1. A handwriting recognition login method is characterized by comprising the following steps:

1) handwriting registration: creating a unique identity identification number, writing for a plurality of times by a user through a handwriting input device and submitting a registered handwriting group, wherein the registered handwriting group is a plurality of registered handwriting sample sets for the user to write a certain standard character for a plurality of times, and the system records handwriting information of each registered handwriting sample through a timer and image recognition to form a user registered handwriting information set; according to the identity identification number, storing a registered handwriting sample set and a registered handwriting information set which are sequentially written and submitted by a user into a database in a one-to-one correspondence manner, and ending the registration process;

2) writing login: after a user inputs an identity identification number, writing for a plurality of times through handwriting input equipment and submitting a login handwriting group, wherein the login handwriting group is a plurality of login handwriting sample sets obtained by writing for a plurality of times for a registration handwriting sample submitted by the user during handwriting registration, the system records the login handwriting information, compares the login handwriting information with the registration handwriting information, and calculates the matching degree of the login handwriting sample and the registration handwriting information in the login handwriting sample set;

3) and (4) successful login: when the matching degree is larger than or equal to the set value, the handwriting login is successful, the user to be logged in is indicated to be the user represented by the user identification number, and the login process is finished;

4) and (3) failure of login: when the matching degree is smaller than the set value, the handwriting login fails, the user to be logged in is indicated to be not the user represented by the user identification number, and the step 2) is repeated;

5) sending early warning information: and (3) when the step 2) is repeated for five times and the matching degree is still smaller than the set value, the system sends early warning information to the user, reminds the user to modify user representation information in time and expand the registered handwriting group, and simultaneously sends auxiliary verification to the user, and the auxiliary verification shows that the user to be logged in is the user represented by the user identification number, the login is successful, and the login process is finished.

2. A method of logging in handwriting recognition according to claim 1, wherein said handwriting information comprises a set of handwriting orders, a set of handwriting coordinates, a set of handwriting speeds, a set of handwriting angles and a set of handwriting outlines for a user writing each registered handwriting sample.

3. The method for logging in handwriting recognition according to claim 2, wherein said set of handwriting orders is a set of stroke order numbers corresponding to stroke order of each stroke of a standard character when a user writes the character; the handwriting track coordinate set is an (x, y, z) set, and represents that each stroke is based on the coordinate set of an x axis and a y axis on an acquired image area when a user writes a certain standard character, and z represents the maximum width pixel value set of the handwriting at the coordinate position; the handwriting speed set is a time set required by a user to write a certain stroke in a certain standard character; the handwriting angle set is an included angle set between a certain stroke in a certain standard character written by a user and an x axis; the handwriting outline set is recorded by image recognition when a user writes a certain standard character.

4. The method for logging in handwriting recognition according to claim 3, characterized in that the handwriting sequence set, the handwriting trajectory coordinate set, the handwriting speed set, the handwriting angle set and the handwriting outline set of each character in the logged handwriting group submitted by the user during logging in are respectively compared with the handwriting sequence set, the handwriting trajectory coordinate set, the handwriting speed set, the handwriting angle set and the handwriting outline set of the corresponding character in the registered handwriting group to obtain a matching rate a of the handwriting sequence set, a matching rate b of the handwriting trajectory coordinate set, a matching rate c of the handwriting speed set, a matching rate d of the handwriting angle set and a matching rate e of the handwriting outline set.

5. A logging method for handwriting recognition according to claim 4, wherein said matching degree is calculated by the following formula:

N=(a×40%)+(b×20%)+(c×10%)+(d×10%)+(e×20%)

wherein N is the matching degree.

6. A logging method for handwriting recognition according to claim 4, wherein said handwriting sequence is numbering the falling sequence of straight-line trajectories which are not bent in user handwriting, and if there is bending, the bending is disassembled into a plurality of straight-line trajectories for numbering; and matching rate a of the handwriting sequence set = number of handwriting in the user login handwriting group, which is the same as the number of handwriting in the registered handwriting group ÷ total number of handwriting numbers in the user registered handwriting group.

7. The method for logging in handwriting recognition according to claim 4, wherein the matching rate b of the handwriting trajectory coordinate set is = number of handwriting trajectories in the user login handwriting set, the coordinates of the handwriting trajectories in the user login handwriting set are the same as the coordinates of the handwriting trajectories in the registered handwriting set ÷ total number of handwriting trajectories in the user registered handwriting set.

8. The method for handwriting recognition according to claim 4, wherein the matching rate c of said set of handwriting velocities is = the number of strokes required by the user in the user's registered handwriting set to write each stroke in the same time as the time required by the user in the registered handwriting set ÷ the total number of strokes in the user's registered handwriting set.

9. The method for logging handwriting recognition according to claim 4, wherein the matching rate d of the handwriting angle set is = the number of strokes, the included angle between each stroke in the user login handwriting set and the x-axis is the same as the included angle between each stroke in the registered handwriting set and the x-axis ÷ the total number of strokes in the user registered handwriting set.

10. The method for logging in handwriting recognition according to claim 4, wherein the matching rate e of the handwriting outline set is = the number of characters in the user login handwriting set which meet the standard of matching with the character handwriting outline in the registered handwriting set ÷ the number of all characters in the user registered handwriting set.

Background

At present, with the rapid development of network information technology, more and more network platforms and APPs are provided for users to provide various services, and for privacy, i.e., security, of a user account, a user is usually required to register the account, and when registering the account, account information such as a login name and a login password is required to be set, and the user logs in a backend server based on the registered account, so that the service provided by the backend server is used.

In actual life, a user login software system mainly depends on a user name and a password, fingerprints and a human face, and can only depend on inputting the user name and the password to log in under the condition that a camera and fingerprint reading equipment are not provided. Characters input by the keyboard are easy to be cracked by peeping or other trace detection technical means, and cannot meet the high safety verification performance under the increasingly updated password cracking means. Passwords, face information and fingerprint biological information are very easily recorded by various implanted viruses, illegal software programs and some software for collecting data without authorization in the current environment.

Disclosure of Invention

In view of the above-mentioned shortcomings in the prior art, an object of the present invention is to provide a handwriting recognition login method, so as to solve the problem of low security through login name and login password in the prior art.

In order to solve the technical problems, the invention adopts the following technical scheme:

a handwriting recognition login method comprises the following steps:

1) handwriting registration: creating a unique identity identification number, writing for a plurality of times by a user through a handwriting input device and submitting a registered handwriting group, wherein the registered handwriting group is a plurality of registered handwriting sample sets for the user to write a certain standard character for a plurality of times, and the system records handwriting information of each registered handwriting sample through a timer and image recognition to form a user registered handwriting information set; according to the identity identification number, storing a registered handwriting sample set and a registered handwriting information set which are sequentially written and submitted by a user into a database in a one-to-one correspondence manner, and ending the registration process;

2) writing login: after a user inputs an identity identification number, writing for a plurality of times through handwriting input equipment and submitting a login handwriting group, wherein the login handwriting group is a plurality of login handwriting sample sets obtained by writing for a plurality of times for a registration handwriting sample submitted by the user during handwriting registration, the system records the login handwriting information, compares the login handwriting information with the registration handwriting information, and calculates the matching degree of the login handwriting sample and the registration handwriting information in the login handwriting sample set;

3) and (4) successful login: when the matching degree is larger than or equal to the set value, the handwriting login is successful, the user to be logged in is indicated to be the user represented by the user identification number, and the login process is finished;

4) and (3) failure of login: when the matching degree is smaller than the set value, the handwriting login fails, the user to be logged in is indicated to be not the user represented by the user identification number, and the step 2) is repeated;

5) sending early warning information: and (3) when the step 2) is repeated for five times and the matching degree is still smaller than the set value, the system sends early warning information to the user, reminds the user to modify user representation information in time and expand the registered handwriting group, and simultaneously sends auxiliary verification to the user, and the auxiliary verification shows that the user to be logged in is the user represented by the user identification number, the login is successful, and the login process is finished.

Preferably, the handwriting information includes a handwriting sequence set, a handwriting trajectory coordinate set, a handwriting speed set, a handwriting angle set and a handwriting outline set when the user writes each registered handwriting sample.

Preferably, the handwriting order set is a stroke order set in which stroke orders of each stroke of a standard character are numbered in a one-to-one correspondence manner when a user writes the character; the handwriting track coordinate set is an (x, y, z) set, and represents that each stroke is based on the coordinate set of an x axis and a y axis on an acquired image area when a user writes a certain standard character, and z represents the maximum width pixel value set of the handwriting at the coordinate position; the handwriting speed set is a time set required by a user to write a certain stroke in a certain standard character; the handwriting angle set is an included angle set between a certain stroke in a certain standard character written by a user and an x axis; the handwriting outline set is recorded by image recognition when a user writes a certain standard character.

Preferably, the handwriting sequence set, the handwriting trajectory coordinate set, the handwriting speed set, the handwriting angle set and the handwriting outline set of each character in the login handwriting group submitted by the user during login are respectively compared with the handwriting sequence set, the handwriting trajectory coordinate set, the handwriting speed set, the handwriting angle set and the handwriting outline set of the corresponding character in the login handwriting group, so as to obtain the matching rate a of the handwriting sequence set, the matching rate b of the handwriting trajectory coordinate set, the matching rate c of the handwriting speed set, the matching rate d of the handwriting angle set and the matching rate e of the handwriting outline set.

Preferably, the matching degree is calculated by the following formula:

N=(a×40%)+(b×20%)+(c×10%)+(d×10%)+(e×20%)

wherein N is the matching degree.

Preferably, the handwriting sequence is a stroke-falling sequence for numbering linear tracks which are not bent in the user handwriting, and if bending exists, the bending is disassembled into a plurality of linear tracks and then numbering is carried out; and matching rate a of the handwriting sequence set = number of handwriting in the user login handwriting group, which is the same as the number of handwriting in the registered handwriting group ÷ total number of handwriting numbers in the user registered handwriting group.

Preferably, the matching rate b of the handwriting trajectory coordinate set = the number of the handwriting trajectories in the user login handwriting group whose coordinates are the same as those in the registered handwriting group ÷ the total number of the handwriting trajectories in the user registered handwriting group.

Preferably, the matching rate c of the handwriting speed set is = the number of strokes required by the user to write each stroke in the user login handwriting group and the same time required by the user to write each stroke in the registered handwriting group ÷ the total number of strokes in the user registered handwriting group.

Preferably, the matching rate d of the handwriting angle set is = the number of strokes, the included angle between each stroke and the x axis in the user login handwriting group is the same as the included angle between each stroke and the x axis in the registered handwriting group ÷ the total number of strokes in the user registered handwriting group.

Preferably, the matching rate e of the handwriting outline set = the number of characters in the user login handwriting group which match with the character handwriting outlines in the registration handwriting group and reach the standard ÷ the number of all characters in the user registration handwriting group.

Compared with the prior art, the invention has the following beneficial effects:

the invention uses the user name and the user handwriting for logging in, the whole logging in process is rapid, the system can match the user only by identifying the handwriting, and the matching of the user name and the password is not needed in the password logging in mode; the applicability is high, and a camera or fingerprint biological identification equipment is not needed; the recognition algorithm is simple, and the handwriting characteristics are easy to master; the system has good reliability and safety, others cannot completely observe the handwriting by using a fade-out mode during handwriting input, and the system can perform secondary verification to improve the safety when logging in abnormal modes such as different places.

Drawings

FIG. 1 is a flow chart of the operation of the present invention.

Detailed Description

The invention will be further explained with reference to the drawings and the embodiments.

A handwriting recognition login method is combined with the accompanying figure 1, and comprises the following steps:

1) handwriting registration: the method comprises the steps that a user creates a unique identity identification number on a system, the user writes for a plurality of times through a handwriting input device and submits a registered handwriting group, the registered handwriting group is a plurality of registered handwriting sample sets obtained by writing a standard character for a plurality of times by the user, handwriting information of each registered handwriting sample is recorded through a timer and image recognition by the system, a user registered handwriting information set is formed, and the user registered handwriting information set can become important comparison information required by a subsequent user during login. And storing the registered handwriting sample set and the registered handwriting information set which are sequentially written and submitted by the user into a handwriting database in a one-to-one correspondence manner according to the identity identification number, and finishing the registration process.

When a user writes in the handwriting input equipment, the handwriting input uses a fade-out mode, and people around the handwriting input equipment are prevented from observing the whole handwriting. The handwriting sample refers to a handwriting written by a user, taking a Chinese character as an example, the handwriting is composed of a group of ordered strokes, and the strokes refer to basic constitutional units of the Chinese character, such as horizontal, vertical, left-falling, right-falling, dot, turning and the like. The standard characters are characters with standard writing styles and expressions which are widely used at present, the widely used characters include but are not limited to Chinese characters, English words and the like, the expressions of Chinese characters include but are not limited to Song script, regular script and the like, and the expressions of English words include but are not limited to Times New Roman, Calibri and the like.

2) Writing login: after the user inputs the identity identification number, writing for a plurality of times through the handwriting input equipment and submitting a login handwriting group, wherein the login handwriting group is a plurality of login handwriting sample sets obtained by writing for a plurality of times for a registration handwriting sample submitted by the user during handwriting registration, the system records the login handwriting information, compares the login handwriting information with the registration handwriting information, and calculates the matching degree of the login handwriting sample and the registration handwriting information in the login handwriting sample set.

3) And (4) successful login: and when the matching degree is greater than or equal to the set value, the handwriting is successfully logged in, the user to be logged in is the user represented by the user identification number, and the logging-in process is finished. And when the login is successful, storing a login handwriting sample set and a login handwriting information set provided by the user for the login, storing the login handwriting sample set and the login handwriting information set into a note database, and integrating the login handwriting sample set into a registered handwriting sample set to provide a comparison handwriting sample for the user for the next login.

4) And (3) failure of login: and when the matching degree is smaller than the set value, the handwriting login fails, the user to be logged in is indicated to be not the user represented by the user identification number, and the step 2) is repeated.

5) Sending early warning information: and (3) when the step 2) is repeated for five times and the matching degree is still smaller than the set value, the system sends early warning information to the user, reminds the user to modify user representation information in time and expand the registered handwriting group, and simultaneously sends auxiliary verification to the user, and the auxiliary verification shows that the user to be logged in is the user represented by the user identification number, the login is successful, and the login process is finished. The auxiliary verification can be that a verification code randomly generated by the system is sent to the user according to a contact way provided by the user, the user to be logged in is proved to be the user represented by the user identification number by inputting the verification code, and the user can input user identity information provided during registration to perform auxiliary verification.

In specific implementation, the handwriting information includes a handwriting sequence set, a handwriting trajectory coordinate set, a handwriting speed set, a handwriting angle set and a handwriting outline set when the user writes each registered handwriting sample. The handwriting sequence set is a stroke-falling sequence set which is used for numbering the stroke-falling sequences of each stroke of a standard character in a one-to-one correspondence manner when a user writes the character. When a user writes a certain standard character, the system records each stroke in the process of writing the character through image recognition, and numbers the stroke falling sequence of each stroke in a one-to-one correspondence manner. The handwriting track coordinate set is an (x, y, z) set, and represents that each stroke is based on the coordinate set of an x axis and a y axis on an acquired image area when a user writes a certain standard character, and z represents the maximum width pixel value set of the handwriting at the coordinate position. The handwriting speed set is a set of time required by a user to write a certain stroke in a certain standard character. The handwriting angle set is an included angle set between a certain stroke in a certain standard character written by a user and an x axis. The handwriting outline set is recorded by image recognition when a user writes a certain standard character.

Comparing the handwriting sequence set, the handwriting track coordinate set, the handwriting speed set, the handwriting angle set and the handwriting outline set of each character in the login handwriting group submitted by the user during login with the handwriting sequence set, the handwriting track coordinate set, the handwriting speed set, the handwriting angle set and the handwriting outline set of the corresponding character in the login handwriting group respectively to obtain the matching rate a of the handwriting sequence set, the matching rate b of the handwriting track coordinate set, the matching rate c of the handwriting speed set, the matching rate d of the handwriting angle set and the matching rate e of the handwriting outline set. If the characters submitted by the user in the login handwriting group are completely different from the characters in the registered handwriting group when the user logs in, the system reminds the user that the characters are different from the registered handwriting and enables the user to input again.

TABLE 1

The table above is the weight ratio of the handwriting sequence, the handwriting track coordinates, the handwriting speed, the handwriting angle and the handwriting outline in the handwriting information. The matching degree is calculated by the following formula:

N=(a×40%)+(b×20%)+(c×10%)+(d×10%)+(e×20%)

and N is the matching degree, and when the matching degree reaches more than 80%, the system determines that the login handwriting is matched with the registration handwriting.

And the handwriting sequence is used for numbering the falling sequence of the straight-line track which is not bent in the user handwriting, and if the straight-line track is bent, the straight-line track is bent and disassembled into a plurality of straight-line tracks and then is numbered. And matching rate a of the handwriting sequence set = number of handwriting in the user login handwriting group, which is the same as the number of handwriting in the registered handwriting group ÷ total number of handwriting numbers in the user registered handwriting group. For example, when registering, the user writes a special character as a registered handwriting, the system records the stroke sequence of the special character as one, five strokes and two strokes when the user writes the special character through image recognition, and numbers the special character, namely one, four strokes and five strokes, wherein the total number of the handwriting numbers is 5, and thus a handwriting number set of the registered handwriting group is formed. The Chinese character is written by a user when the user logs in, the system numbers the Chinese character by adopting the same method, then the system compares the Chinese character with a registered handwriting group handwriting number set to confirm whether the user writes according to the handwriting sequence, if the Chinese character is written according to the sequence, the number of the handwriting with the same number as the handwriting number in the registered handwriting group in the user logging handwriting group is 5, the number of the handwriting with the same number as the handwriting number in the registered handwriting group in the user logging group is the same as the total number of the handwriting numbers in the user registering handwriting group, and at the moment, the matching rate a is 1. If the user does not write according to the above sequence, for example, writes according to the sequence of (i) one, phi ', one', phi ', and (phi', the user logs in the handwriting group with the same number of the handwriting as the registered handwriting group being 3, and the matching rate is 0.6.

And the matching rate b of the handwriting track coordinate set is = the number of the handwriting tracks in the user login handwriting group, which are the same as the handwriting track coordinates in the registered handwriting group, and the total number of the handwriting tracks in the user registered handwriting group. When registering, the user writes a 'special' character as a registered handwriting, coordinates of each stroke on an x-axis and a y-axis on an image area when the user writes the 'special' character are recorded through image recognition, and meanwhile, the maximum width pixel value of each stroke at the position of the corresponding coordinate is recorded to form (x, y, z), and the total number of the character handwriting is 5. The user writes the character when logging in, the system compares (x, y, z) of each stroke written by the user when logging in with (x, y, z) of each stroke when registering, if the same is 1, and if the same number is 4, the matching rate is 0.8.

The matching rate c of the handwriting speed set is = the number of strokes which are required by the user to write each stroke in the user login handwriting group and are the same as the time required by the user to write each stroke in the registered handwriting group ÷ the total number of strokes in the user registered handwriting group. The user writes a 'special' word during registration, the system records the time consumed by the user in writing strokes of 'one', 'I', 'five strokes', 'four strokes' and 'four strokes', corresponding to the strokes, as t1, t2, t3, t4 and t5, the time consumed is accurate to millisecond, and simultaneously records the total number of strokes in the registered handwriting group as 5. When logging in, the user writes a 'special' word again, the system records that the time consumed by the user for writing strokes is t1 ', t 2', t3 ', t 4' and t5 ', compares t 1', t2 ', t 3', t4 ', t 5' with t1, t2, t3, t4 and t5, and the difference between the two is within 1s, so that the time required by the user to write each stroke in the registered handwriting group is considered to be the same as the time required by the user to write each stroke in the registered handwriting group.

And matching rate d of the handwriting angle set is = the number of strokes, the included angle between each stroke and the x axis in the user login handwriting group is the same as the included angle between each stroke and the x axis in the registered handwriting group ÷ the total number of strokes in the user registered handwriting group. When a user writes a 'special' character as a registered handwriting during registration, the system records a deflection angle A between one stroke 'one' on an image area and an x axis through image recognition. The deflection angle between the stroke written by the user in the login process and the x axis is A ', the system compares A with A ', the difference value between A and A ' is within 1-2 degrees, and the included angle between the stroke and the x axis in the user login handwriting group is considered to be the same as the included angle between the stroke and the x axis in the registered handwriting group.

And the matching rate e of the handwriting outline set is = the number of characters in the user login handwriting group which are matched with the character handwriting outlines in the registered handwriting group and reach the standard ÷ the number of all characters in the user registered handwriting group. The user writes a 'special' character as a registered handwriting during registration, the system records the outline of the Chinese character written by the user through image recognition, the system records the outline of the character written by the user again during login, the two are compared, the recognition accuracy reaches more than 80%, and the matching of the outline of the character handwriting in the user login handwriting group and the outline of the character handwriting in the registered handwriting group is considered to reach the standard.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the technical solutions, and those skilled in the art should understand that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all that should be covered by the claims of the present invention.