WO2016110061A1

WO2016110061A1 - Terminal unlocking method and device based on eye print recognition

Info

Publication number: WO2016110061A1
Application number: PCT/CN2015/082107
Authority: WO
Inventors: 张本好
Original assignee: 中兴通讯股份有限公司
Priority date: 2015-01-06
Filing date: 2015-06-23
Publication date: 2016-07-14
Also published as: CN105825102A; WO2016110024A1

Abstract

Disclosed is a terminal unlocking method and device based on eye print recognition. The method comprises: collecting eye print information of a user via a terminal sensor; determining whether the collected eye print information matches pre-stored eye print information; if so, instructing a terminal system to conduct an unlocking operation. The present invention pre-stores eye print information of a user; when the user needs to unlock a terminal, collection of the eye print information is triggered; if the collected eye print information matches with pre-stored eye print information, a terminal system conducts an unlocking operation or, if the information does not match, does not conduct the unlocking operation. Since the eye print information is unique, terminal unlocking security is improved.

Description

Terminal unlocking method and device based on eye pattern recognition

Technical field

The present invention relates to the field of communications technologies, and in particular, to a terminal unlocking method and apparatus based on eye pattern recognition.

Background technique

Locking and unlocking is an important application for smart terminals. The locking and unlocking function with strong robustness is of great significance for protecting the privacy of users in intelligent terminals.

At present, there are many ways to unlock smart terminals, including: voiceprint recognition detection, sliding unlocking, and face detection and recognition and unlocking.

In the prior art, there is also an unlocking scheme that uses eyeball information. The solution mainly captures the activity track of the user's eyeball, compares the activity track of the user's eyeball with the pre-stored position information, and if the user's eyeball's activity track coincides with the position information, the unlocking operation is performed.

However, whether it is voiceprint recognition detection, sliding unlocking, face detection and recognition unlocking, or eyeball trajectory unlocking, the information input by the end user for unlocking is not unique, that is, voiceprint, sliding gesture, face They are all available through simulation. Therefore, the existing unlocking method is less secure.

Summary of the invention

The embodiment of the invention provides a terminal unlocking method and device based on eye pattern recognition, so as to at least solve the problem that the unlocking mode in the related art has low security.

Based on the above technical problems, the present invention is solved by the following technical solutions.

An embodiment of the present invention provides a terminal unlocking method based on eye pattern recognition, which includes: collecting eye tracking information of a user through a terminal sensor; wherein the eye pattern information includes: a position of a user's eyeball, a position of an eyelid, and The eye pattern feature determines whether the collected eye pattern information is successfully matched with the pre-stored eye pattern information; if the matching is successful, the terminal system is notified to perform the unlocking operation.

The method further includes: if the matching is successful, correcting the pre-stored eye pattern information according to the eye sensor information collected by the terminal sensor.

The method includes: if the matching is unsuccessful, re-passing the terminal sensor, collecting the eye pattern information of the user, or performing alarm processing according to the preset alarm policy.

Wherein, in the case that the matching is unsuccessful, re-passing the terminal sensor to collect the eyeprint information of the user further includes: accumulating the number of times of collecting the eyeprint information of the user through the terminal sensor; determining whether the accumulated number of times reaches the pre-predetermined The threshold of the number of collections is set; if yes, the alarm processing is performed according to the preset alarm policy; if not, the user's eye pattern information is collected through the terminal sensor.

The collecting, by the terminal sensor, the user's eye pattern information includes: collecting a user's face image through the terminal sensor; determining, in the user's face image, the position of the eye and the position of the eyelid; The position is processed to extract an eyeball region to determine the position of the eyeball; the eyeball image is extracted by processing the eyeball region; and the eyeprint feature is extracted from the eyeprint image based on the Markov model.

The embodiment of the present invention further provides a terminal unlocking device based on eye mark recognition, comprising: an collecting module, configured to collect eyelet information of a user through a terminal sensor; wherein the eyeprint information comprises: a position of a user's eyeball a judging module, configured to determine whether the collected eye pattern information and the pre-stored eye pattern information are successfully matched; and the notification module is configured to be determined when the judging module determines that the matching is successful , notify the terminal system to perform the unlock operation.

The device further includes a correction module, configured to correct the pre-stored eye pattern information according to the eye sensor information collected by the terminal sensor when the determining module determines that the matching is successful.

The device further includes a re-acquisition and alarm module, configured to: when the judging module determines that the matching is successful, invoke the collecting module, and re-use the terminal sensor to collect the user's eye pattern information; or according to the preset alarm policy. , perform alarm processing.

The re-acquisition and alarm module is further configured to: collect the number of times the collection module re-acquires the user's eye-grain information through the terminal sensor; and determine whether the accumulated number of times reaches a preset collection number threshold; if yes, The alarm processing is performed according to the preset alarm policy; if not, the collection module is called, and the user's eye pattern information is collected through the terminal sensor.

The collecting module is configured to: collect a user facial image by using a terminal sensor; determine a position of the eye and a position of the eyelid in the user facial image; and extract the eyeball by processing the position of the eye a region to determine a position of the eyeball; an eyeprint image is extracted by processing the eyeball region; and an eyeprint feature is extracted from the eyeprint image based on a Markov model.

The beneficial effects of the present invention are as follows:

The embodiment of the present invention pre-stores the eye pattern information of the user; when the user needs to unlock the terminal, triggers the collection of the user's eye pattern information; if the collected eye pattern information matches the stored eye pattern information, the terminal system performs an unlocking operation; , the unlock operation is not performed. Because the eye pattern information is unique, the present invention increases the security of terminal unlocking.

DRAWINGS

1 is a flowchart of a method for unlocking a terminal based on eye pattern recognition according to an embodiment of the present invention;

2 is a flow chart showing the steps of storing eyeprint information according to an embodiment of the present invention;

3 is a flow chart showing steps of unlocking a terminal based on eye pattern recognition according to an embodiment of the invention;

4 is a structural diagram of a terminal unlocking device based on eye pattern recognition according to an embodiment of the present invention.

detailed description

The main idea of the present invention is to pre-store the user's eye pattern information; when the user needs to unlock the terminal, trigger the collection of the user's eye pattern information; if the collected eye pattern information matches the stored eye pattern information, the terminal system performs the unlocking. Operation; otherwise, the unlock operation is not performed.

Because the eye pattern information of the person is unique, and the eye pattern recognition is not interfered by environmental factors, the information collection is also very convenient, so the accuracy of the eye pattern recognition is high, and the security of the terminal can be increased.

The invention will be further described in detail below with reference to the drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The invention provides a terminal unlocking method based on eye pattern recognition. As shown in FIG. 1, FIG. 1 is a flowchart of a method for unlocking a terminal based on eye pattern recognition according to an embodiment of the present invention.

Step S110, collecting eyeprint information of the user through the terminal sensor.

The eye pattern information includes: the position of the user's eyeball, the position of the eyelid, and the eye pattern.

The terminal sensor can be a terminal external sensor or a terminal built-in sensor. The built-in sensor is, for example, a terminal camera.

The terminal sensor collects image data of the user's eyes, and based on the image processing technology, obtains the position of the user's eyeball, the position of the eyelid, and the eye pattern.

In step S120, it is determined whether the collected eye pattern information and the pre-stored eye pattern information match successfully. If yes, step S130 is performed; if no, step S140 is performed.

Matching success means that the collected eyeball position is the same as the pre-stored eyeball position, the collected eyelid position is the same as the pre-stored eyelid position, and the acquired eyeprint feature matches the pre-stored eyeprint feature by more than or equal to the preset Match the threshold.

Unsuccessful matching (matching failure) means that the acquired eyeball position is different from the pre-stored eyeball position, the collected eyelid position is different from the pre-stored eyelid position, or the acquired eyeprint feature matches the pre-stored eyeprint feature. Less than the preset matching threshold.

Step S130, notifying the terminal system to perform an unlocking operation.

In step S140, the eye sensor information of the user is collected through the terminal sensor, or the alarm processing is performed according to the preset alarm policy.

The cumulative number of times the user collects the eyeprint information of the user through the terminal sensor; determines whether the accumulated number of times reaches the preset number of collection times; if yes, performs alarm processing according to the preset alarm policy; if not, re-passes the terminal sensor The user's eye pattern information is collected, that is, step S110 is re-executed.

Specifically, when the user's eye pattern information is collected for the first time, the cumulative number of times is 0; when the user's eye pattern information is collected for the second time, the first re-acquisition is started, and the cumulative number of times is 1; the third time collecting the user When the eye pattern information is started, the second re-acquisition is started, and the cumulative number of times is 2.

The alarm processing is performed according to the preset alarm policy, including: pre-configuring an alarm policy including an alarm processing method; and executing the alarm processing method when the accumulated number of times reaches the collection threshold. The alarm processing method includes, but is not limited to, prompting the user to unlock the terminal within a preset time period; automatically sending information to the preset contact that the terminal is illegally unlocked; issuing an alarm prompt tone; and deleting data in the terminal system.

A specific application example of the present invention is given below. In this embodiment, the terminal is an intelligent terminal.

The source of the eyeprint information pre-stored in the terminal will be described first. 2 is a flow chart showing the steps of storing eyeprint information according to an embodiment of the present invention.

In step S210, the user selects registration eye pattern information in the smart terminal.

The number of users who register eyeprint information in the smart terminal may be plural. The number of users allowed to be registered is set by the owner of the smart terminal. These users who register eye tracking information are legitimate users who can unlock the smart terminal.

In step S220, the user's face image is obtained by calling the smart terminal camera.

The smart terminal captures one or more user facial images through the camera; during the shooting process, the camera maintains a certain distance from the user, and the camera uses different exposure brightness to shoot. In this embodiment, preferably, the distance between the camera and the user's face is 20 cm to 50 cm.

Step S230, analyzing the user's eye pattern information based on the user's face image.

By performing image processing on one or more user face images and synthesizing the image processing results, the user's eye pattern information can be obtained.

Perform the following steps for each image:

Step 1. In the user's face image, determine the position of the user's eyes and the position of the user's eyelids. Further, in the face image of the user, the position of the user's eyes and the position of the user's eyelid are determined by the face detection and the human eye detection algorithm. Such as the outline of the eyelids.

In step 2, the position of the eye is processed, and the eyeball area is extracted to determine the position of the eyeball. Further, an image segmentation algorithm may be used to process the position of the user's eyes, extract the user's eyeball region, and determine the position of the user's eyeball; such as the contour of the two eyeballs and the distance between the two eyeballs.

In step 3, the eyeball area is processed to extract an eye pattern image. Further, the user's eyeball region is binarized to extract the user's eyeprint image.

In step 4, based on the Markov model, the eye pattern feature is extracted from the user's eye pattern image.

If the photographed user's face image is a plurality of sheets, the image processing result in accordance with the image selection condition is selected as the eye pattern information. The image selection condition is a criterion for selecting an image to conform to in order to select an appropriate image to obtain eye contour information. Specific image selection conditions can be set as needed. For example, the brightness of the image is in the preset brightness range, so that the image cannot be too dark or too bright.

In step S240, the eye pattern information is stored in a local database of the smart terminal.

When storing eye pattern information, set access rights to the eye pattern information. The purpose of setting access rights is to enable the terminal owner to read and write the eye pattern information, and other users other than the owner cannot read and write the eye pattern information, thereby ensuring that the eye pattern information is not illegally falsified. Increase the security of the terminal.

When the user wants to unlock the terminal, the user's identity is verified by the eyeprint information stored in the terminal. If the verification succeeds, the terminal is unlocked, and if the verification fails, the terminal is not unlocked. FIG. 3 is a flow chart showing the steps of unlocking a terminal based on eye pattern recognition according to an embodiment of the invention.

Step S310, triggering the smart terminal to unlock the task.

The smart terminal unlocking task is started by the user's operation. This operation is, for example, clicking a preset button.

Step S320, obtaining a user face image by calling a camera of the smart terminal.

Step S330, analyzing the user's eye pattern information based on the user's face image.

For specific implementations of steps S320 and S330, steps S220 and S230 may be referred to, respectively.

In step S340, the analyzed eye pattern information is matched in the local database of the smart terminal.

Step S350, determining whether there is eye pattern information matching the analyzed eye pattern information in the local database. If yes, step S360 is performed; if yes, step S370 is performed.

In step S360, the smart terminal system performs an unlocking operation.

In an embodiment, because even if the eye pattern information is successfully matched, the analyzed eye pattern features and the eye pattern features stored in the local database have a problem of matching degree. Therefore, after the smart terminal is unlocked, the unlocking may be performed according to the current unlocking. The eye pattern information corrects the eye pattern in the local database, increases the correctness of the stored eye pattern information, and reduces the failure rate of the user's eye pattern information matching.

In step S370, the smart terminal system does not perform the unlocking operation, and the number of times is accumulated.

In step S380, it is determined whether the current accumulated number of times reaches the collection number threshold. If yes, step S390 is performed. If no, step S320 is performed.

In the process, the user may also be prompted to have an eye pattern information error, please re-collect the eye pattern information.

Step S390, sending alarm information to the preset contact.

The invention also provides a terminal unlocking device based on eye pattern recognition. The device is set up with the terminal. 4 is a structural diagram of a terminal unlocking device based on eye pattern recognition according to an embodiment of the present invention.

The device includes:

The acquisition module 410 is configured to collect the eye pattern information of the user through the terminal sensor. The eye pattern information includes: the position of the user's eyeball, the position of the eyelid, and the eye pattern.

The determining module 420 is configured to determine whether the collected eye pattern information and the pre-stored eye pattern information are successfully matched.

The notification module 430 is configured to notify the terminal system to perform an unlocking operation if the determining module 420 determines that the collected eye pattern information matches the pre-stored eye pattern information.

The retrieving and alarming module 440 is configured to, when the determining module 420 determines that the collected eye pattern information does not match the pre-stored eye pattern information, invoke the collecting module 410 to re-acquire the user's eye pattern information through the terminal sensor; or The alarm processing is performed according to the preset alarm policy.

The re-acquisition and alarm module 440 is further configured to accumulate the number of times the collection module 410 re-acquires the user's eye-grain information through the terminal sensor; whether the accumulated number of times reaches the preset collection number threshold; if yes, according to the preset The alarm policy performs alarm processing; if not, the acquisition module is called again, and the user's eye pattern information is collected again through the terminal sensor.

In one embodiment, the apparatus further includes a correction module (not shown) configured to correct the pre-stored eye pattern information based on the terminal sensor collecting the user's eye pattern information if the matching is successful.

In another embodiment, the apparatus further includes a setting module (not shown) configured to set an access right for the eye pattern information when the eye pattern information is stored in advance.

The functions of the device in this embodiment have been described in the method embodiment shown in FIG. 1-3. Therefore, in the description of the present embodiment, reference may be made to the related description in the foregoing embodiment. Do not repeat them.

While the preferred embodiments of the present invention have been disclosed for purposes of illustration, those skilled in the art will recognize that various modifications, additions and substitutions are possible, and the scope of the invention should not be limited to the embodiments described above.

Industrial applicability

As described above, the method and apparatus for unlocking a terminal based on the eye pattern recognition provided by the embodiment of the present invention have the following beneficial effects: pre-storing the eye pattern information of the user; and triggering the collection of the user's eye pattern information when the user needs to unlock the terminal; Only in the case that the collected eye pattern information matches the stored eye pattern information, the terminal system performs the unlocking operation, thereby increasing the security of the terminal unlocking.

Claims

A terminal unlocking method based on eye pattern recognition, comprising:

Collecting eyeprint information of the user through the terminal sensor; wherein the eyeprint information includes: a position of the eyeball of the user, a position of the eyelid, and an eyeprint feature;

Determining whether the collected eye pattern information and the pre-stored eye pattern information are successfully matched;

In the case where the matching is successful, the terminal system is notified to perform an unlocking operation.
The method of claim 1 wherein the method further comprises:

In the case that the matching is successful, the pre-stored eye pattern information is corrected according to the eye sensor information collected by the terminal sensor.
The method of claim 1 wherein said method comprises:

If the matching is unsuccessful, the terminal sensor is used to collect the eye tracking information of the user, or the alarm processing is performed according to the preset alarm policy.
The method of claim 3, wherein the retrieving the user's eye pattern information through the terminal sensor in the case that the matching is unsuccessful comprises:

Accumulating the number of times the user's eye pattern information is collected through the terminal sensor;

Determining whether the accumulated number of times reaches a preset collection number threshold;

If yes, perform alarm processing according to the preset alarm policy.

If no, the user's eye pattern information is collected again through the terminal sensor.
The method according to any one of claims 1 to 4, wherein the collecting, by the terminal sensor, the eyeprint information of the user comprises:

Collecting a user's face image through a terminal sensor;

Determining the position of the eye and the position of the eyelid in the user's face image;

By processing the position of the eye, extracting an eyeball region to determine the position of the eyeball;

Extracting the eye pattern by processing the eyeball region;

Based on the Markov model, eye pattern features are extracted from the eye pattern image.
A terminal unlocking device based on eye pattern recognition, comprising:

The collection module is configured to collect the eye pattern information of the user through the terminal sensor, where the eye pattern information includes: a position of the eyeball of the user, a position of the eyelid, and an eye pattern;

a determining module, configured to determine whether the collected eye pattern information and the pre-stored eye pattern information are successfully matched;

The notification module is configured to notify the terminal system to perform an unlocking operation if the determining module determines that the matching is successful.
The device according to claim 6, wherein the device further comprises a correction module configured to: when the determining module determines that the matching is successful, collecting the eye pattern information of the user according to the terminal sensor, and the pre-stored eye The grain information is corrected.
The apparatus of claim 6, wherein the apparatus further comprises a re-acquisition and alarm module, configured to call the acquisition module to re-acquire the user's eye through the terminal sensor if the determination module determines that the matching is unsuccessful Pattern information; or perform alarm processing according to a preset alarm policy.
The device of claim 8 wherein

The re-acquisition and alarm module is further configured to: collect the number of times the collection module re-collects the user's eye-grain information through the terminal sensor; determine whether the accumulated number of times reaches a preset collection number threshold; if yes, according to the pre- Set the alarm policy to perform alarm processing; if not, call the acquisition module and re-use the terminal sensor to collect the user's eye pattern information.
The apparatus according to any one of claims 6 to 9, wherein the acquisition module is configured to:

Collecting a user's face image through a terminal sensor;

Determining the position of the eye and the position of the eyelid in the user's face image;

By processing the position of the eye, extracting an eyeball region to determine the position of the eyeball;

Extracting the eye pattern by processing the eyeball region;

Based on the Markov model, eye pattern features are extracted from the eye pattern image.