogleNet, ResNet, DenseNet, MobileNets, Ghosnet, etc.
具體地,所述神經網路模型的訓練過程包括:設置所述神經網路模型的初始參數,將所述訓練資料集中的高品質圖像作為所述神經網路模型的輸入資料,低品質圖像作為所述神經網路模型的輸出資料,將多組由一高品質圖像和至少一個低品質圖像組成的訓練資料登錄所述神經網路模型,所述神經網路模型提取高品質圖像的特徵和低品質圖像的特徵,並建立高品質圖像與低品質圖像之間的映射關係。藉由多組訓練資料的反覆運算,所述神經網路模型對高品質圖像與低品質圖像之間的映射關係進行更新,直至損失函數的輸出值小於輸出值,從而生成訓練好的神經網路模型。 Specifically, the training process of the neural network model includes: setting the initial parameters of the neural network model, using high-quality images in the training data set as input data of the neural network model, and using low-quality images as input data for the neural network model. As the output data of the neural network model, multiple sets of training data consisting of one high-quality image and at least one low-quality image are logged into the neural network model, and the neural network model extracts high-quality images. The characteristics of the image and the characteristics of the low-quality image, and establish the mapping relationship between the high-quality image and the low-quality image. Through repeated operations of multiple sets of training data, the neural network model updates the mapping relationship between high-quality images and low-quality images until the output value of the loss function is less than the output value, thereby generating a trained neural network model. Network model.
具體地,藉由所述訓練好的神經網路模型對所述第一範本指紋圖像進行退化處理包括:將所述第一範本指紋圖像輸入所述訓練好的神經網路模型,所述訓練好的神經網路模型提取所述第一範本指紋圖像(高品質圖像)的特徵,並根據所述高品質圖像與低品質圖像之間的映射關係生成低品質圖像的特徵,即所述第二範本指紋圖像的特徵,將生成的所述第二範本指紋圖像的特徵融合,得到所述第二範本指紋圖像。 Specifically, performing degradation processing on the first template fingerprint image through the trained neural network model includes: inputting the first template fingerprint image into the trained neural network model, the The trained neural network model extracts the features of the first template fingerprint image (high-quality image) and generates the features of the low-quality image based on the mapping relationship between the high-quality image and the low-quality image. , that is, the characteristics of the second template fingerprint image are fused with the generated characteristics of the second template fingerprint image to obtain the second template fingerprint image.
在一實施方式中,對所述第一範本指紋圖像進行退化處理,得到至少一第二範本指紋圖像還包括:每種圖像退化模型對所述第一範本指紋圖像進行退化處理,以得到預設數量的第二範本指紋圖像。 In one embodiment, performing degradation processing on the first template fingerprint image to obtain at least one second template fingerprint image further includes: performing degradation processing on the first template fingerprint image using each image degradation model, To obtain a preset number of second template fingerprint images.
在一實施方式中,上述的圖像退化模型可以對第一範本指紋圖像的全部區域或部分區域進行退化處理,以得到所述第二範本指紋圖像。 In one embodiment, the above-mentioned image degradation model can perform degradation processing on all areas or part of the first template fingerprint image to obtain the second template fingerprint image.
S203,獲取待識別的指紋圖像,基於所述至少一第一範本指紋圖像和所述至少一第二範本指紋圖像對所述待識別的指紋圖像進行驗證。 S203: Obtain the fingerprint image to be identified, and verify the fingerprint image to be identified based on the at least one first template fingerprint image and the at least one second template fingerprint image.
在一實施方式中,在解鎖、支付、登錄等需要進行指紋驗證的場景下,藉由指紋模組採集用戶的指紋圖像,並對採集的指紋圖像進行識別驗證。 In one embodiment, in scenarios such as unlocking, payment, and login that require fingerprint verification, the fingerprint image of the user is collected through a fingerprint module, and the collected fingerprint image is identified and verified.
在一實施方式中,基於所述至少一第一範本指紋圖像和所述至少一第二範本指紋圖像對所述待識別的指紋圖像進行驗證包括:判斷所述待識別的指紋圖像是否與所述至少一第一範本指紋圖像和所述至少一第二範本指紋圖像中的至少一範本指紋圖像匹配。若確定所述待識別的指紋圖像與所述至少一個第一範本指紋圖像和所述至少一個第二範本指紋圖像中的至少一範本指紋圖像匹配,確定所述待識別的指紋圖像通過驗證。若確定所述待識別的指紋圖像與所述至少一個第一範本指紋圖像和所述至少一個第二範本指紋圖像中的所有範本指紋圖像都不匹配,確定所述待識別的指紋圖像驗證失敗。 In one embodiment, verifying the fingerprint image to be identified based on the at least one first template fingerprint image and the at least one second template fingerprint image includes: determining the fingerprint image to be identified Whether it matches at least one template fingerprint image among the at least one first template fingerprint image and the at least one second template fingerprint image. If it is determined that the fingerprint image to be identified matches at least one of the at least one first template fingerprint image and the at least one second template fingerprint image, determine the fingerprint image to be identified. Like verified. If it is determined that the fingerprint image to be identified does not match all template fingerprint images in the at least one first template fingerprint image and the at least one second template fingerprint image, determine that the fingerprint to be identified is Image verification failed.
需要說明的是,由於所述第二範本指紋圖像基於對所述第一範本指紋圖像進行退化生成,所述第二範本指紋圖像與所述第一範本指紋圖像的區別僅在於圖像品質的差異,指紋紋路仍然不變,如此,可以用來作為範本指紋圖像,在保障隱私安全的前提下,擴充範本指紋圖像,類比不同雜訊或外部環境下的指紋圖像,提高了指紋驗證過程中的指紋匹配成功率。 It should be noted that since the second template fingerprint image is generated based on the degradation of the first template fingerprint image, the difference between the second template fingerprint image and the first template fingerprint image is only in the figure. Like the difference in quality, the fingerprint texture remains unchanged. In this way, it can be used as a template fingerprint image. On the premise of ensuring privacy and security, the template fingerprint image can be expanded to compare with fingerprint images under different noise or external environments to improve the quality of the fingerprint image. The fingerprint matching success rate in the fingerprint verification process is improved.
請參閱圖5所示,為本申請較佳實施方式提供的電子設備的結構示意圖。 Please refer to FIG. 5 , which is a schematic structural diagram of an electronic device provided by a preferred embodiment of the present application.
所述電子設備1包括,但不僅限於,處理器10、記憶體20、存儲在所述記憶體20中並可在所述處理器10上運行的電腦程式30及指紋模組40。例如,所述電腦程式30為指紋識別程式。所述處理器10執行所述電腦程式30時實現指紋識別方法中的步驟,例如圖2所示的步驟S201~S203。
The electronic device 1 includes, but is not limited to, a
示例性的,所述電腦程式30可以被分割成一個或複數個模組/單元,所述一個或者複數個模組/單元被存儲在所述記憶體20中,並由所述處理器10執行,以完成本申請。所述一個或複數個模組/單元可以是能夠完成特定功能的一系列電腦程式指令段,所述指令段用於描述所述電腦程式30在所述電子設備1中的執行過程。
Exemplarily, the
本領域技術人員可以理解,所述示意圖僅僅是電子設備1的示例,並不構成對電子設備1的限定,可以包括比圖示更多或更少的部件,或者組合某些部件,或者不同的部件,例如所述電子設備1還可以包括輸入輸出設備、網路接入設備、匯流排等。 Those skilled in the art can understand that the schematic diagram is only an example of the electronic device 1 and does not constitute a limitation of the electronic device 1. It may include more or fewer components than shown in the diagram, or some components may be combined or different. Components, for example, the electronic device 1 may also include input and output devices, network access devices, buses, etc.
所述處理器10可以是中央處理單元(Central Processing Unit,CPU),還可以是其他通用處理器、數位訊號處理器(Digital Signal Processor,DSP)、專用積體電路(Application Specific Integrated Circuit,ASIC)、現成可程式設計閘陣列(Field-Programmable Gate Array,FPGA)或者其他可程式設計邏輯器件、分立門或者電晶體邏輯器件、分立硬體元件等。通用處理器可以是微處理器或者所述處理器10也可以是任何常規的處理器等,所述處理器10是所述電子設備1的控制中心,利用各種介面和線路連接整個電子設備1的各個部分。
The
所述記憶體20可用於存儲所述電腦程式30和/或模組/單元,所述處理器10藉由運行或執行存儲在所述記憶體20內的電腦程式和/或模組/單元,以及調用存儲在記憶體20內的資料,實現所述電子設備1的各種功能。所述記憶體20可主要包括存儲程式區和存儲資料區,其中,存儲程式區可存儲作業系統、至少一個功能所需的應用程式(比如聲音播放功能、圖像播放功能等)等;存儲資料區可存儲根據電子設備1的使用所創建的資料(比如音訊資料、電話本等)等。此外,記憶體20可以包括易失性和非易失性記憶體,例如硬碟、記憶體、插接式硬碟,智慧存儲卡(Smart Media Card,SMC),安全數位(Secure Digital,
SD)卡,快閃記憶體卡(Flash Card)、至少一個磁碟記憶體件、快閃記憶體器件、或其他記憶體件。
The
所述指紋模組40至少包括指紋採集單元和圖像生成單元,所述指紋採集單元用於接受手指的觸摸,並採集手指指紋,所述圖像生成單元用於基於採集的手指指紋紋路生成指紋圖像。
The
在一實施例中,所述指紋模組40為一獨立的指紋識別晶片,可以獨立執行所述指紋識別方法,即,可以獨立實現圖2所示的步驟S201~S203。
In one embodiment, the
所述電子設備1集成的模組/單元如果以軟體功能單元的形式實現並作為獨立的產品銷售或使用時,可以存儲在一個電腦可讀取存儲介質中。基於這樣的理解,本申請實現上述實施例方法中的全部或部分流程,也可以藉由電腦程式來指令相關的硬體來完成,所述的電腦程式可存儲於一電腦可讀存儲介質中,所述電腦程式在被處理器執行時,可實現上述各個方法實施例的步驟。其中,所述電腦程式包括電腦程式代碼,所述電腦程式代碼可以為原始程式碼形式、物件代碼形式、可執行檔或某些中間形式等。所述電腦可讀介質可以包括:能夠攜帶所述電腦程式代碼的任何實體或裝置、記錄介質、隨身碟、移動硬碟、磁碟、光碟、電腦記憶體、唯讀記憶體(ROM,Read-Only Memory)、隨機存取記憶體(RAM,Random Access Memory)。 If the integrated modules/units of the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the above embodiment methods by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in the form of original program code, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a flash drive, a mobile hard drive, a magnetic disk, an optical disk, computer memory, and read-only memory (ROM, Read-only memory). Only Memory), random access memory (RAM, Random Access Memory).
本申請提供的指紋識別方法、指紋模組及電子設備藉由對電子設備中的範本指紋圖像進行退化處理,在擴充範本指紋圖像的同時,類比品質較差的指紋圖像,如此,在指紋識別的過程中,即使由於受到雜訊和外部環境的影響導致採集的指紋圖像品質較差,也可以匹配成功,從而提高指紋匹配成功率,提升用戶體驗。 The fingerprint identification method, fingerprint module and electronic device provided by this application perform degradation processing on the template fingerprint image in the electronic device, while expanding the template fingerprint image, and at the same time, compare the fingerprint image with poor quality. In this way, in the fingerprint During the identification process, even if the quality of the collected fingerprint images is poor due to the influence of noise and external environment, the matching can still be successful, thereby increasing the success rate of fingerprint matching and improving user experience.
對於本領域技術人員而言,顯然本申請不限於上述示範性實施例的細節,而且在不背離本申請的精神或基本特徵的情況下,能夠以其他的具體 形式實現本申請。因此,無論從哪一點來看,均應將實施例看作是示範性的,而且是非限制性的,本申請的範圍由所附申請專利範圍而不是上述說明限定,因此旨在將落在申請專利範圍的等同要件的含義和範圍內的所有變化涵括在本申請內。不應將申請專利範圍中的任何附圖標記視為限制所涉及的申請專利範圍。此外,顯然“包括”一詞不排除其他單元或步驟,單數不排除複數。裝置申請專利範圍中陳述的複數個單元或裝置也可以由同一個單元或裝置藉由軟體或者硬體來實現。第一,第二等詞語用來表示名稱,而並不表示任何特定的順序。 It is obvious to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, and can be embodied in other specific forms without departing from the spirit or essential characteristics of the present application. Form implementation of this application. Therefore, the embodiments should be regarded as illustrative and non-restrictive from any point of view, and the scope of the present application is defined by the appended patent scope rather than the above description, and it is therefore intended that the scope of the application fall within the scope of the application. All changes within the meaning and scope of equivalent elements of the patent scope are included in this application. Any reference signs in a claim shall not be construed as limiting the scope of the claim concerned. Furthermore, it is clear that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device patent scope may also be implemented by the same unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any specific order.
綜上所述,本發明符合發明專利要件,爰依法提出專利申請。惟,以上所述者僅為本發明之較佳實施方式,舉凡熟悉本案技藝之人士,於爰依本發明精神所作之等效修飾或變化,皆應涵蓋於以下之申請專利範圍內。 To sum up, this invention meets the requirements for an invention patent and a patent application should be filed in accordance with the law. However, the above are only the preferred embodiments of the present invention. Anyone familiar with the art of this case will find equivalent modifications or changes made in accordance with the spirit of the present invention, and they should be covered by the following patent applications.
S201-S203:步驟 S201-S203: Steps
Claims (9)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210101467.X | 2022-01-27 | ||
CN202210101467.XA CN114299555A (en) | 2022-01-27 | 2022-01-27 | Fingerprint identification method, fingerprint module and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202244758A TW202244758A (en) | 2022-11-16 |
TWI818496B true TWI818496B (en) | 2023-10-11 |
Family
ID=80978150
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111112899A TWI818496B (en) | 2022-01-27 | 2022-04-01 | Fingerprint recognition method, fingerprint module, and electronic device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114299555A (en) |
TW (1) | TWI818496B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117711031A (en) * | 2023-08-03 | 2024-03-15 | 荣耀终端有限公司 | Fingerprint matching method and electronic equipment |
CN117711032A (en) * | 2023-08-18 | 2024-03-15 | 荣耀终端有限公司 | Fingerprint identification method and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108960214A (en) * | 2018-08-17 | 2018-12-07 | 中控智慧科技股份有限公司 | Fingerprint enhancement binarization method, device, equipment, system and storage medium |
CN110326001A (en) * | 2016-12-08 | 2019-10-11 | 维里迪乌姆Ip有限责任公司 | The system and method for executing the user authentication based on fingerprint using the image captured using mobile device |
TW202139057A (en) * | 2020-04-08 | 2021-10-16 | 大陸商上海耕岩智能科技有限公司 | Fingerprint Matching Method And Apparatus, Electronic Equipment And Readable Storage Medium |
US20210397813A1 (en) * | 2020-06-22 | 2021-12-23 | Samsung Display Co., Ltd. | Fingerprint authentication device, display device including the same, and method of authenticating fingerprint |
-
2022
- 2022-01-27 CN CN202210101467.XA patent/CN114299555A/en active Pending
- 2022-04-01 TW TW111112899A patent/TWI818496B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110326001A (en) * | 2016-12-08 | 2019-10-11 | 维里迪乌姆Ip有限责任公司 | The system and method for executing the user authentication based on fingerprint using the image captured using mobile device |
CN108960214A (en) * | 2018-08-17 | 2018-12-07 | 中控智慧科技股份有限公司 | Fingerprint enhancement binarization method, device, equipment, system and storage medium |
TW202139057A (en) * | 2020-04-08 | 2021-10-16 | 大陸商上海耕岩智能科技有限公司 | Fingerprint Matching Method And Apparatus, Electronic Equipment And Readable Storage Medium |
US20210397813A1 (en) * | 2020-06-22 | 2021-12-23 | Samsung Display Co., Ltd. | Fingerprint authentication device, display device including the same, and method of authenticating fingerprint |
Also Published As
Publication number | Publication date |
---|---|
TW202244758A (en) | 2022-11-16 |
CN114299555A (en) | 2022-04-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI818496B (en) | Fingerprint recognition method, fingerprint module, and electronic device | |
CN111967609B (en) | Model parameter verification method, device and readable storage medium | |
WO2019051941A1 (en) | Method, apparatus and device for identifying vehicle type, and computer-readable storage medium | |
CN106934376A (en) | A kind of image-recognizing method, device and mobile terminal | |
CN114764765A (en) | Image defect detection method and device, electronic equipment and storage medium | |
CN114764768A (en) | Defect detection and classification method and device, electronic equipment and storage medium | |
CN111027428A (en) | Training method and device of multi-task model and electronic equipment | |
CN110929733A (en) | Denoising method and device, computer equipment, storage medium and model training method | |
CN111027412A (en) | Human body key point identification method and device and electronic equipment | |
CN109993026B (en) | Training method and device for relative recognition network model | |
CN112037223A (en) | Image defect detection method and device and electronic equipment | |
CN110135428B (en) | Image segmentation processing method and device | |
CN110765843A (en) | Face verification method and device, computer equipment and storage medium | |
CN111815748B (en) | Animation processing method and device, storage medium and electronic equipment | |
CN115760641B (en) | Remote sensing image cloud and fog removing method and equipment based on multiscale characteristic attention network | |
TWI803243B (en) | Method for expanding images, computer device and storage medium | |
CN114241044A (en) | Loop detection method, device, electronic equipment and computer readable medium | |
CN112037814B (en) | Audio fingerprint extraction method and device, electronic equipment and storage medium | |
CN110647805B (en) | Reticulate pattern image recognition method and device and terminal equipment | |
TWI754241B (en) | A method, a device for extracting features of fingerprint images and computer-readable storage medium | |
TWI775038B (en) | Method and device for recognizing character and storage medium | |
CN111582456A (en) | Method, apparatus, device and medium for generating network model information | |
TWI786977B (en) | Finger authenticity recognition method, electronic device, and storage medium | |
CN112752098B (en) | Video editing effect verification method and device | |
CN114881864B (en) | Training method and device for seal restoration network model |