CN117707361A - Sign input method based on finger fingerprint identification - Google Patents

Abstract

The application provides a symbol input method based on finger fingerprint identification, which relates to the technical field of symbol input, and is applied to a symbol input system, wherein the symbol input system comprises: the fingerprint image acquisition module, the finger positioning module, the symbol mapping module and the feedback module, wherein the method comprises the following steps: collecting fingerprint images of the user finger knocked on the touch screen through the fingerprint image collecting module; comparing the collected fingerprint image with a stored fingerprint template by utilizing the finger positioning module, and identifying finger information and knocking position information of the fingerprint image; mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation through the symbol mapping module; and forming visual feedback based on the symbols through the feedback module, and displaying the symbols on a display screen.

Description

Sign input method based on finger fingerprint identification

Technical Field

The application relates to the technical field of symbol input, in particular to a symbol input method based on finger fingerprint identification.

Background

At present, touch screens are still the main input modes of mobile terminals such as smart phones, tablets and the like. However, a long-time staring at a screen soft keyboard for symbol input is likely to cause visual fatigue, and a touch screen input too dependent on visual feedback is not friendly for a user with vision impairment.

Furthermore, the input efficiency of touch screen devices is often limited by user proficiency, and it may be necessary for a beginner to spend a significant amount of time recognizing the letter layout and finding the designated key position. The touch screen input mode can achieve higher input efficiency only when the user can accurately see their finger positions and specific keys on the mobile phone keyboard. Although there are voice and gesture based input modes, each of these modes has its own environmental limitations. Therefore, to improve the input efficiency and user experience, a new input mode independent of the visual positioning key needs to be developed.

Disclosure of Invention

In view of the foregoing, embodiments of the present application provide a method and system for inputting symbols based on finger fingerprinting, so as to overcome or at least partially solve the foregoing problems.

In a first aspect of the embodiments of the present application, a symbol input method based on finger fingerprint recognition is provided, and the symbol input method is applied to a symbol input system, where the symbol input system includes: the fingerprint image acquisition module, the finger positioning module, the symbol mapping module and the feedback module, wherein the method comprises the following steps:

Collecting fingerprint images of the user finger knocked on the touch screen through the fingerprint image collecting module;

comparing the collected fingerprint image with a stored fingerprint template by utilizing the finger positioning module, and identifying to obtain finger information and knocking position information of the fingerprint image;

mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation through the symbol mapping module;

and forming visual feedback based on the symbols through the feedback module, and displaying the symbols on a display screen.

In one possible implementation manner, the comparing, by the finger positioning module, the collected fingerprint image with a stored fingerprint template, and identifying finger information of the fingerprint image includes:

the fingerprint image and the stored fingerprint templates are matched one by one through the finger positioning module, and the finger type of the user finger in the fingerprint image is determined; the finger type at least comprises: left hand, right hand, index finger, ring finger, little finger, thumb and middle finger;

determining a finger part to which the fingerprint image belongs, wherein the finger part at least comprises: finger tips, finger belly, left finger side, right finger side.

In one possible embodiment, the symbol input system further comprises: a fingerprint registration module; the method further comprises the steps of:

for a registered user used for the first time, the fingerprint registration module starts a fingerprint sensor to acquire registered fingerprint images of different fingers of the registered user; the enrolled fingerprint image is a full rolling fingerprint image for a single finger and/or a planar fingerprint image for each of the finger parts of a single finger;

extracting fingerprint characteristics of the registered fingerprint image to generate a fingerprint template of each finger of the registered user;

and storing fingerprint templates of all fingers of the registered user in the fingerprint database.

In a possible implementation manner, after the registered fingerprint image is acquired, the method further includes:

performing fingerprint quality evaluation on the registered fingerprint image, and determining the fingerprint quality of the registered fingerprint image;

and re-acquiring the registered fingerprint image of the finger under the condition that the fingerprint quality of the registered fingerprint image is lower than a preset quality threshold.

In one possible implementation manner, the knocking position information of the fingerprint image is obtained by the following steps:

Under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, a touch screen of the fingerprint sensor is divided into a plurality of areas, area information corresponding to the touch screen knocked by the fingers of the user in the fingerprint image is obtained, and the area information is used as the knocking position information;

under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors which only accommodate single fingers, acquiring identity information of the small-area sensors which acquire the fingerprint images, and taking the identity information of the small-area sensors as the knocking position information.

In one possible embodiment, the method further comprises:

under the condition that the fingerprint sensor is a small-area sensor which only supports single finger output, symbol mapping is carried out according to finger types and finger parts, and the symbol mapping relation is generated;

dividing a touch screen of the fingerprint sensor into a plurality of areas under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, and performing symbol mapping by combining the finger type, the finger position and different areas of the touch screen to generate the symbol mapping relation;

In the case that the fingerprint sensor is a combination of a plurality of small-area sensors which only accommodate a single finger, symbol mapping is performed in combination with different combinations of finger type, finger position and the small-area sensors, and the symbol mapping relation is generated.

In a possible implementation manner, the matching the fingerprint image with the fingerprint template stored in the fingerprint database includes:

the finger positioning module performs feature extraction on the fingerprint image by using a feature extraction algorithm to obtain fingerprint features; the feature extraction algorithm is at least one of a minutiae feature extraction algorithm, a local feature extraction algorithm, a ridge line feature extraction algorithm and a deep learning descriptor extraction algorithm;

the finger positioning module utilizes a matching algorithm to match the fingerprint characteristics with fingerprint templates stored in the fingerprint database, wherein the matching algorithm is at least one of a sliding window searching method, a correlation matching method, a characteristic point matching method and a similarity distance judging method.

In one possible embodiment, the method further comprises:

forming, by the feedback module, acoustic feedback based on the symbols, and/or,

And forming vibration feedback based on the symbol through the feedback module.

In one possible embodiment, the method further comprises:

under the condition that the fingerprint images comprise a plurality of fingerprints, splitting the fingerprint images into a plurality of independent fingerprint images, and utilizing the finger positioning module to match each independent fingerprint image with a fingerprint template stored in a fingerprint database, so as to obtain finger information and knocking position information in each independent fingerprint image.

In a possible implementation manner, after identifying the finger information and the knocking position information, the method further includes:

determining a knocking area according to the finger information and the knocking position information;

matching the knocking area with a pre-defined symbol mapping table to obtain a symbol corresponding to the knocking area;

and outputting the symbol corresponding to the knocking area to display equipment.

The second aspect of the embodiments of the present application further provides a symbol input system based on finger fingerprint recognition, where the system includes:

the fingerprint image acquisition module is used for acquiring fingerprint images of the user finger knocked on the touch screen;

The finger positioning module is used for comparing the acquired fingerprint image with a stored fingerprint template and identifying finger information and knocking position information of the fingerprint image;

the symbol mapping module is used for mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation;

and the feedback module is used for forming visual feedback based on the symbols and displaying the symbols on a display screen.

In one possible embodiment, the finger positioning module comprises:

the finger type determining submodule is used for matching the fingerprint image with the stored fingerprint templates one by one and determining the finger type of the user finger in the fingerprint image; the finger type at least comprises: left hand, right hand, index finger, ring finger, little finger, thumb and middle finger;

a finger position determining submodule, configured to determine a finger position to which the fingerprint image belongs, where the finger position at least includes: finger tips, finger belly, left finger side, right finger side.

In one possible embodiment, the system further comprises: fingerprint registration module for:

starting a fingerprint sensor for a first-time used registered user, and collecting registered fingerprint images of different fingers of the registered user; the enrolled fingerprint image is a full rolling fingerprint image for a single finger and/or a planar fingerprint image for each of the finger parts of a single finger;

Extracting fingerprint characteristics of the registered fingerprint image to generate a fingerprint template of each finger of the registered user;

and storing fingerprint templates of all fingers of the registered user in a fingerprint database.

In one possible embodiment, the system further comprises:

the quality evaluation module is used for evaluating the fingerprint quality of the registered fingerprint image after the registered fingerprint image is acquired, and determining the fingerprint quality of the registered fingerprint image;

and the reminding module is used for collecting the registered fingerprint image of the finger again under the condition that the fingerprint quality of the registered fingerprint image is lower than a preset quality threshold value.

In one possible embodiment, the finger positioning module comprises:

the first knocking position information acquisition sub-module is used for dividing a touch screen of the fingerprint sensor into a plurality of areas under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, acquiring area information corresponding to the touch screen knocked by the fingers of the user in the fingerprint image, and taking the area information as the knocking position information;

the second knocking position information obtaining sub-module is used for obtaining the identity information of the small-area sensor for collecting the fingerprint image under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors only containing single fingers, and taking the identity information of the small-area sensor as the knocking position information.

In one possible embodiment, the system further comprises:

the first symbol mapping relation generation module is used for performing symbol mapping according to the finger type and the finger position to generate the symbol mapping relation under the condition that the fingerprint sensor is a small-area sensor which only supports single finger output;

the second symbol mapping relation generation module is used for dividing a touch screen of the fingerprint sensor into a plurality of areas and carrying out symbol mapping by combining a finger type, a finger part and different areas of the touch screen under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers so as to generate the symbol mapping relation;

and the third symbol mapping relation generation module is used for carrying out symbol mapping by combining different combinations of the finger type, the finger part and the small-area sensor under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors only containing a single finger, so as to generate the symbol mapping relation.

In a possible implementation manner, the finger positioning module is further configured to perform feature extraction on the fingerprint image by using a feature extraction algorithm to obtain fingerprint features; the feature extraction algorithm is at least one of a minutiae feature extraction algorithm, a local feature extraction algorithm, a ridge line feature extraction algorithm and a deep learning descriptor extraction algorithm;

The finger positioning module is further configured to match the fingerprint feature with a fingerprint template stored in the fingerprint database by using a matching algorithm, where the matching algorithm is at least one of a sliding window searching method, a correlation matching method, a feature point matching method, and a similarity distance judging method.

In a possible embodiment, the feedback module is further configured to form acoustic feedback based on the symbol and/or form vibration feedback based on the symbol.

In a possible implementation manner, the finger positioning module is further configured to split the fingerprint image into a plurality of independent fingerprint images when the fingerprint image includes a plurality of fingerprints, match each of the independent fingerprint images with a fingerprint template stored in a fingerprint database, and obtain finger information and tapping position information in each of the independent fingerprint images.

In one possible embodiment, the apparatus further comprises:

the knocking area determining module is used for determining a knocking area according to the finger information and the knocking position information after the finger information and the knocking position information are obtained through recognition;

The matching module is used for matching the knocking area with a predefined symbol mapping table to obtain a symbol corresponding to the knocking area;

and the display module is used for outputting the symbol corresponding to the knocking area to display equipment.

The third aspect of the embodiment of the application further provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps in the symbol input method based on finger fingerprint recognition according to the first aspect of the embodiment of the application.

The fourth aspect of the embodiments of the present application further provides a computer readable storage medium, on which a computer program/instruction is stored, which when executed by a processor, implements the steps in the finger fingerprint recognition-based symbol input method according to the first aspect of the embodiments of the present application.

A fifth aspect of the embodiments of the present application also provides a computer program product, which when run on an electronic device causes a processor to carry out the steps in the finger-fingerprint-identification-based symbol input method according to the first aspect of the embodiments of the present application.

The symbol input method based on finger fingerprint identification is applied to a symbol input system, and the symbol input system comprises the following steps: the fingerprint image acquisition module, the finger positioning module, the symbol mapping module and the feedback module, wherein the method comprises the following steps: collecting fingerprint images of the user finger knocked on the touch screen through the fingerprint image collecting module; comparing the collected fingerprint image with a stored fingerprint template by utilizing the finger positioning module, and identifying to obtain finger information and knocking position information of the fingerprint image; mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation through the symbol mapping module; and forming visual feedback based on the symbols through the feedback module, and displaying the symbols on a display screen.

The fingerprint identification method and the fingerprint identification device have the advantages that the fingerprint image is matched with the fingerprint template stored in the fingerprint database by collecting the fingerprint image of the user knocking on the touch screen, so that the fingerprint is identified and positioned, the finger information (such as which finger of a registered user the fingerprint belongs to) of the fingerprint belongs to, and the knocking position information (the specific region of the finger knocking on the touch screen) indicated by the fingerprint image are determined. Therefore, the method and the device can determine the symbol indicated by the fingerprint image according to the preset symbol mapping relation (the mapping relation among finger information, knocking position information and the symbol), display the symbol on a display screen and finish symbol input. According to the fingerprint recognition method and device, the finger and the knocking position are recognized, the predefined symbol mapping relation is utilized, finger typing input and command control can be achieved without looking at a keyboard, meanwhile, recognition of fingerprint images can be utilized, and identity recognition is achieved in an auxiliary mode while symbol input is achieved, so that the use safety is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments of the present application will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flowchart of steps of a symbol input method based on finger fingerprint recognition according to an embodiment of the present application;

FIG. 2 is a schematic diagram of symbol mapping relationship of two finger sensors according to an embodiment of the present disclosure;

fig. 3 is a schematic flow chart of a fingerprint registration process according to an embodiment of the present application;

fig. 4 is a schematic diagram of a symbol input flow based on fingerprint recognition according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a symbol input system according to an embodiment of the present disclosure;

fig. 6 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

At present, touch screens are still the main input modes of mobile terminals such as smart phones, tablets and the like. However, a long-time staring at a screen soft keyboard for symbol input is likely to cause visual fatigue, and a touch screen input too dependent on visual feedback is not friendly for a user with vision impairment. Furthermore, the input efficiency of touch screen devices is often limited by user proficiency, and it may be necessary for a beginner to spend a significant amount of time recognizing the letter layout and finding the designated key position. The touch screen input mode can achieve higher input efficiency only when the user can accurately see their finger positions and specific keys on the mobile phone keyboard. Although there are voice and gesture based input modes, each of these modes has its own environmental limitations.

In view of the above problems, an embodiment of the present application provides a symbol input method and system based on finger fingerprint recognition, so as to solve the problems that the touch screen typing is too dependent on visual feedback. The symbol input method based on finger fingerprint recognition provided in the embodiments of the present application is described in detail below with reference to the accompanying drawings through some embodiments and application scenarios thereof.

An embodiment of the present application provides a symbol input method based on finger fingerprint recognition, which is applied to a symbol input system, where the symbol input system includes: referring to fig. 1, fig. 1 is a step flowchart of a symbol input method based on finger fingerprint identification provided in an embodiment of the present application, as shown in fig. 1, the method includes:

step S101, collecting fingerprint images of the user finger knocked on the touch screen through the fingerprint image collecting module.

In this embodiment, the symbol input system includes a fingerprint image capturing module, which is configured to capture a fingerprint image, and specifically, the fingerprint image capturing module includes a fingerprint sensor and a touch screen adapted to the fingerprint sensor. The touch screen of the fingerprint sensor can be arranged at any position suitable for operation on corresponding electronic equipment such as a mobile phone, a tablet computer, a watch and the like.

When a user needs to input a symbol, the user clicks a corresponding area on the touch screen with a finger, the fingerprint sensor detects the clicking action, and image acquisition is performed to obtain a fingerprint image pressed on the touch screen by the finger of the user. When the user needs to execute the symbol input operation in actual application, the corresponding virtual keyboard can be displayed on the symbol input area of the touch screen, so that the user is assisted to accurately strike the corresponding position of the touch screen according to the virtual keyboard.

Further, the fingerprint sensor in the fingerprint image acquisition module may be an optical sensor, an ultrasonic sensor, a capacitive sensor, or the like, and in this embodiment, the type of the fingerprint sensor is not limited. The hardware carrier (such as a fingerprint sensor, a touch screen and the like) related to the embodiment of the application is suitable for various electronic input devices, including but not limited to mobile phones, tablets, smart watches, wearable devices and the like.

In one possible embodiment, the method further comprises:

under the condition that the fingerprint images comprise a plurality of fingerprints, splitting the fingerprint images into a plurality of independent fingerprint images, and utilizing the finger positioning module to match each independent fingerprint image with a fingerprint template stored in a fingerprint database, so as to obtain finger information and knocking position information in each independent fingerprint image.

In the actual application process, a user can only use a single finger to strike the touch screen, and fingerprints of only a single finger exist in the fingerprint image acquired by the fingerprint image acquisition module; the user can also utilize a plurality of fingers to strike the touch screen simultaneously, and fingerprints of a plurality of fingers can exist simultaneously in the fingerprint image acquired by the fingerprint image acquisition module.

In the present embodiment, in the case where a plurality of fingerprints are included in a fingerprint image, the fingerprint image is split into a plurality of independent fingerprint images. Specifically, the fingerprint image may be segmented into a plurality of smaller sub-images such that there is only a finger print of one finger in each sub-image. After the multiple independent fingerprint images are obtained through splitting, step S102 is executed on each independent fingerprint image, and each independent fingerprint image is matched with a fingerprint template stored in a fingerprint database by utilizing a finger positioning module, so that finger information and knocking position information in each independent fingerprint image are obtained.

Step S102, comparing the collected fingerprint image with a stored fingerprint template by utilizing the finger positioning module, and identifying to obtain finger information and knocking position information of the fingerprint image.

After the fingerprint image is acquired, fingerprint identification and finger positioning are performed on the fingerprint image by utilizing a finger positioning module. Specifically, the fingerprint image is subjected to feature extraction to obtain fingerprint features, and then the extracted fingerprint features are matched with fingerprint templates stored in a fingerprint database in advance. The fingerprint template is a fingerprint template of a finger itself stored in the fingerprint database by a registration operation before the first use by the user.

In practical application, there may be multiple registered users, so that the fingerprint database stores multiple fingerprint templates belonging to different users, and when the fingerprint features are matched with the fingerprint templates one by one, the identity of the user currently executing the symbol input operation is determined according to the matched fingerprint templates. When the fingerprint features are not matched with all fingerprint templates in the fingerprint database, determining that the finger in the fingerprint image does not belong to a registered user, stopping the symbol input operation, and generating an input failure reminder.

In this embodiment, the finger positioning module matches the currently collected fingerprint with the registered fingerprint to determine the finger position, where the finger position may be the finger level of the left little finger, the right index finger, or the like. Specifically, when the fingerprint features extracted from the fingerprint image are successfully matched with the fingerprint templates stored in the fingerprint database, determining the finger information in the fingerprint image according to the information corresponding to the fingerprint templates, wherein the finger information comprises the type information of the currently pressed finger in the fingerprint image (for example, the finger is a right index finger). The type information can be specifically classified into: left hand, right hand, index finger, ring finger, little finger, thumb and middle finger. Correspondingly, each fingerprint template stored in the fingerprint database corresponds to one finger type of the registered user. When a user registers, fingerprint collection needs to be carried out on each individual finger, and an independent fingerprint template is generated, so that each fingerprint template corresponds to one finger type.

Further, it is also required to acquire tapping position information according to a fingerprint image, where the tapping position information indicates a specific area where a finger taps on the touch screen, for example, a left area of the touch screen is tapped by the finger in the fingerprint image. For example, specific position information of the finger tap can be calculated according to position coordinates of the finger print in the fingerprint image.

In a possible implementation manner, the matching the fingerprint image with the fingerprint template stored in the fingerprint database includes:

the finger positioning module performs feature extraction on the fingerprint image by using a feature extraction algorithm to obtain fingerprint features; the feature extraction algorithm is at least one of a minutiae feature extraction algorithm, a local feature extraction algorithm, a ridge line feature extraction algorithm and a deep learning descriptor extraction algorithm.

The finger positioning module utilizes a matching algorithm to match the fingerprint characteristics with fingerprint templates stored in the fingerprint database, wherein the matching algorithm is at least one of a sliding window searching method, a correlation matching method, a characteristic point matching method and a similarity distance judging method.

Optionally, the symbol input system further comprises an auxiliary module for combining other input and biological feature recognition technologies, so that the safety of the system is improved.

In one possible implementation manner, the comparing, by the finger positioning module, the collected fingerprint image with a stored fingerprint template, and identifying finger information of the fingerprint image includes:

the fingerprint image and the stored fingerprint templates are matched one by one through the finger positioning module, and the finger type of the user finger in the fingerprint image is determined; the finger type at least comprises: left hand, right hand, index finger, ring finger, little finger, thumb and middle finger;

determining a finger part to which the fingerprint image belongs, wherein the finger part at least comprises: finger tips, finger belly, left finger side, right finger side.

In the present embodiment, the finger information includes: the type information of the currently pressed finger in the fingerprint image (e.g., the finger is the right index finger), and the finger location information of the finger (e.g., the finger fingerprint belongs to the fingertip of the right index finger). Specifically, after the fingerprint image is matched with the fingerprint templates stored in the fingerprint database through the finger positioning module, the finger information of the fingerprint image is identified according to the matched fingerprint templates, specifically, after the type of the finger in the currently acquired fingerprint image is identified and determined (for example, the finger performing the knocking operation in the fingerprint image is the index finger of the right hand), the finger position (for example, the finger performing the knocking operation in the fingerprint image is the middle finger tip and the middle finger belly of the right hand) of the finger fingerprint in the fingerprint image can be further determined. In the process of actually knocking the touch screen, the user's finger may not completely release the screen of the touch screen, so that the finger print in the fingerprint image acquired by the fingerprint sensor is incomplete. If the fingerprint database stores planar fingerprints or complete rolling fingerprints with different postures of the same finger, the finger positions (such as fingertips, finger pads, left finger sides and right finger sides) contacted with the touch screen can be judged. Correspondingly, each fingerprint template stored in the fingerprint database corresponds to a finger position in one finger type of the registered user. When a user registers a fingerprint, the user needs to acquire the fingerprint for each individual finger to obtain planar fingerprints or complete rolling fingerprints with different postures of the same finger, and independent fingerprint templates are respectively generated for different parts (finger tip, finger belly, left finger side and right finger side) of the finger, so that each fingerprint template corresponds to one finger part in one finger type.

In one possible implementation, the knocking position information of the fingerprint image is obtained by the following steps:

under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, a touch screen of the fingerprint sensor is divided into a plurality of areas, area information corresponding to the touch screen knocked by the fingers of the user in the fingerprint image is obtained, and the area information is used as the knocking position information;

under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors which only accommodate single fingers, acquiring identity information of the small-area sensors which acquire the fingerprint images, and taking the identity information of the small-area sensors as the knocking position information.

In this embodiment, when acquiring the knocking position information of the finger in the fingerprint image, the size of the touch screen in the fingerprint sensor and the symbol mapping need to be adjusted accordingly. Specifically, for a small-area sensor capable of accommodating only one finger (i.e., the area of the touch screen adapted by the fingerprint sensor is smaller than that of two fingers), it is not suitable to divide the touch screen into areas, and the corresponding knocking position information is the same position information.

For a large-area sensor capable of accommodating multiple finger strokes (i.e., the area of the touch screen adapted by the fingerprint sensor is not smaller than the area of two fingers), the touch screen can be divided into a plurality of areas. Correspondingly, the knocking position information is used for indicating a specific region of the finger knocking in the fingerprint image. For example, the touch screen of the fingerprint sensor can accommodate two fingers at the same time, so that the touch screen can be divided into a left area and a right area, and the tapping position information acquired according to the fingerprint image is used for indicating whether the finger taps a left area or a right area of the touch screen.

Furthermore, the fingerprint sensor may be a combination of a plurality of small area sensors accommodating only a single finger, and the corresponding tap position information is used to indicate which small area sensor in the combination, i.e. the identity information of the small area sensor, e.g. the number of the sensor, the finger taps.

Step S103, mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation through the symbol mapping module.

In this embodiment, the symbol mapping module maps the finger information (one or more identified tapping positions) and the tapping position information (tapping areas of the fingers) of the acquired fingerprint image to corresponding symbols by using a preset symbol mapping relationship, where the symbols may be alphabetic symbols, numeric symbols, punctuation marks, functional symbols, and the like.

In one possible embodiment, the method further comprises:

under the condition that the fingerprint sensor is a small-area sensor which only supports single finger output, symbol mapping is carried out according to finger types and finger parts, and the symbol mapping relation is generated;

dividing a touch screen of the fingerprint sensor into a plurality of areas under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, and performing symbol mapping by combining the finger type, the finger position and different areas of the touch screen to generate the symbol mapping relation;

in the case that the fingerprint sensor is a combination of a plurality of small-area sensors which only accommodate a single finger, symbol mapping is performed in combination with different combinations of finger type, finger position and the small-area sensors, and the symbol mapping relation is generated.

In this embodiment, before symbol input is performed, a symbol mapping relationship, that is, a mapping relationship between finger information, tap position information, and a symbol, needs to be defined. In the process of executing symbol input by a user, symbol mapping relations can be synchronously displayed on a display screen, so that the user is assisted to execute knocking actions, and the accuracy of symbol input is further improved. Specifically, the symbol mapping mode is related to the size of the touch screen in the fingerprint sensor, if the fingerprint sensor is a small-area sensor, that is, the area of the touch screen adapted to the sensor is small, only one finger is supported, the absolute position of the finger in the sensor area can be not considered, symbol mapping is performed only according to the finger type (such as middle finger, little finger and thumb) and the finger part (fingertip and finger belly) contacted with the touch screen, and a symbol mapping relation is generated.

If the area of the touch screen of the fingerprint sensor is large, for example, two fingers can be accommodated at the same time, the touch screen can be divided into two areas (left area and right area), and symbol mapping is performed by combining the finger type and the finger position. If the touch screen is larger in area, more fingers are allowed to strike simultaneously, more areas (e.g., a first area, a second area, etc.) can be divided, more finger combinations and area combinations can be selected, and a symbol mapping table which is more in accordance with ergonomics and even special requirements of individuals can be selected from the symbol mapping table.

If the fingerprint sensor is a combination of a plurality of small area sensors which only accommodate a single finger, the fingerprint sensor is used as a single area every other small area sensor, so that the symbol mapping relationship is generated by combining the area information, the finger type and the finger position. In addition, the user can define the mapping relation among the finger combination, the knocking position and the symbol according to the actual requirement.

In one possible implementation, taking as an example a fingerprint sensor capable of accommodating two fingers simultaneously, the touch screen is divided into two areas (left area, right area), and symbol mapping is performed in combination with the finger type and the finger position. Referring to fig. 2, fig. 2 shows a symbol mapping relation diagram of two finger sensors, and as shown in fig. 2, a user's left hand set is provided, and mainly uses the thumb of the left hand and the five fingers of the right hand to type, before first use, the user needs to register the fingerprints of the thumb of the left hand and the five fingers of the right hand respectively, and the fingerprints of each finger are recorded in a fingerprint database. In this embodiment, symbol mapping is performed on three pieces of information including a touch screen area, a finger type, and a finger position of the fingerprint sensor. Specifically, in the touch screen area part, left and right area information can be obtained; six pieces of information of a right thumb (0), a right index finger (1), a right middle finger (2), a right ring finger (3), a right little finger (4) and a left thumb (5) are obtained in the finger type part; in the finger portion, two kinds of information of the finger belly o and the fingertip can be obtained.

By using the fingerprint sensor, fingerprint image acquisition is performed when a user taps the touch screen, the acquired fingerprint image is compared with a stored fingerprint template, it is determined that the finger tapped by the user at present is the index finger (1) of the right hand, the finger part tapped by the touch screen is the finger belly o, then it is determined that the tapped area of the touch screen is the right side area, and according to the symbol mapping relation in fig. 2, it can be known that the corresponding output symbol is W.

Furthermore, different types of symbol inputs may have respective independent symbol mappings. For example, fig. 2 shows the symbol mapping relation of the alphabetic symbol and the mapping relation of the numeric symbol, and when the current symbol input interface is the input interface of the alphabetic symbol, the required alphabetic symbol needs to be obtained by matching according to the symbol mapping relation of the alphabetic symbol. Illustratively, comparing the fingerprint image with a stored fingerprint template, and identifying the finger information as: the finger of the current user knocking the touch screen is a middle finger (2) of the right hand, the finger part knocking the touch screen is a fingertip, and the knocking position information is obtained by: in the right area, the letter input mode is currently adopted, and the corresponding symbol can be determined to be the letter L through the symbol mapping relation of the letter symbol shown in fig. 2.

Or when the current symbol input interface is the input interface of the digital symbol, comparing the fingerprint image with the stored fingerprint template, and identifying to obtain the finger information as follows: the finger of the current user knocking the touch screen is a middle finger (2) of the right hand, the finger part knocking the touch screen is a fingertip, and the knocking position information is obtained by: in the left area, the corresponding symbol is determined to be the number 7 by the symbol mapping relationship of the number symbol shown in fig. 2.

In a possible implementation manner, after identifying the finger information and the knocking position information, the method further includes:

determining a knocking area according to the finger information and the knocking position information;

matching the knocking area with a pre-defined symbol mapping table to obtain a symbol corresponding to the knocking area;

and outputting the symbol corresponding to the knocking area to display equipment.

In this embodiment, a corresponding symbol mapping table is generated based on the tap region and the symbol, so that in actual application, the tap region is determined according to finger information and tap position information obtained by identifying from the fingerprint image, the tap region is matched with the symbol mapping table, so as to obtain a corresponding symbol, and the symbol is displayed on a display device.

In addition, in order to realize input error correction, the accuracy of symbol input is further improved, and the input symbol combination can be subjected to error correction by utilizing a natural language statistical model.

And step S104, forming visual feedback based on the symbol through the feedback module, and displaying the symbol on a display screen.

In this embodiment, the finger positioning module determines one or more types of knocking fingers, finger positions of knocking fingers and knocking sensor areas according to the current collected image of the sensor, maps to obtain a symbol, and displays the symbol on the display screen through the feedback module, so that visual feedback is realized.

In one possible embodiment, the method further comprises:

forming, by the feedback module, acoustic feedback based on the symbols, and/or,

and forming vibration feedback based on the symbol through the feedback module.

In this embodiment, the feedback module may feedback the symbol input in various manners, such as visual, audio, and tactile. Specifically, by generating visual feedback, displaying the symbol obtained by mapping on a display screen; synchronously playing the pronunciation of the symbol by generating sound feedback; by generating the vibration feedback, a vibration is generated synchronously each time a symbol is successfully output. Therefore, through one or more feedback modes, the symbol input efficiency is further improved, and the visual dependence of a user during typing is reduced.

In one possible embodiment, the symbol input system further comprises: a fingerprint registration module; the method further comprises the steps of:

for a registered user used for the first time, the fingerprint registration module starts a fingerprint sensor to acquire registered fingerprint images of different fingers of the registered user; the enrolled fingerprint image is a full rolling fingerprint image for a single finger and/or a planar fingerprint image for each of the finger parts of a single finger;

extracting fingerprint characteristics of the registered fingerprint image to generate a fingerprint template of each finger of the registered user;

and storing fingerprint templates of all fingers of the registered user in a fingerprint database.

In this embodiment, registration needs to be completed before the user performs the first symbol input, so as to store own fingerprint data. Specifically, referring to fig. 3, fig. 3 shows a flow chart of a fingerprint registration process, and as shown in fig. 3, after a fingerprint registration module receives a registration request, fingerprint image acquisition is performed for different fingers of a registered user, so as to obtain a registered fingerprint image. In the process, different symbol mapping relations have different requirements on acquisition of registered fingerprint images. Specifically, if the preset symbol mapping relationship is a symbol mapping relationship only for the finger type layer, and there is no mapping relationship related to the finger position of the finger striking the touch screen, then only a complete rolling fingerprint image of each finger of the user needs to be acquired during image acquisition. If there are different finger positions and symbol mapping relationships in the symbol mapping relationship, then in image acquisition, a planar fingerprint image of each finger position of each finger needs to be acquired, for example, a fingerprint image of a fingertip position of a right index finger and a fingerprint image of a finger belly position of the right index finger.

As shown in fig. 3, after the image acquisition is completed, the acquired registered fingerprint image needs to be preprocessed through operations such as enhancement, clipping, correction and the like.

In a possible implementation manner, after the registered fingerprint image is acquired, the method further includes:

performing fingerprint quality evaluation on the registered fingerprint image, and determining the fingerprint quality of the registered fingerprint image;

and re-acquiring the registered fingerprint image of the finger under the condition that the fingerprint quality of the registered fingerprint image is lower than a preset quality threshold. Specifically, when registering a fingerprint, a fingerprint quality judging function may be added to automatically identify a fingerprint image with poor quality (a registered fingerprint image with fingerprint quality lower than a preset quality threshold), and remind the user to re-register the finger so as to improve the quality of the registered fingerprint template.

In this embodiment, for the obtained registered fingerprint image, feature extraction is performed on the registered fingerprint image to obtain fingerprint features. Specifically, feature extraction may be performed by using a feature extraction algorithm, where the feature extraction algorithm may be one or more of a minutiae feature extraction algorithm, a ridge valley feature extraction algorithm, and a local feature extraction algorithm, so as to extract fingerprint features (such as a direction field, a period, an endpoint, a bifurcation point, or other machine learning depth features) from a registered fingerprint image, generate a fingerprint template of the registered user, and store the fingerprint template in a fingerprint database.

Through the registering step, fingerprint templates of all authorized users are stored in the fingerprint database, after the current fingerprint image is acquired, the fingerprint image is matched with the fingerprint templates in the fingerprint database one by one, if the fingerprint templates are not matched, the user is not an authorized user, so that the user is authenticated in the symbol input process, and the system safety is further improved.

Referring to fig. 4, fig. 4 shows a schematic symbol input flow diagram based on fingerprint identification, and as shown in fig. 4, when a user uses the symbol input system for the first time, fingerprint registration is performed by using a fingerprint registration module, a fingerprint sensor is controlled by the fingerprint registration module to collect registered fingerprint images of the user, fingerprint features of each typing finger are extracted from the registered fingerprint images, and a fingerprint template is generated. After registration is completed, when a user needs to input a symbol, a fingerprint sensor collects a fingerprint image, a finger positioning module performs image preprocessing and feature extraction to obtain the fingerprint feature of one or more current knocking fingerprints, the fingerprint feature is matched with a fingerprint template in a fingerprint database, so that the type of the finger in the fingerprint image and the finger position of the finger knocking the touch screen are determined, the region (knocking position information) of the knocking touch screen is determined, then symbol mapping is performed according to the information through a symbol mapping module according to a preset symbol mapping relation to obtain the symbol, and finally feedback such as vision, sound, vibration and the like is generated through a feedback module based on the symbol. Therefore, the technical scheme that finger symbol input (namely touch typing) and command control can be performed without looking at a keyboard is realized by identifying the struck finger and based on the predefined symbol mapping relation. Compared with the prior art, the symbol input method provided by the embodiment of the application is more natural and visual in operation, personalized input can be realized by customizing symbol mapping, the problems of visual dependence, low efficiency, lack of personalized input and the like are solved, identity recognition can be realized in an auxiliary mode, and the use safety is improved.

The second aspect of the embodiments of the present application further provides a symbol input system based on finger fingerprint recognition, referring to fig. 5, fig. 5 shows a schematic structural diagram of a symbol input system, as shown in fig. 5, where the system includes:

the fingerprint image acquisition module is used for acquiring fingerprint images of the user finger knocked on the touch screen;

the finger positioning module is used for comparing the acquired fingerprint image with a stored fingerprint template and identifying finger information and knocking position information of the fingerprint image;

the symbol mapping module is used for mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation;

and the feedback module is used for forming visual feedback based on the symbols and displaying the symbols on a display screen.

In one possible embodiment, the finger positioning module comprises:

the finger type determining submodule is used for matching the fingerprint image with the stored fingerprint templates one by one and determining the finger type of the user finger in the fingerprint image; the finger type at least comprises: left hand, right hand, index finger, ring finger, little finger, thumb and middle finger;

A finger position determining submodule, configured to determine a finger position to which the fingerprint image belongs, where the finger position at least includes: finger tips, finger belly, left finger side, right finger side.

In one possible embodiment, the system further comprises: fingerprint registration module for:

starting a fingerprint sensor for a first-time used registered user, and collecting registered fingerprint images of different fingers of the registered user; the enrolled fingerprint image is a full rolling fingerprint image for a single finger and/or a planar fingerprint image for each of the finger parts of a single finger;

extracting fingerprint characteristics of the registered fingerprint image to generate a fingerprint template of each finger of the registered user;

and storing fingerprint templates of all fingers of the registered user in a fingerprint database.

In one possible embodiment, the system further comprises:

the quality evaluation module is used for evaluating the fingerprint quality of the registered fingerprint image after the registered fingerprint image is acquired, and determining the fingerprint quality of the registered fingerprint image;

and the reminding module is used for collecting the registered fingerprint image of the finger again under the condition that the fingerprint quality of the registered fingerprint image is lower than a preset quality threshold value.

In one possible embodiment, the finger positioning module comprises:

the first knocking position information acquisition sub-module is used for dividing a touch screen of the fingerprint sensor into a plurality of areas under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, acquiring area information corresponding to the touch screen knocked by the fingers of the user in the fingerprint image, and taking the area information as the knocking position information;

the second knocking position information obtaining sub-module is used for obtaining the identity information of the small-area sensor for collecting the fingerprint image under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors only containing single fingers, and taking the identity information of the small-area sensor as the knocking position information.

In one possible embodiment, the system further comprises:

the first symbol mapping relation generation module is used for performing symbol mapping according to the finger type and the finger position to generate the symbol mapping relation under the condition that the fingerprint sensor is a small-area sensor which only supports single finger output;

the second symbol mapping relation generation module is used for dividing a touch screen of the fingerprint sensor into a plurality of areas and carrying out symbol mapping by combining a finger type, a finger part and different areas of the touch screen under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers so as to generate the symbol mapping relation;

And the third symbol mapping relation generation module is used for carrying out symbol mapping by combining different combinations of the finger type, the finger part and the small-area sensor under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors only containing a single finger, so as to generate the symbol mapping relation.

In a possible implementation manner, the finger positioning module is further configured to perform feature extraction on the fingerprint image by using a feature extraction algorithm to obtain fingerprint features; the feature extraction algorithm is at least one of a minutiae feature extraction algorithm, a local feature extraction algorithm, a ridge line feature extraction algorithm and a deep learning descriptor extraction algorithm;

the finger positioning module is further configured to match the fingerprint feature with a fingerprint template stored in the fingerprint database by using a matching algorithm, where the matching algorithm is at least one of a sliding window searching method, a correlation matching method, a feature point matching method, and a similarity distance judging method.

In a possible embodiment, the feedback module is further configured to form acoustic feedback based on the symbol and/or form vibration feedback based on the symbol.

In a possible implementation manner, the finger positioning module is further configured to split the fingerprint image into a plurality of independent fingerprint images when the fingerprint image includes a plurality of fingerprints, match each of the independent fingerprint images with a fingerprint template stored in a fingerprint database, and obtain finger information and tapping position information in each of the independent fingerprint images.

In one possible embodiment, the apparatus further comprises:

the knocking area determining module is used for determining a knocking area according to the finger information and the knocking position information after the finger information and the knocking position information are obtained through recognition;

the matching module is used for matching the knocking area with a predefined symbol mapping table to obtain a symbol corresponding to the knocking area;

and the display module is used for outputting the symbol corresponding to the knocking area to display equipment.

The embodiment of the application also provides an electronic device, and referring to fig. 6, fig. 6 is a schematic diagram of the electronic device according to the embodiment of the application. As shown in fig. 6, the electronic device 100 includes: the memory 110 is in communication connection with the processor 120 through a bus, and a computer program is stored in the memory 110 and can run on the processor 120, so that the steps in the symbol input method based on finger fingerprint recognition disclosed in the embodiment of the application are realized.

Embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program/instruction which, when executed by a processor, implements steps in a finger fingerprint recognition based symbol input method as disclosed in embodiments of the present application.

Embodiments of the present application also provide a computer program product which, when run on an electronic device, causes a processor to perform the steps of a finger-fingerprint-identification-based symbol input method as disclosed in embodiments of the present application.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, electronic devices, and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the present application.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.

The above description is made in detail on a symbol input method based on finger fingerprint recognition provided in the present application, and specific examples are applied herein to illustrate the principles and embodiments of the present application, where the above description of the examples is only for helping to understand the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims (10)

1. A symbol input method based on finger fingerprint recognition, characterized in that it is applied to a symbol input system, the symbol input system comprising: the fingerprint image acquisition module, the finger positioning module, the symbol mapping module and the feedback module, wherein the method comprises the following steps:

collecting fingerprint images of the user finger knocked on the touch screen through the fingerprint image collecting module;

comparing the collected fingerprint image with a stored fingerprint template by utilizing the finger positioning module, and identifying to obtain finger information and knocking position information of the fingerprint image;

mapping the finger information and the knocking position information into symbols according to a predefined symbol mapping relation through the symbol mapping module;

and forming visual feedback based on the symbols through the feedback module, and displaying the symbols on a display screen.

2. The symbol input method based on finger fingerprint recognition according to claim 1, wherein the comparing the collected fingerprint image with a stored fingerprint template by using the finger positioning module, and recognizing the finger information of the fingerprint image, comprises:

The fingerprint image and the stored fingerprint templates are matched one by one through the finger positioning module, and the finger type of the user finger in the fingerprint image is determined; the finger type at least comprises: left hand, right hand, index finger, ring finger, little finger, thumb and middle finger;

determining a finger part to which the fingerprint image belongs, wherein the finger part at least comprises: finger tips, finger belly, left finger side, right finger side.

3. The finger-fingerprint-identification-based symbol input method of claim 2, wherein the symbol input system further comprises: a fingerprint registration module; the method further comprises the steps of:

for a registered user used for the first time, the fingerprint registration module starts a fingerprint sensor to acquire registered fingerprint images of different fingers of the registered user; the enrolled fingerprint image is a full rolling fingerprint image for a single finger and/or a planar fingerprint image for each of the finger parts of a single finger;

extracting fingerprint characteristics of the registered fingerprint image to generate a fingerprint template of each finger of the registered user;

and storing fingerprint templates of all fingers of the registered user in a fingerprint database.

4. A finger-fingerprint-identification-based symbol input method according to claim 3, wherein after acquiring the registered fingerprint image, the method further comprises:

performing fingerprint quality evaluation on the registered fingerprint image, and determining the fingerprint quality of the registered fingerprint image;

and re-acquiring the registered fingerprint image of the finger under the condition that the fingerprint quality of the registered fingerprint image is lower than a preset quality threshold.

5. The symbol input method based on finger print recognition according to claim 1, wherein the knocking position information of the fingerprint image is obtained by:

under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, a touch screen of the fingerprint sensor is divided into a plurality of areas, area information corresponding to the touch screen knocked by the fingers of the user in the fingerprint image is obtained, and the area information is used as the knocking position information;

under the condition that the fingerprint sensor is a combination of a plurality of small-area sensors which only accommodate single fingers, acquiring identity information of the small-area sensors which acquire the fingerprint images, and taking the identity information of the small-area sensors as the knocking position information.

6. The finger-fingerprint-identification-based symbol input method of claim 2, further comprising:

under the condition that the fingerprint sensor is a small-area sensor which only supports single finger output, symbol mapping is carried out according to finger types and finger parts, and the symbol mapping relation is generated;

dividing a touch screen of the fingerprint sensor into a plurality of areas under the condition that the fingerprint sensor is a large-area sensor capable of accommodating a plurality of fingers, and performing symbol mapping by combining the finger type, the finger position and different areas of the touch screen to generate the symbol mapping relation;

in the case that the fingerprint sensor is a combination of a plurality of small-area sensors which only accommodate a single finger, symbol mapping is performed in combination with different combinations of finger type, finger position and the small-area sensors, and the symbol mapping relation is generated.

7. The finger-fingerprint-identification-based symbol input method of claim 1, wherein said matching the fingerprint image with a fingerprint template stored in a fingerprint database comprises:

the finger positioning module performs feature extraction on the fingerprint image by using a feature extraction algorithm to obtain fingerprint features; the feature extraction algorithm is at least one of a minutiae feature extraction algorithm, a local feature extraction algorithm, a ridge line feature extraction algorithm and a deep learning descriptor extraction algorithm;

The finger positioning module utilizes a matching algorithm to match the fingerprint characteristics with fingerprint templates stored in the fingerprint database, wherein the matching algorithm is at least one of a sliding window searching method, a correlation matching method, a characteristic point matching method and a similarity distance judging method.

8. The finger-fingerprint-identification-based symbol input method of claim 1, further comprising:

forming, by the feedback module, acoustic feedback based on the symbols, and/or,

and forming vibration feedback based on the symbol through the feedback module.

9. The finger-fingerprint-identification-based symbol input method of claim 1, further comprising:

under the condition that the fingerprint images comprise a plurality of fingerprints, splitting the fingerprint images into a plurality of independent fingerprint images, and utilizing the finger positioning module to match each independent fingerprint image with a fingerprint template stored in a fingerprint database, so as to obtain finger information and knocking position information in each independent fingerprint image.

10. The finger-fingerprint-identification-based symbol input method according to claim 1, wherein after the finger information and the tap position information are identified, the method further comprises:

Determining a knocking area according to the finger information and the knocking position information;

matching the knocking area with a pre-defined symbol mapping table to obtain a symbol corresponding to the knocking area;

outputting the symbol corresponding to the knocking area to a display device _。