Film detection method and device, fingerprint anti-counterfeiting method and device and electronic equipment

Abstract

The embodiment of the invention provides a film detection method and device, a fingerprint anti-counterfeiting method and device and electronic equipment, the method and device are applied to the electronic equipment comprising a display screen, and the method of one embodiment comprises the steps that an optical fingerprint device is used for collecting a fingerprint subgraph of at least one light path direction of an input fingerprint; determining an actual subgraph offset according to the fingerprint subgraph of the at least one light path direction; according to the actual sub-graph offset and a reference sub-graph offset, whether the display screen is subjected to film pasting or not is judged, and the reference sub-graph offset is the sub-graph offset when the display screen is not subjected to film pasting. By adopting the embodiment, whether the display screen is pasted with the film or not can be stably and reliably detected. According to the method of another embodiment, the weight coefficient of the anti-counterfeiting index is adjusted based on whether the display screen is pasted with the film, the anti-counterfeiting score is calculated based on the anti-counterfeiting index and the weight coefficient, and the authenticity of the input fingerprint is determined based on the anti-counterfeiting score, so that the calculated anti-counterfeiting score can be matched with whether the display screen is pasted with the film, and the authenticity of the input fingerprint is determined more accurately.

Description

Technical Field

[0001] The present application relates to the field of optical fingerprint technology, and in particular to a method, device and electronic equipment for film detection and fingerprint anti-counterfeiting. Background Art

[0002] Biometric systems are widely used to improve the security of electronic devices. In particular, fingerprint recognition systems are widely used in personal electronic devices such as mobile phones. Fingerprint recognition systems can be used for electronic device unlocking, mobile payment, account login, real-name authentication, etc.

[0003] Fingerprint anti-counterfeiting is an important issue in fingerprint recognition systems. Fingerprint anti-counterfeiting refers to preventing the imitation of live fingerprints. If a live fingerprint is successfully imitated, unauthorized unlocking, payment, and account login of the system may be mistakenly approved, which may lead to serious consequences. In an optical fingerprint system, the physical feature differences between real fingers and fake fingerprints can be extracted, and the above physical feature differences are quantified, calculated, and modeled to intercept fake fingerprint attacks.

[0004] In personal electronic devices such as mobile phones, the optical fingerprint system is set under the display screen (referred to as the under-screen optical fingerprint system). Users may apply a screen protector to the display screen to protect it. The fingerprint image collected by the optical fingerprint system after the film is applied is different from that before the film is applied, which may cause the original anti-counterfeiting system to fail.

[0005] Therefore, identifying whether the display screen is covered with a film in the under-screen optical fingerprint system is an important issue in fingerprint anti-counterfeiting. In the related art, a model for identifying whether a film is covered is used to detect whether the display screen is covered with a film. The model involves relatively cumbersome model training, and the model reasoning also requires high computing resources. Therefore, there is room for improvement in the current technical solution for detecting whether the display screen is covered with a film. Summary of the invention

[0006] In view of the above problems, the embodiments of the present application provide a method, device and electronic device for film detection and fingerprint anti-counterfeiting to solve the above technical problems.

[0007] In the first aspect, the embodiment of the present application provides a method for detecting film sticking, which is applied to an electronic device including a display screen, and the method includes: using an optical fingerprint device to collect a fingerprint sub-image of at least one optical path direction of an input fingerprint; determining an actual sub-image offset according to the fingerprint sub-image of at least one optical path direction; judging whether the display screen is film-sticked according to the actual sub-image offset and the reference sub-image offset, wherein the reference sub-image offset is the sub-image offset when the display screen is not film-sticked. With this embodiment, the film sticking is used to increase the physical distance between the input fingerprint and the optical fingerprint device, thereby causing the actual sub-image offset to change relative to the sub-image offset when the film is not sticked, and judging whether the display screen is film-sticked according to the actual sub-image offset and the reference sub-image offset, it is possible to stably and reliably detect whether the display screen is film-sticked.

[0008] In some embodiments, judging whether a display screen is pasted with a film is performed based on an actual sub-image offset and a reference sub-image offset, including: determining a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; if the offset difference is greater than or equal to a film offset threshold, judging that the display screen is pasted with a film; if the offset difference is less than the film offset threshold, judging that the display screen is not pasted with a film.

[0009] In some embodiments, the above method also includes: determining the film thickness information based on the actual sub-image offset and the reference sub-image offset, including: determining the difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; determining the film thickness interval based on a comparison result of the offset difference and at least one thickness threshold, and the at least one thickness threshold divides at least two film thickness intervals.

[0010] In the second aspect, the embodiment of the present application provides a fingerprint anti-counterfeiting method, which is applied to an electronic device including a display screen, and the method includes: determining the actual sub-image offset according to the fingerprint sub-image of at least one optical path direction of the input fingerprint; judging whether the display screen is pasted with a film according to the actual sub-image offset and the reference sub-image offset, wherein the reference sub-image offset is the sub-image offset when the display screen is not pasted with a film; determining the weight coefficients of at least two anti-counterfeiting indicators according to the judgment result of whether the display screen is pasted with a film, wherein the weight coefficient when the display screen is pasted with a film is different from the weight coefficient when the display screen is not pasted with a film; determining the anti-counterfeiting score according to the at least two anti-counterfeiting indicators and the weight coefficient; determining the authenticity of the input fingerprint according to the anti-counterfeiting score. With this embodiment, it is possible to stably and reliably detect whether the display screen is pasted with a film, and adjust the weight coefficient of the anti-counterfeiting indicator based on whether the display screen is pasted with a film, so that the anti-counterfeiting score calculated can match whether the display screen is pasted with a film, and more accurately judge the authenticity of the input fingerprint.

[0011] In some embodiments, anti-counterfeiting authentication is performed on the input fingerprint based on the judgment result of whether the display screen is covered with a film, and the method also includes: determining an anti-counterfeiting score threshold based on the judgment result of whether the display screen is covered with a film, wherein the anti-counterfeiting score threshold when the display screen is covered with a film is different from the anti-counterfeiting score threshold when the display screen is not covered with a film; determining the authenticity of the input fingerprint based on the anti-counterfeiting score includes: comparing the anti-counterfeiting score with the anti-counterfeiting score threshold, and determining the authenticity of the input fingerprint based on the comparison result.

[0012] In some embodiments, weight coefficients of at least two anti-counterfeiting indicators and an anti-counterfeiting score threshold are determined based on a judgment result of whether the display screen is covered with a film, including: if the judgment result indicates that the display screen is not covered with a film, the weight coefficients of at least two anti-counterfeiting indicators are determined to be a first weight coefficient, and the anti-counterfeiting score threshold is determined to be a first anti-counterfeiting score threshold; if the judgment result indicates that the display screen is covered with a film, the weight coefficients of at least two anti-counterfeiting indicators are determined to be a second weight coefficient, and the anti-counterfeiting score threshold is determined to be a second anti-counterfeiting score threshold; wherein the first weight coefficient is different from the second weight coefficient, and the first anti-counterfeiting score threshold is different from the second anti-counterfeiting score threshold.

[0013] In some embodiments, the above method also includes: determining the film thickness information based on the actual sub-image offset and the reference sub-image offset; determining the weight coefficients of at least two anti-counterfeiting indicators and the anti-counterfeiting score threshold based on the judgment result of whether the display screen is filmed, including: if the judgment result is that the display screen is filmed, then the second weight coefficient of at least two anti-counterfeiting indicators is the weight coefficient corresponding to the film thickness information, and / or the second anti-counterfeiting score threshold is the anti-counterfeiting score threshold corresponding to the film thickness information.

[0014] In some embodiments, the film thickness information includes a film thickness interval, and the film thickness information is determined according to an actual sub-image offset and a reference sub-image offset, including: determining a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; determining the film thickness interval according to a comparison result of the offset difference and at least one thickness threshold, the at least one thickness threshold being divided into at least two film thickness intervals; wherein the second weight coefficients corresponding to any two film thickness intervals are different.

[0015] In some embodiments, the at least two anti-counterfeiting indicators include a model prediction score, which is a score indicating whether the input fingerprint is authentic and output by the model based on the fingerprint subgraphs of at least two light path directions of the input fingerprint.

[0016] In some embodiments, the weight coefficient of the model prediction score when the display screen is covered with a film is greater than the weight coefficient when the display screen is not covered with a film.

[0017] In some embodiments, the at least two anti-counterfeiting indicators mentioned above also include: polarization degree, which is the light intensity difference of the fingerprint sub-image in at least two light path directions of the input fingerprint; and / or similarity, which is the fingerprint pattern similarity of the fingerprint sub-image in at least two light path directions of the input fingerprint.

[0018] In some embodiments, the fingerprint subgraphs of at least two optical path directions of the input fingerprint include: a first fingerprint subgraph in a first optical path direction, a second fingerprint subgraph in a second optical path direction, a third fingerprint subgraph in a third optical path direction, and a fourth fingerprint subgraph in a fourth optical path direction, the first optical path direction and the fourth optical path direction are located on a first diagonal of the imaging projection, and the second optical path direction and the third optical path direction are located on a second diagonal of the imaging projection; the polarization degree is a ratio of light intensity indication values ​​of two non-diagonal fingerprint subgraphs; or the polarization degree is a ratio of a first light intensity indication value to a second light intensity indication value, wherein the first light intensity indication value is the sum of light intensity indication values ​​of the two fingerprint subgraphs on the first diagonal, and the second light intensity indication value is the sum of light intensity indication values ​​of the two fingerprint subgraphs on the second diagonal.

[0019] In some embodiments, if the display screen is not covered with a film, S1 = A1*DL+B1*PL+C1*SL; if the display screen is covered with a film, S2 = A2*DL+B2*PL+C2*SL; wherein: S1 represents the anti-counterfeiting score when the display screen is not covered with a film, and S2 represents the anti-counterfeiting score when the display screen is covered with a film; DL represents the model prediction score, PL represents the degree of polarization, and SL represents the similarity; A1 and A2 represent the weight coefficients corresponding to the model prediction scores when the display screen is not covered with a film and when the film is covered, respectively; B1 and B2 represent the weight coefficients of the degree of polarization when the display screen is not covered with a film and when the film is covered, respectively; C1 and C2 represent the weight coefficients of the similarity when the display screen is not covered with a film and when the film is covered, respectively; A1 is less than A2, and: B1 is greater than B2, and / or C1 is greater than C2.

[0020] In some embodiments, judging whether a display screen is pasted with a film is performed based on an actual sub-image offset and a reference sub-image offset, including: determining a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; if the offset difference is greater than or equal to a film offset threshold, judging that the display screen is pasted with a film; if the offset difference is less than the film offset threshold, judging that the display screen is not pasted with a film.

[0021] In a third aspect, an embodiment of the present application provides a fingerprint processing device, which is applied to an electronic device with a display screen, and the device includes: an optical fingerprint device, which is used to: image a fingerprint light signal reflected by a finger above the display screen to obtain at least two fingerprint sub-images, the fingerprint light signal includes a light signal in a first light path direction and a light signal in a second direction, and the first light path direction is different from the second light path direction; a processing unit, which is used to execute the above-mentioned film detection method or the above-mentioned fingerprint anti-counterfeiting method.

[0022] In a fourth aspect, an embodiment of the present application provides an electronic device, which includes: a display screen; and the above-mentioned fingerprint processing device.

[0023] The film detection solution provided in the embodiment of the present application utilizes the film to increase the physical distance between the input fingerprint and the optical fingerprint device, thereby causing the actual sub-image offset to change relative to the sub-image offset when the film is not applied. The actual sub-image offset and the reference sub-image offset are used to determine whether the display screen is filmed, and whether the display screen is filmed can be stably and reliably detected. The fingerprint anti-counterfeiting solution provided in the embodiment of the present application can stably and reliably detect whether the display screen is filmed, and adjust the weight coefficient of the anti-counterfeiting index based on whether the display screen is filmed. The anti-counterfeiting score calculated in this way can match whether the display screen is filmed, and more accurately determine the authenticity of the input fingerprint.

[0024] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1A A schematic diagram of an electronic device to which an exemplary embodiment of the present application can be applied is shown.

[0027] Figure 1B A schematic diagram of an optical fingerprint device that can be applied according to an exemplary embodiment of the present application is shown.

[0028] Figure 1C A system block diagram of an electronic device to which the exemplary embodiments of the present application can be applied is shown.

[0029] Figure 2 A schematic diagram showing the direction of light paths to which the exemplary embodiments of the present application can be applied.

[0030] Figure 3 Shows Figure 2 The collected visible range and fingerprint sub-images and their positional relationships in the light path direction are shown.

[0031] Figure 4 A flow chart of a film detection method provided in an embodiment of the present application is shown.

[0032] Figure 5 Shows Figure 2 The fingerprint sub-image position relationship and sub-image offset in the light path direction are shown.

[0033] Fig. 6A A schematic diagram showing the acquisition visual range of a display screen with and without a film.

[0034] Figure 6B A schematic diagram showing the offset change between fingerprint sub-images with and without a display screen film.

[0035] Figure 7 A flowchart of a typical film detection method provided in an embodiment of the present application is shown.

[0036] Figure 8 A flow chart of a fingerprint anti-counterfeiting method provided in an embodiment of the present application is shown.

[0037] Fig. 9 A flowchart of a typical fingerprint anti-counterfeiting method provided in an embodiment of the present application is shown.

[0038] Fig.10 A structural block diagram of a fingerprint processing device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0039] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0040] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0041] In the embodiments of the present application, it should be noted that, in this article, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0042] Moreover, the terms "comprises," "comprising," or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0043] In the description of the embodiments of the present application, words such as "example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "example" or "for example" in the embodiments of the present application is not to be interpreted as being more preferred or having more advantages than another embodiment or design. The use of words such as "example" or "for example" is intended to present relative concepts in a clear manner.

[0044] In addition, the "plurality" in the embodiments of the present application refers to two or more than two. In view of this, in the embodiments of the present application, "plurality" can also be understood as "at least two". "At least one" can be understood as one or more, for example, one, two or more. For example, including at least one means including one, two or more, and there is no limit on which ones are included. For example, including at least one of A, B and C, then A, B, C, A and B, A and C, B and C, or A, B and C can be included.

[0045] It should be noted that, in the embodiments of the present application, "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the associated objects before and after are in an "or" relationship.

[0046] It should be noted that in the embodiments of the present application, "connection" can be understood as electrical connection, and the connection between two electrical components can be a direct or indirect connection between the two electrical components. For example, the connection between A and B can be either a direct connection between A and B or an indirect connection between A and B through one or more other electrical components.

[0047] Figure 1A and Figure 1B A schematic diagram of an electronic device in which various schemes described herein may be implemented according to an exemplary embodiment of the present application is shown. Figure 1A and Figure 1BAs shown, the electronic device 100 may include a device body 11, an optical fingerprint device 12 and a display screen 13. The optical fingerprint device 12 may be arranged in a partial area or the entire area below the display screen, thereby forming an under-display or under-screen optical fingerprint system. Alternatively, the optical fingerprint device 12 may be partially or fully integrated into the display screen 13 of the electronic device, thereby forming an in-display or in-screen optical fingerprint system. Specifically, in the electronic device 100, the optical fingerprint device 12 receives light returned from the top surface of the display screen of the electronic device 100. The returned light carries information of an object (such as a finger) in contact with the top surface of the display screen, and the fingerprint information of the finger is obtained by collecting and detecting the returned light.

[0048] In some embodiments, the electronic device 100 may be a portable electronic device, and the portable electronic device may be a smart phone, a tablet computer, a laptop computer, a personal digital assistant, etc. In other embodiments, the electronic device 100 may also be a smart wearable device, such as a smart watch, a virtual reality head-mounted device, an augmented reality head-mounted device, etc. The embodiment of the present application does not limit the type of the electronic device 100, and it may be any electronic device with a display screen.

[0049] See also Figure 1A As a typical embodiment, the device body 11 includes a middle frame 20. Among them, the display screen 13 is located on the front of the device body 11, and is used to display the picture and provide a human-computer interaction interface for the user; the middle frame 20 is generally located between the display screen 13 and the back shell of the electronic device, and is used to support the display screen 13 and to carry various functional components inside the device body 11, such as a motherboard, a battery, a camera, a speaker, a microphone, various sensor units, etc. In a specific embodiment, the middle frame 20 includes a frame located on the periphery of the device body 11, and the frame may include multiple sides and carry a power button, a volume button or other function buttons. In a specific embodiment, the optical fingerprint device 12 can be specifically a fingerprint recognition chip or a fingerprint module with a fingerprint recognition chip, so that the user can input a fingerprint to realize the fingerprint recognition function of the electronic device 100.

[0050] Please also read Figure 1B The display screen 13 includes an upper cover plate 131, a light emitting layer 132 and a lower cover plate 133. Depending on the light emitting layer, the display screen 13 can be a display screen with a self-luminous display unit or a non-self-luminous display screen.

[0051] As a typical embodiment, the display screen 13 may be a display screen having a self-luminous display unit, for example, Figure 1BAs shown, the display screen 13 may be an organic light emitting diode (OLED) display screen, however, the present application is not limited thereto, for example, a micro light emitting diode (Micro LED) may also be used. When an OLED display screen is used, the optical fingerprint device 12 may use the OLED light source corresponding to the fingerprint collection area position of the display screen 13 as an excitation light source for fingerprint detection. When the finger 30 presses on the fingerprint collection area of ​​the display screen 13, the light source at the corresponding position in the display screen 13 emits a light beam to the finger 30 above the fingerprint collection area, and the light beam is reflected on the surface where the finger 30 contacts the display screen 13 to form reflected light. The reflected light from the fingerprint ridge 31 and the reflected light from the fingerprint valley 32 have different light intensities. After the reflected light of different intensities passes through the optical component, it is received by the optical fingerprint device 12 and converted into a corresponding electrical signal, i.e., a fingerprint detection signal. Based on the fingerprint detection signal, fingerprint data can be obtained for realizing the fingerprint recognition function in the electronic device 100.

[0052] As a typical embodiment, the display screen 13 can be a non-self-luminous display screen, such as a liquid crystal display (LCD). The optical fingerprint device 12 uses a built-in light source or an external light source as an excitation light source to provide an optical signal for fingerprint detection. The fingerprint detection principle when the built-in light source or the external light source is used as the excitation light source is the same as the fingerprint detection principle when the OLED display screen is used as mentioned above, and will not be repeated here.

[0053] Please continue reading Figure 1B The optical fingerprint device 12 can be arranged in a local area below the display screen 13, and can include an optical component 121 and an optical detection component 122. The optical component 121 can be arranged above the optical detection component 122, and can specifically include a light guide layer or a light path guiding structure and other optical elements. The light guide layer or the light path guiding structure is mainly used to guide the reflected light reflected from the finger surface to the optical detection component 122 for optical detection.

[0054] There are many implementation schemes for the light-guiding layer or light-path guiding structure of the optical component 121. For example, in some embodiments, the light-guiding layer or light-path guiding structure can be an optical lens (Lens) layer, which has one or more lenses, and is used to converge the reflected light reflected from the finger to the sensing array of the light detection part 122 below it, so that the sensing array can be imaged based on the reflected light, thereby obtaining the fingerprint image of the finger. Optionally, the optical lens layer can also form a pinhole in the light path of the lens unit, and the pinhole can cooperate with the optical lens layer to expand the field of view of the optical fingerprint device to improve the fingerprint imaging effect of the optical fingerprint device 12.

[0055] Please continue reading Figure 1C As shown, the optical detection component 122 includes a photosensitive array 1221 and an output module 1222 electrically connected to the photosensitive array 1221 and other auxiliary circuits. The auxiliary circuit may include a driving module 1223, and the driving module 1223 is used to drive the sensing array 1221 to perform fingerprint scanning to collect fingerprint information of the user's finger. The photosensitive array 1221 may include a plurality of photosensitive units distributed in an array, which may also be referred to as pixel units or photosensitive pixels. The photosensitive array 1221 is mainly used to detect the received light signal so as to generate fingerprint data through the output module 1222 electrically connected thereto. The output module 1222 can output the fingerprint data to the control system 14 through the interface module 1224, and the interface module 1224 can be specifically a serial peripheral interface (SPI).

[0056] Continue reading Figure 1C , the control system 14 may include one or more general-purpose single-chip or multi-chip processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic components, discrete hardware components, or combinations thereof. According to some examples, the control system 14 may include dedicated components for controlling the optical fingerprint device 12. In some implementations, the functionality of the control system 14 may be divided between one or more controllers or processors, such as between a dedicated sensor controller and an application processor of an electronic device. Reference Figure 1C , the control system 14 may include an application processor 141 of the electronic device. The application processor 141 may be specifically a central processing unit CPU or other processing unit or control unit with processing capability inside the electronic device 100, such as a microcontroller (MCU), which is connected to the interface module 1224 and includes a fingerprint recognition module, which is mainly used to control the working state of the optical fingerprint device 12, and process the fingerprint data output by the optical fingerprint device 12 and perform fingerprint anti-counterfeiting, fingerprint template registration, and fingerprint matching verification to determine whether the currently collected fingerprint image belongs to a legal fingerprint, and unlock the electronic device 100 or perform other functions related to fingerprint recognition according to the judgment result.

[0057] In an embodiment of the present application, the optical component 121 may include a plurality of light guide channels, the plurality of light guide channels having a plurality of light path directions, any one light path direction being different from the other light path directions, and each conduction channel being used to conduct a fingerprint light signal in a light path direction. The photosensitive units (pixel units) of the photosensitive array 1221 correspond one-to-one to the light guide channels. Among the photosensitive units of the photosensitive array 1221, each photosensitive unit of the photosensitive array 1221 only receives the fingerprint light signal conducted by the light guide channel corresponding thereto, and converts it into a fingerprint electrical signal. The output module 1222 outputs the fingerprint image of the light path direction, i.e., the fingerprint sub-graph of the light path direction, based on the fingerprint electrical signal of the photosensitive unit corresponding to each light path direction. Thus, the input fingerprint is optically fingerprinted from multiple directions to obtain fingerprint images in multiple directions. Multiple fingerprint sub-graphs corresponding to multiple light path directions can be used for fingerprint recognition.

[0058] The optical path direction is the angle relative to the plane where the photosensitive array 1221 is located. Taking the plane where the photosensitive array 1221 is located as the viewing angle, each optical path direction corresponds to a visible range of the collected image, and each fingerprint sub-image is a fingerprint image of the input fingerprint in the corresponding visible range. The multiple visible ranges corresponding to the multiple optical path directions partially overlap, and accordingly, the projections of the multiple fingerprint sub-images on the plane where the photosensitive array 1221 is located partially overlap.

[0059] In some embodiments, the plurality of light guide channels may include a first light guide channel, a second light guide channel, a third light guide channel, and a fourth light guide channel, and correspondingly, the plurality of light path directions may include a first light path direction, a second light path direction, a third light path direction, and a fourth light path direction. It should be understood that the embodiments of the present application do not limit the number of light guide channels and light path directions, and in specific implementations, different numbers of light guide channels may be set according to actual needs to form a corresponding number of light path directions.

[0060] Exemplary, reference Figure 2 As shown, the multiple light path directions may include: light path 0 (i.e., the first light path direction), light path 1 (the second light path direction), light path 2 (the third light path direction), and light path 3 (the fourth light path direction). For ease of understanding, the first, second, third, and fourth light path directions are described in the embodiments of the present application. Figure 3 As shown, four fingerprint sub-images can be collected from four light path directions. Figure 3 Part (a) shows the fingerprint sub-image a and its optical path. Figure 3 Part (b) shows the fingerprint sub-image b and its optical path. Figure 3 Part (c) shows the fingerprint sub-image c and its optical path. Figure 3 Part (d) shows the fingerprint sub-image d and its optical path. Figure 3 The thick solid line represents the photosensitive array plane or its projection. Figure 3 As shown in part (e), fingerprint sub-image a is offset relative to the upper left direction of the photosensitive array plane, fingerprint sub-image b is offset relative to the upper right direction of the photosensitive array plane, fingerprint sub-image c is offset relative to the lower left direction of the photosensitive array plane, and fingerprint sub-image d is offset relative to the lower right direction of the photosensitive array plane.

[0061] The present application provides a method for detecting film sticking, which can be applied to Figure 1A , Figure 1B and Figure 1C The electronic device 100 shown determines whether a film is applied to the display screen based on a fingerprint sub-image of at least one optical path direction of the input fingerprint, so as to improve the film application detection effect.

[0062] Figure 4 A flowchart of a film detection method provided by an embodiment of the present application is shown. Figure 4 As shown, the method uses the film to increase the physical distance between the input fingerprint and the optical fingerprint device, which leads to the phenomenon that the actual sub-image offset changes relative to the sub-image offset when the film is not applied. Whether the display screen is filmed is judged based on the actual sub-image offset and the reference sub-image offset. Whether the display screen is filmed can be stably and reliably detected, which specifically includes the following steps.

[0063] Step S401: using an optical fingerprint device to collect a fingerprint sub-graph of at least one optical path direction of an input fingerprint.

[0064] In the application embodiment, in the electronic device 100, the optical fingerprint device 12 of the electronic device 100 can collect fingerprint sub-graphs of multiple optical path directions of the input fingerprint.

[0065] Specifically, when the display screen 13 of the electronic device 100 adopts a self-luminous display screen (for example, an OLED display screen), the optical fingerprint device 12 can use the OLED light source corresponding to the fingerprint collection area of ​​the display screen 13 as an excitation light source for fingerprint detection. When a finger presses on the fingerprint collection area of ​​the display screen 13, the light source at the corresponding position of the display screen 13 emits a light beam to the finger above the fingerprint collection area, and the light beam is reflected on the surface where the finger contacts the display screen 13 to form reflected light.

[0066] When the display screen 13 of the electronic device 100 is a non-self-luminous display screen (such as an LCD display screen), the optical fingerprint device 12 uses a built-in light source or an external light source as an excitation light source to provide an optical signal for fingerprint detection. When a finger presses on the fingerprint collection area of ​​the display screen 13, the built-in light source or the external light source emits a light beam to the finger above the fingerprint collection area, and the light beam is reflected on the surface where the finger contacts the display screen 13 to form reflected light.

[0067] Furthermore, the reflected light from the fingerprint ridge and the reflected light from the fingerprint valley have different light intensities, and the reflected light of different intensities is received by the optical fingerprint device 12 and converted into corresponding electrical signals, namely, fingerprint detection signals. Specifically, each conductive channel in the optical component 121 of the optical fingerprint device 12 conducts reflected light in a light path direction. Each photosensitive unit of the photosensitive array 1221 only receives the reflected signal conducted by the corresponding light guide channel and converts it into a fingerprint electrical signal. The output module 1222 outputs the fingerprint image of the light path direction, namely, the fingerprint sub-map of the light path direction, based on the fingerprint electrical signal of the photosensitive unit corresponding to each light path direction. In this way, the input fingerprint is optically fingerprinted from multiple directions to obtain fingerprint images in multiple directions.

[0068] For example, collecting input fingerprints in Figure 2 The fingerprint images in the four optical paths shown can be obtained as follows Figure 3 The four fingerprint subgraphs shown are fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d.

[0069] The optical fingerprint device 12 can transmit the fingerprint sub-graphs of multiple optical path directions of the input fingerprint to the application processor 141 through the interface module 1224. The fingerprint recognition module in the application processor 141 can process the multiple fingerprint sub-graphs output by the optical fingerprint device 12. Figure 3 The fingerprint sub-image a, fingerprint sub-image b, fingerprint sub-image c and fingerprint sub-image d shown are transmitted to the fingerprint recognition module.

[0070] Step S402: determining an actual sub-image offset according to the fingerprint sub-image of the at least one optical path direction.

[0071] In the embodiment of the present application, the sub-image offset can be defined as the distance between the center point of the fingerprint sub-image and the center point of the photosensitive array of the optical fingerprint device 12. Figure 5 As shown, the sub-image offset corresponding to fingerprint sub-image a is the distance La between the center point Pa of fingerprint sub-image a and the center point Po of the photosensitive array; the sub-image offset corresponding to fingerprint sub-image b is the distance Lb between the center point Pb of fingerprint sub-image b and the center point Po of the photosensitive array; the sub-image offset corresponding to fingerprint sub-image c is the distance Lc between the center point Pc of fingerprint sub-image c and the center point Po of the photosensitive array; the sub-image offset corresponding to fingerprint sub-image d is the distance Ld between the center point Pd of fingerprint sub-image d and the center point Po of the photosensitive array.

[0072] In some embodiments, the sub-image offset may be determined based on the sub-image offsets corresponding to at least two fingerprint sub-images. For example, the sub-image offset may be the sum or average of the sub-image offsets corresponding to at least two fingerprint sub-images. For example, the sub-image offset may be the sum of La and Lb, or the average of La and Lb.

[0073] In the embodiment of the present application, the sub-image offset can be defined as the distance between the center points of two fingerprint sub-images. Figure 5 As shown, the sub-image offset can be: the distance between the center point Pa of fingerprint sub-image a and the center point Pb of fingerprint sub-image b; or the distance between the center point Pa of fingerprint sub-image a and the center point Pc of fingerprint sub-image c; or the distance between the center point Pa of fingerprint sub-image a and the center point Pd of fingerprint sub-image d; or the distance between the center point Pb of fingerprint sub-image b and the center point Pc of fingerprint sub-image c; or the distance between the center point Pb of fingerprint sub-image b and the center point Pd of fingerprint sub-image d; or the distance between the center point Pc of fingerprint sub-image c and the center point Pd of fingerprint sub-image d.

[0074] In some embodiments, the sub-image offset may be determined based on at least two of the aforementioned sub-image offsets, for example, the sub-image offset may be the sum or average of the at least two aforementioned sub-image offsets, for example, the distance between the center point Pa of fingerprint sub-image a and the center point Pc of fingerprint sub-image c, and the sum or average of the distance between the center point Pa of fingerprint sub-image a and the center point Pd of fingerprint sub-image d.

[0075] In the embodiment of the present application, the sub-image offset when the display screen 13 of the electronic device 100 is not filmed can be predetermined as the reference sub-image offset and stored in the memory (e.g., non-volatile memory) of the electronic device 100. In some optional implementations, the reference sub-image offset can be calibrated using striped weights or weights with special patterns during the mass production stage (striped weights or weights with special patterns can be used to simulate fingers). The fingerprint recognition module in the electronic device 100 can read the reference sub-image offset from the memory.

[0076] If the display screen 13 of the electronic device 100 is not covered with a film, the sub-image offset of the fingerprint sub-image collected by the optical fingerprint device 12 is substantially equal to the reference sub-image offset. Figure 2 , Figure 3 and Fig. 6A As shown, if the display screen 13 of the electronic device 100 is covered with a film, the distance between the input fingerprint and the photosensitive array of the optical fingerprint device 12 increases due to the film, and the visible range of the captured image changes, thereby causing the sub-image offset to change. That is to say, when the display screen 13 of the electronic device 100 is covered with a film, the actual sub-image offset is different from the reference sub-image offset.

[0077] For example, refer to Figure 2 , Figure 3 and Figure 6B As shown, after the display screen 13 of the electronic device 100 is filmed, the offset of the fingerprint sub-image a toward the upper left of the photosensitive array becomes larger, the offset of the fingerprint sub-image b toward the upper right of the photosensitive array becomes larger, the offset of the fingerprint sub-image c toward the lower left of the photosensitive array becomes larger, the offset of the fingerprint sub-image d toward the lower right of the photosensitive array becomes larger, and the overlapping parts of the four fingerprint sub-images become smaller.

[0078] In the electronic device 100, the fingerprint recognition module in the application processor 141 can determine the actual sub-image offset according to the fingerprint sub-image of at least one optical path direction. In the embodiment of the present application, the actual sub-image offset can be determined by using a known technology, which will not be described in detail in the embodiment of the present application.

[0079] Step S403, judging whether the display screen is covered with a film according to the actual sub-image offset and the reference sub-image offset, wherein the reference sub-image offset is the sub-image offset when the display screen is not covered with a film.

[0080] In some possible implementations, step S403 may include: determining the difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; if the offset difference is greater than or equal to a film offset threshold, determining that the display screen has a film; if the offset difference is less than the film offset threshold, determining that the display screen has no film.

[0081] In some embodiments, the film thickness information may also be determined based on the actual sub-image offset and the reference sub-image offset. As an implementation, the film thickness information is a film thickness interval, and the film thickness information is determined based on the actual sub-image offset and the reference sub-image offset, including: determining the difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; determining the film thickness interval based on a comparison result of the offset difference and at least one thickness threshold, the at least one thickness threshold dividing at least two film thickness intervals. The thickness threshold may be determined in advance based on the offset difference of protective films of different thicknesses.

[0082] Exemplarily, if the offset difference is less than the film offset threshold, it is determined that the display screen 13 of the electronic device 100 is not filmed; if the offset difference is greater than or equal to the film offset threshold, it is determined that the display screen 13 of the electronic device 100 is filmed. Further, in some implementations, the film thickness is divided into a first film thickness interval and a second film thickness interval based on a first thickness threshold, wherein if the offset difference is greater than the film offset threshold and less than the first thickness threshold, it is determined to belong to the first film thickness interval, and the first film thickness interval can be defined as a thin film interval (i.e., the film thickness is relatively small); if the offset difference is greater than the first thickness threshold, it is determined to belong to the second film thickness interval, and the second film thickness interval can be defined as a non-thin film interval (i.e., the film thickness is relatively large). In some implementations, based on the second thickness threshold and the third thickness threshold, the film thickness is divided into a third film thickness interval, a fourth film thickness interval, and a fifth film thickness interval, wherein if the offset difference is greater than the film offset threshold and less than the second thickness threshold, it is determined to belong to the third film thickness interval, and the third film thickness interval can be defined as a thin film interval; if the offset difference is greater than the second thickness threshold and less than the third thickness threshold, it is determined to belong to the fourth film thickness interval, and the fourth film thickness interval can be defined as a medium film interval (i.e., the film thickness is medium); if the offset difference is greater than the third thickness threshold, it is determined to belong to the fifth film thickness interval, and the fifth film thickness interval can be defined as a thick film interval (i.e., the film thickness is relatively large). The first thickness threshold and the second thickness threshold in the aforementioned implementation can be equal or unequal. It should be understood that in a specific implementation, the film thickness interval and the thickness threshold can be set as needed.

[0083] The typical process of the above film testing can be Figure 7 The flowchart shown is summarized. Figure 7 A flow chart of a film detection method according to an exemplary embodiment of the present application is shown. Figure 7 As shown, it specifically includes the following steps.

[0084] Step S701: using an optical fingerprint device to collect a fingerprint sub-graph of at least one optical path direction of an input fingerprint.

[0085] Step S702: determining an actual sub-image offset according to the fingerprint sub-image of the at least one light path direction.

[0086] Step S703: determine the difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference.

[0087] Step S704, compare the offset difference with the film offset threshold. If the offset difference is less than the film offset threshold, it is determined that the display screen 13 of the electronic device 100 is not pasted with a film. If the offset difference is greater than or equal to the film offset threshold, it is determined that the display screen 13 of the electronic device 100 is pasted with a film. In some possible implementations, when it is determined that the display screen 13 of the electronic device 100 is pasted with a film, step S705 may also be entered.

[0088] Step S705, compare the offset difference with the thickness thresholds L1 and L2. If the offset difference is greater than the film offset threshold and less than L1, it is determined to belong to the thin film interval, and the protective film can be determined to be a thin film; if the offset difference is greater than L1 and less than L2, it is determined to belong to the medium film interval, and the protective film can be determined to be a medium film; if the offset difference is greater than L2, it is determined to belong to the thick film interval, and the protective film can be determined to be a thick film. Among them, L1 corresponds to the aforementioned second thickness threshold, and L2 corresponds to the aforementioned third thickness threshold.

[0089] The present application also provides a fingerprint anti-counterfeiting method, which can be applied to Figure 1A , Figure 1B and Figure 1C The electronic device 100 shown adjusts the fingerprint anti-counterfeiting judgment condition according to whether the display screen is covered with a film to improve the fingerprint anti-counterfeiting effect. The fingerprint anti-counterfeiting judgment condition can be an anti-counterfeiting score determined based on at least two anti-counterfeiting indicators and their weight coefficients. Figure 8 A flow chart of a fingerprint anti-counterfeiting method provided in an embodiment of the present application is shown. Figure 8 As shown, it specifically includes the following steps.

[0090] Step S801, determining an actual sub-image offset according to a fingerprint sub-image of at least one optical path direction of an input fingerprint.

[0091] Step S802, judging whether the display screen is covered with a film according to the actual sub-image offset and the reference sub-image offset, wherein the reference sub-image offset is the sub-image offset when the display screen is not covered with a film.

[0092] Step S801 and step S802 can be found in Figure 4 And its description, I will not go into details here.

[0093] Step S803, determining weight coefficients of at least two anti-counterfeiting indicators according to the result of judging whether the display screen is covered with a film, wherein the weight coefficient when the display screen is covered with a film is different from the weight coefficient when the display screen is not covered with a film.

[0094] In an embodiment of the present application, in the electronic device 100, the fingerprint recognition module can determine at least two anti-counterfeiting indicators based on the fingerprint sub-graph of the input fingerprint collected by the optical fingerprint device 12, determine the anti-counterfeiting score based on the at least two anti-counterfeiting indicators and the weight coefficient, and determine the authenticity of the input fingerprint based on the anti-counterfeiting score.

[0095] See also Fig. 6A As shown, in the electronic device 100, when the display screen 13 is filmed, the distance between the optical fingerprint device 12 and the input fingerprint increases and the visible range of the collected image changes, which causes the sub-image offset to change, and the anti-counterfeiting feature is offset accordingly. That is to say, the distribution of anti-counterfeiting features when the display screen 13 of the electronic device 100 is filmed is different from the distribution of anti-counterfeiting features when the display screen 13 is not filmed. In the embodiment of the present application, the weight coefficient when the display screen is filmed is different from the weight coefficient when the display screen is not filmed, so as to adapt to the change of the distribution of anti-counterfeiting features. Specifically, the weight coefficient of each anti-counterfeiting indicator when the display screen is not filmed is pre-set as the first weight coefficient, and the weight coefficient of each anti-counterfeiting indicator when the display screen is filmed is pre-set as the second weight coefficient, and the first weight coefficient and the second weight coefficient can be pre-stored in the memory of the electronic device 100. If the judgment result of whether the display screen is filmed indicates that the display screen is not filmed, the weight coefficient of the anti-counterfeiting indicator is the first weight coefficient; if the judgment result of whether the display screen is filmed indicates that the display screen is filmed, the weight coefficient of the anti-counterfeiting indicator is the second weight coefficient.

[0096] In some possible implementation modes, the anti-counterfeiting score threshold can also be determined according to the judgment result of whether the display screen is pasted with a film, wherein the anti-counterfeiting score threshold when the display screen is pasted with a film is different from the anti-counterfeiting score threshold when the display screen is not pasted with a film. The anti-counterfeiting score can be compared with the anti-counterfeiting score threshold, and the authenticity of the input fingerprint can be determined according to the comparison result. With this implementation, the weight coefficient of the anti-counterfeiting index and the anti-counterfeiting score threshold are adapted to the anti-counterfeiting feature distribution when the film is pasted and when the film is not pasted, and the real fingerprint can be better distinguished from the forged fingerprint. Specifically, the anti-counterfeiting score threshold when the display screen is not pasted with a film is pre-set as the first anti-counterfeiting score threshold, and the anti-counterfeiting score threshold when the display screen is pasted with a film is pre-set as the second anti-counterfeiting score threshold, and the first anti-counterfeiting score threshold and the second anti-counterfeiting score threshold can be pre-stored in the memory of the electronic device 100. If the judgment result of whether the display screen is pasted with a film indicates that the display screen is not pasted with a film, the anti-counterfeiting score threshold is the first anti-counterfeiting score threshold; if the judgment result of whether the display screen is pasted with a film indicates that the display screen is pasted with a film, the anti-counterfeiting score threshold is the second anti-counterfeiting score threshold.

[0097] In some possible implementations, the film thickness information can also be determined based on the actual sub-image offset and the reference sub-image offset. Different film thicknesses can correspond to different weight coefficients and / or anti-counterfeiting score thresholds, and the weight coefficient and / or anti-counterfeiting score threshold can be determined based on the film thickness information. Specifically, if the judgment result is that the display screen is filmed, the second weight coefficient of at least two anti-counterfeiting indicators is the weight coefficient corresponding to the film thickness information, and / or the second anti-counterfeiting score threshold is the anti-counterfeiting score threshold corresponding to the film thickness information.

[0098] As a typical implementation, the film thickness information may include a film thickness interval, and the film thickness information is determined according to the actual sub-image offset and the reference sub-image offset, including: determining the difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; determining the film thickness interval according to a comparison result of the offset difference and at least one thickness threshold, the at least one thickness threshold divides at least two film thickness intervals; wherein the second weight coefficients corresponding to any two film thickness intervals are different. The specific implementation of the film thickness interval can be found in the description of the film detection method described above in this application, and will not be repeated here.

[0099] In some possible implementations, the at least two anti-counterfeiting indicators mentioned above may include: a model prediction score, which is a score indicating whether the input fingerprint is authentic and output by the model based on the fingerprint subgraphs of at least two optical path directions of the input fingerprint. Specifically, the model may adopt a neural network model, and the neural network model may include a convolutional neural network (CNN) and the like. In a specific implementation, fingerprint images may be collected and their authenticity may be annotated to form labels, for example, the fingerprint image of a real fingerprint may be annotated as "1", and the fingerprint image of a forged fingerprint may be annotated as "0", that is, the label of the fingerprint image of the real fingerprint is "1", and the label of the fingerprint image of the forged fingerprint is "0". The neural network model is trained based on the fingerprint image and its label so that the neural network outputs a score indicating whether the input fingerprint is authentic based on the fingerprint image.

[0100] In some possible implementations, the at least two anti-counterfeiting indicators may include: polarization degree, which is the light intensity difference of the fingerprint sub-image in at least two optical path directions of the input fingerprint. Generally speaking, the polarization degree of the fingerprint image of a real fingerprint is greater than the polarization degree of the fingerprint image of a forged fingerprint, so the authenticity of the fingerprint can be judged at least partially based on the polarization degree.

[0101] Specifically, the polarization degree can be obtained by calculating the light intensity difference based on the light intensity indication values ​​of at least two fingerprint sub-images of the input fingerprint. Figure 2 , Figure 3 and Figure 5In the light path direction shown, the light intensity indication values ​​of the fingerprint sub-graphs in the diagonal direction are relatively close, and the light intensity indication values ​​of the fingerprint sub-graphs in the non-diagonal direction are relatively different. Preferably, the polarization degree is determined based on the light intensity indication values ​​of the fingerprint sub-graphs in the non-diagonal direction. As an example, the polarization degree is the ratio of the light intensity indication values ​​of the two non-diagonal fingerprint sub-graphs. As another example, the polarization degree is the ratio of the first light intensity indication value to the second light intensity indication value, wherein the first light intensity indication value is the sum of the light intensity indication values ​​of the two fingerprint sub-graphs in the first diagonal, and the second light intensity indication value is the sum of the light intensity indication values ​​of the two fingerprint sub-graphs in the second diagonal.

[0102] In some implementations, the fingerprint signal quantity of the fingerprint sub-graph may be calculated, and the polarization degree may be determined based on the fingerprint signal quantities of at least two fingerprint sub-graphs, for example, the polarization degree may be the ratio of the fingerprint signal quantities of the two fingerprint sub-graphs. In some implementations, the pixel mean of the fingerprint sub-graph may be calculated, and the polarization degree may be determined based on the pixel mean of at least two fingerprint sub-graphs, for example, the polarization degree may be the ratio of the pixel mean of the two fingerprint sub-graphs. The pixel mean may be the mean of all pixels of the fingerprint sub-graph or the mean of pixels of a partial area.

[0103] For example, see Figure 2 , Figure 3 and Figure 5 As shown, the fingerprint subgraph of the input fingerprint includes: fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d, fingerprint subgraph a and d are located on the first diagonal, and fingerprint subgraph b and fingerprint subgraph c are located on the second diagonal. As an example, the polarization degree is the ratio of the pixel means of two non-diagonal fingerprint subgraphs, for example, the ratio of the pixel means of fingerprint subgraph a to fingerprint subgraph b, or the ratio of the pixel means of fingerprint subgraph a to fingerprint subgraph c, or the ratio of the pixel means of fingerprint subgraph b to fingerprint subgraph d. As another example, the polarization degree is the ratio of the first pixel mean to the second pixel mean, wherein the first pixel mean is the sum of the pixel means of the two fingerprint subgraphs on the first diagonal, and the second pixel mean is the sum of the pixel means of the two fingerprint subgraphs on the second diagonal. For example, the ratio of the sum of the pixel means of fingerprint subgraph a and fingerprint subgraph d to the sum of the pixel means of fingerprint subgraph b and fingerprint subgraph c.

[0104] In some possible implementations, the at least two anti-counterfeiting indicators may include: similarity, where the similarity is the fingerprint pattern similarity of the fingerprint sub-graphs in at least two optical path directions of the input fingerprint. When observing an asymmetric 3D object from different angles, the observed forms are different, and this phenomenon also exists after being converted into an image. When observing a 2D object from different angles, the forms seen are basically the same, and this phenomenon also exists after being converted into an image. In the electronic device 100, the optical fingerprint device 12 uses multiple light guide channels to realize imaging of the fingerprint pattern of the input fingerprint from different angles, and obtain fingerprint sub-graphs in multiple optical path directions. The real fingerprint is 3D, and the fingerprint sub-graphs are quite different; the forged fingerprint is 2D or 2.5D, and the fingerprint sub-graphs are basically the same or have little difference. In addition, the 3D fake fingerprint obtained in the non-cooperation situation also has a high similarity to the real finger it imitates. The fingerprint recognition module of the electronic device 100 can distinguish the real fingerprint from the forged fingerprint at least partially by calculating the similarity of the fingerprint pattern images between the fingerprint sub-graphs in at least two optical path directions of the input fingerprint collected by the optical fingerprint device 12.

[0105] For example, see Figure 2 , Figure 3 and Figure 5 As shown, the fingerprint subgraphs of the input fingerprint include fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d. The similarity can be the fingerprint pattern similarity of the overlapping parts of any two fingerprint images, the fingerprint pattern similarity of the overlapping parts of any three fingerprint images, or the fingerprint pattern similarity of the overlapping parts of four fingerprint images.

[0106] See also Fig. 6A As shown in the figure, the film increases the physical distance between the input fingerprint and the optical fingerprint device, and increases the visual range of the captured image. For further information, please refer to Figure 6B As shown, the overlapped part between fingerprint sub-graphs becomes smaller after film application. Similarity is mainly determined based on the overlapped part of fingerprint images. The overlapped part becomes smaller when film is applied relative to that when film is not applied, and the weight of similarity in distinguishing real fingerprints from forged fingerprints is reduced. Therefore, the weight coefficient of similarity when film is applied can be set to be smaller than the weight coefficient when film is not applied. Similarly, the overlapped part becomes smaller when film is applied relative to that when film is not applied, and the weight of polarization in distinguishing real fingerprints from forged fingerprints is reduced. Therefore, the weight coefficient of polarization when film is applied can be set to be smaller than the weight coefficient when film is not applied. The model outputs prediction scores based on fingerprint sub-graphs, and the accuracy of prediction scores is basically not affected by the reduction of overlapped part between fingerprint sub-graphs. The weight coefficient of model prediction scores when the display screen is filmed can be set to be larger than the weight coefficient when film is not applied.

[0107] Step S804: determining an anti-counterfeiting score according to at least two anti-counterfeiting indicators and a weight coefficient.

[0108] In some possible implementations, the anti-counterfeiting index may include at least two of the model prediction score, polarization degree, and similarity. As a typical example, the anti-counterfeiting index includes the model prediction score, polarization degree, and similarity.

[0109] Exemplarily, in the electronic device 100, if the display screen 13 is not covered with a film, then S1 = A1*DL+B1*PL+C1*SL; if the display screen is covered with a film, then S2 = A2*DL+B2*PL+C2*SL; where: S1 represents the anti-counterfeiting score when the display screen is not covered with a film, and S2 represents the anti-counterfeiting score when the display screen is covered with a film; DL represents the model prediction score, PL represents the polarization degree, and SL represents the similarity; A1 and A2 represent the weight coefficients corresponding to the model prediction scores when the display screen is not covered with a film and when the film is covered; B1 and B2 represent the weight coefficients of the polarization degree when the display screen is not covered with a film and when the film is covered; C1 and C2 represent the weight coefficients of the similarity when the display screen is not covered with a film and when the film is covered. Preferably, A1 is less than A2, and: B1 is greater than B2, and / or C1 is greater than C2.

[0110] Step S805: determining the authenticity of the input fingerprint according to the anti-counterfeiting score.

[0111] In some possible implementations, the anti-counterfeiting score can be compared with the anti-counterfeiting score threshold, and the authenticity of the input fingerprint can be determined based on the comparison result. Specifically, if the display screen is not pasted with a film, the anti-counterfeiting score is compared with the first anti-counterfeiting score threshold; if the display screen is pasted with a film, the anti-counterfeiting score is compared with the second anti-counterfeiting score threshold. Exemplarily, when the display screen is not pasted with a film, if the anti-counterfeiting score is greater than the first anti-counterfeiting score threshold, the input fingerprint is determined to be a fake fingerprint; if the anti-counterfeiting score is less than or equal to the first anti-counterfeiting score threshold, the input fingerprint is determined to be a real fingerprint. When the display screen is pasted with a film, if the anti-counterfeiting score is greater than the second anti-counterfeiting score threshold, the input fingerprint is determined to be a fake fingerprint; if the anti-counterfeiting score is less than or equal to the second anti-counterfeiting score threshold, the input fingerprint is determined to be a real fingerprint.

[0112] The typical process of fingerprint anti-counterfeiting can be achieved through Fig. 9 The flowchart shown is summarized. Fig. 9 A flow chart of a fingerprint anti-counterfeiting method according to an exemplary embodiment of the present application is shown. Fig. 9 As shown, it specifically includes the following steps.

[0113] Step S901: using an optical fingerprint device to collect fingerprint sub-graphs of at least two optical path directions of an input fingerprint.

[0114] In the electronic device 100, the fingerprint recognition module can control the light source to emit a light beam to the finger above the fingerprint collection area when the finger is pressed on the fingerprint collection area of ​​the display screen 13. Specifically, when the display screen 13 adopts a self-luminous display screen, the fingerprint recognition module controls the light source at the corresponding position in the display screen 13 to emit a light beam to the finger above the fingerprint collection area. When the display screen 13 of the electronic device 100 adopts a non-self-luminous display screen, the fingerprint recognition module controls the built-in light source or external light source of the optical fingerprint device 12 to emit a light beam to the finger above the fingerprint collection area. The light beam is reflected on the surface where the finger contacts the display screen 13 to form reflected light.

[0115] Further, the fingerprint recognition module controls the optical fingerprint device 12 to receive the reflected light and convert it into a corresponding electrical signal, namely, a fingerprint detection signal. Specifically, each conductive channel in the optical component 121 of the optical fingerprint device 12 conducts reflected light in one optical path direction. Each photosensitive unit of the photosensitive array 1221 only receives the reflected signal conducted by the corresponding light-conducting channel and converts it into a fingerprint electrical signal. The output module 1222 outputs the fingerprint image of the optical path direction, namely, the fingerprint sub-map of the optical path direction, based on the fingerprint electrical signal of the photosensitive unit corresponding to each optical path direction. The optical fingerprint device 12 can transmit the fingerprint sub-maps of multiple optical path directions of the input fingerprint to the fingerprint recognition module through the interface module 1224.

[0116] For illustration purposes, see Figure 2 , Figure 3 and Figure 5 , collect input fingerprints in Figure 2 The fingerprint images in the four optical paths shown can be obtained as follows Figure 3 and Figure 5 The four fingerprint subgraphs shown are fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d.

[0117] Step S902, determining at least two anti-counterfeiting indicators according to the collected fingerprint sub-graphs. The at least two anti-counterfeiting indicators are used to determine the anti-counterfeiting score, which may specifically include the following steps.

[0118] Step S9021, inputting at least part of the collected fingerprint sub-graph into a pre-trained neural network model, and outputting a model prediction score through the neural network model, wherein the model prediction score is a score indicating whether the input fingerprint is authentic.

[0119] Continue reading Figure 2 , Figure 3 and Figure 5At least two fingerprint subgraphs among fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d can be input into a pre-trained neural network model, and the neural network model outputs the model prediction score. Considering that the fingerprint subgraphs on the diagonal are similar in polarization characteristics and the like, preferably, when the input of the neural network model is two fingerprint subgraphs, two fingerprint subgraphs on the non-diagonal line are input, for example, fingerprint subgraph a and fingerprint subgraph b, or fingerprint subgraph a and fingerprint subgraph c, or fingerprint subgraph b and fingerprint subgraph d, or fingerprint subgraph c and fingerprint subgraph d.

[0120] Step S9022: determine the similarity of fingerprint patterns of at least part of the collected fingerprint sub-images.

[0121] Continue reading Figure 2 , Figure 3 and Figure 5 As shown, the fingerprint subgraphs of the input fingerprint include fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d. The similarity can be the fingerprint pattern similarity of the overlapping parts of any two fingerprint images, the fingerprint pattern similarity of the overlapping parts of any three fingerprint images, or the fingerprint pattern similarity of the overlapping parts of four fingerprint images.

[0122] Step S9023: determining the degree of polarization based on at least part of the collected fingerprint sub-image.

[0123] Continue reading Figure 2 , Figure 3 and Figure 5 As shown, the fingerprint subgraph of the input fingerprint includes: fingerprint subgraph a, fingerprint subgraph b, fingerprint subgraph c and fingerprint subgraph d, fingerprint subgraph a and d are located on the first diagonal, and fingerprint subgraph b and fingerprint subgraph c are located on the second diagonal. As an example, the polarization degree is the ratio of the pixel means of two non-diagonal fingerprint subgraphs, for example, the ratio of the pixel means of fingerprint subgraph a to fingerprint subgraph b, or the ratio of the pixel means of fingerprint subgraph a to fingerprint subgraph c, or the ratio of the pixel means of fingerprint subgraph b to fingerprint subgraph d. As another example, the polarization degree is the ratio of the first pixel mean to the second pixel mean, wherein the first pixel mean is the sum of the pixel means of the two fingerprint subgraphs on the first diagonal, and the second pixel mean is the sum of the pixel means of the two fingerprint subgraphs on the second diagonal. For example, the ratio of the sum of the pixel means of fingerprint subgraph a and fingerprint subgraph d to the sum of the pixel means of fingerprint subgraph b and fingerprint subgraph c.

[0124] Step S903: determining an actual sub-image offset based on at least part of the collected fingerprint sub-image.

[0125] Step S904: obtaining a pre-stored reference sub-image offset and a film offset threshold.

[0126] In the embodiment of the present application, the sub-image offset when the display screen 13 of the electronic device 100 is not filmed can be predetermined as the reference sub-image offset and stored in the memory (e.g., non-volatile memory) of the electronic device 100. In some optional implementations, the reference sub-image offset can be calibrated using striped weights or weights with special patterns during the mass production stage (striped weights or weights with special patterns can be used to simulate fingers). The fingerprint recognition module in the electronic device 100 can read the reference sub-image offset from the memory.

[0127] In the embodiment of the present application, the film offset threshold may be predetermined and stored in a memory (eg, non-volatile memory) of the electronic device 100. The fingerprint recognition module in the electronic device 100 may read the film offset threshold from the memory.

[0128] Step S905, judging whether the display screen is filmed according to the difference between the actual sub-image offset and the reference sub-image offset and the film offset threshold. If the judgment result indicates that the display screen is not filmed, proceed to step S906; if the judgment result indicates that the display screen is filmed, proceed to step S908.

[0129] Step S906: determining a first anti-counterfeiting score based on the first weight coefficient.

[0130] Exemplarily, in the electronic device 100, if the display screen 13 is not affixed with a film, S1=A1*DL+B1*PL+C1*SL; wherein: S1 represents the anti-counterfeiting score when the display screen is not affixed with a film; DL represents the model prediction score, PL represents the degree of polarization, and SL represents the similarity; A1 represents the weight coefficient corresponding to the model prediction score when the display screen is not affixed with a film; B1 represents the weight coefficient of the degree of polarization when the display screen is not affixed with a film; C1 represents the weight coefficient of the similarity when the display screen is not affixed with a film.

[0131] Step S907, comparing the first anti-counterfeiting score with the first anti-counterfeiting score threshold, if the first anti-counterfeiting score is greater than the first anti-counterfeiting score threshold, determining that the input fingerprint is a fake fingerprint; otherwise, determining that the input fingerprint is a real fingerprint.

[0132] Step S908: Determine and obtain a second anti-counterfeiting score based on the second weight coefficient.

[0133] For example, in the electronic device 100, if the display screen is covered with a film, then S2 = A2*DL+B2*PL+C2*SL; where: S2 represents the anti-counterfeiting score when the display screen is covered with a film; DL represents the model prediction score, PL represents the polarization degree, and SL represents the similarity; A2 represents the weight coefficient corresponding to the model prediction score when the display screen is covered with a film; B2 represents the weight coefficient of the polarization degree when the display screen is covered with a film; C2 represents the weight coefficient of the similarity when the display screen is covered with a film. Preferably, A1 is less than A2, B1 is greater than B2, and C1 is greater than C2.

[0134] Step S909, comparing the second anti-counterfeiting score with the second anti-counterfeiting score threshold, if the second anti-counterfeiting score is greater than the second anti-counterfeiting score threshold, determining that the input fingerprint is a fake fingerprint; otherwise, determining that the input fingerprint is a real fingerprint.

[0135] The fingerprint anti-counterfeiting solution of the embodiment of the present application can stably and reliably detect whether the display screen is covered with a film, and adjust the weight coefficient of the anti-counterfeiting index based on whether the display screen is covered with a film. The anti-counterfeiting score calculated in this way can match whether the display screen is covered with a film, and more accurately determine the authenticity of the input fingerprint.

[0136] The present application also provides a fingerprint processing device, such as Fig.10 As shown, the device includes: an optical fingerprint device 1010 and a processing unit 1020. The optical fingerprint device 1010 is used to: image the fingerprint light signal reflected by the finger above the display screen to obtain at least two fingerprint sub-images, the fingerprint light signal includes a light signal in a first light path direction and a light signal in a second light path direction, and the first light path direction is different from the second light path direction. The processing unit 1020 is used in the film detection method and the fingerprint anti-counterfeiting method of the embodiment of the present application. The fingerprint processing device can be specifically Figure 1C The electronic device 100 shown in FIG. 1010 may be specifically Figure 1C The optical fingerprint device 12 shown in the figure, the processing unit 1020 can be specifically Figure 1C The application processor 141 (such as a central processing unit CPU) shown is used to execute the main steps of the methods of the above embodiments. In other alternative embodiments, the processing unit 1020 can also be implemented by other processing units or control units (such as a microcontroller MCU) with image processing capabilities.

[0137] The above are only preferred embodiments of the present application, and are not intended to limit the present application in any form. Although the present application has been disclosed as above with preferred embodiments, it is not intended to limit the present application. Any technical personnel in the field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present application. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A film detection method, applied to an electronic device including a display screen, characterized in that: The method comprises: Using an optical fingerprint device to collect a fingerprint sub-image of at least one optical path direction of an input fingerprint; Determine an actual sub-image offset according to the fingerprint sub-image of the at least one optical path direction; It is determined whether the display screen is covered with a film according to the actual sub-image offset and the reference sub-image offset, wherein the reference sub-image offset is the sub-image offset when the display screen is not covered with a film.

2. The method according to claim 1, characterized in that The step of judging whether the display screen is film-covered according to the actual sub-image offset and the reference sub-image offset includes: Determine a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; If the offset difference is greater than or equal to the film offset threshold, it is determined that the display screen has a film; If the offset difference is less than the film-sticking offset threshold, it is determined that the display screen is not film-sticking.

3. The method according to claim 1 or 2, characterized in that The method further includes: determining film thickness information according to the actual sub-image offset and the reference sub-image offset, including: Determine a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; The film thickness interval is determined according to a comparison result between the offset difference and at least one thickness threshold, and the at least one thickness threshold divides at least two film thickness intervals.

4. A fingerprint anti-counterfeiting method, applied to an electronic device including a display screen, characterized in that: The method comprises: Determine an actual sub-image offset according to a fingerprint sub-image of at least one optical path direction of the input fingerprint; Determining whether the display screen is filmed according to the actual sub-image offset and the reference sub-image offset, wherein the reference sub-image offset is the sub-image offset when the display screen is not filmed; Determining weight coefficients of at least two anti-counterfeiting indicators according to the result of judging whether the display screen is covered with a film, wherein the weight coefficient when the display screen is covered with a film is different from the weight coefficient when the display screen is not covered with a film; Determining an anti-counterfeiting score according to the at least two anti-counterfeiting indicators and the weight coefficient; The authenticity of the input fingerprint is determined according to the anti-counterfeiting score.

5. The method according to claim 4, characterized in that The method further includes: determining an anti-counterfeiting score threshold according to a result of determining whether the display screen is covered with a film, wherein the anti-counterfeiting score threshold when the display screen is covered with a film is different from the anti-counterfeiting score threshold when the display screen is not covered with a film; Determining the authenticity of the input fingerprint according to the anti-counterfeiting score includes: comparing the anti-counterfeiting score with the anti-counterfeiting score threshold, and determining the authenticity of the input fingerprint according to the comparison result.

6. The method according to claim 5, characterized in that Determining the weight coefficients of the at least two anti-counterfeiting indicators and the anti-counterfeiting score threshold according to the judgment result of whether the display screen is covered with a film includes: If the judgment result indicates that the display screen is not covered with a film, determine that the weight coefficients of the at least two anti-counterfeiting indicators are the first weight coefficients, and the anti-counterfeiting score threshold is the first anti-counterfeiting score threshold; If the judgment result indicates that the display screen is filmed, determine that the weight coefficients of the at least two anti-counterfeiting indicators are the second weight coefficients, and the anti-counterfeiting score threshold is the second anti-counterfeiting score threshold; The first weight coefficient is different from the second weight coefficient, and the first anti-counterfeiting score threshold is different from the second anti-counterfeiting score threshold.

7. The method according to claim 6, characterized in that The method further includes: determining film thickness information according to the actual sub-image offset and the reference sub-image offset; The weight coefficients of the at least two anti-counterfeiting indicators and the anti-counterfeiting score threshold are determined according to the judgment result of whether the display screen is covered with a film, including: if the judgment result is that the display screen is covered with a film, the second weight coefficient of the at least two anti-counterfeiting indicators is the weight coefficient corresponding to the film thickness information, and / or the second anti-counterfeiting score threshold is the anti-counterfeiting score threshold corresponding to the film thickness information.

8. The method according to claim 7, characterized in that The film thickness information includes a film thickness range, and determining the film thickness information according to the actual sub-image offset and the reference sub-image offset includes: Determine a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; Determine a film thickness interval according to a comparison result between the offset difference and at least one thickness threshold, wherein the at least one thickness threshold divides at least two film thickness intervals; The second weight coefficients corresponding to any two of the film thickness intervals are different.

9. The method according to any one of claims 4 to 8, characterized in that The at least two anti-counterfeiting indicators include a model prediction score, which is a score output by the model based on a fingerprint subgraph of at least two light path directions of the input fingerprint, indicating whether the input fingerprint is authentic.

10. The method according to claim 9, characterized in that The weight coefficient of the model prediction score when the display screen is covered with a film is greater than the weight coefficient when the display screen is not covered with a film.

11. The method according to claim 9, characterized in that The at least two anti-counterfeiting indicators also include: Polarization degree, the polarization degree is the light intensity difference of the fingerprint sub-image in at least two light path directions of the input fingerprint; and / or Similarity, where the similarity is the fingerprint pattern similarity of the fingerprint sub-images in at least two light path directions of the input fingerprint.

12. The method according to claim 11, characterized in that The fingerprint subgraphs of at least two optical path directions of the input fingerprint include: a first fingerprint subgraph in a first optical path direction, a second fingerprint subgraph in a second optical path direction, a third fingerprint subgraph in a third optical path direction, and a fourth fingerprint subgraph in a fourth optical path direction, wherein the first optical path direction and the fourth optical path direction are located on a first diagonal line of an imaging projection, and the second optical path direction and the third optical path direction are located on a second diagonal line of an imaging projection; The polarization degree is the ratio of the light intensity indication values ​​of two non-diagonal fingerprint sub-images; or The polarization degree is a ratio of a first light intensity indication value to a second light intensity indication value, wherein the first light intensity indication value is the sum of the light intensity indication values ​​of the two fingerprint subgraphs on the first diagonal line, and the second light intensity indication value is the sum of the light intensity indication values ​​of the two fingerprint subgraphs on the second diagonal line.

13. The method according to claim 11, characterized in that If the display screen is not covered with a film, then S1 = A1*DL + B1*PL + C1*SL; if the display screen is covered with a film, then S2 = A2*DL + B2*PL + C2*SL; in: S1 represents the anti-counterfeiting score of the display screen without film, and S2 represents the anti-counterfeiting score of the display screen with film; DL represents the model prediction score, PL represents the polarization degree, and SL represents the similarity; A1 and A2 represent the weight coefficients corresponding to the model prediction scores when the display screen is not covered with a film and when the display screen is covered with a film, respectively; B1 and B2 represent the weight coefficients of the polarization degree when the display screen is not coated with a film and when the display screen is coated with a film, respectively; C1 and C2 represent the weight coefficients of the similarity when the display screen is not covered with a film and when the display screen is covered with a film, respectively; A1 is smaller than A2, and: B1 is larger than B2, and / or C1 is larger than C2.

14. The method according to any one of claims 4 to 8, characterized in that The step of judging whether the display screen is film-covered according to the actual sub-image offset and the reference sub-image offset includes: Determine a difference between the actual sub-image offset and the reference sub-image offset to obtain an offset difference; If the offset difference is greater than or equal to the film offset threshold, it is determined that the display screen has a film; If the offset difference is less than the film-sticking offset threshold, it is determined that the display screen is not film-sticking.

15. A fingerprint processing device, characterized in that: Applicable to an electronic device having a display screen, the device comprises: Optical fingerprint device for: Imaging a fingerprint light signal reflected by a finger above the display screen to obtain at least two fingerprint sub-images, the fingerprint light signal comprising a light signal in a first light path direction and a light signal in a second direction, the first light path direction being different from the second light path direction; A processing unit is used to execute the film detection method described in any one of 1-3 or the fingerprint anti-counterfeiting method described in any one of 4-14.

16. An electronic device, characterized in that: The electronic device comprises: Display screen; The fingerprint processing device according to claim 15.

Images