WO2015158087A1

WO2015158087A1 - Method and apparatus for detecting health status of human eyes and mobile terminal

Info

Publication number: WO2015158087A1
Application number: PCT/CN2014/084844
Authority: WO
Inventors: 晏国淇
Original assignee: 中兴通讯股份有限公司
Priority date: 2014-04-18
Filing date: 2014-08-20
Publication date: 2015-10-22
Also published as: CN105022981B; CN105022981A

Abstract

A method and an apparatus for detecting health status of human eyes and a mobile terminal. The method comprises: acquiring a blink rate of eyes in a predetermined time period through a camera (S102); and comparing the blink rate with a preset blink rate threshold, determining the health status of the eyes of a user according to a comparison result, and giving a corresponding tip for using eyes according to the health status (S104). By collecting a blink rate of eyes through a camera and comparing the data with a preset blink rate threshold to determine the health status of the eyes and present different tips for using eyes, the use of eyes of a user can be monitored through a corresponding camera of a terminal when the user uses the terminal. Therefore, the eyesight of the user is protected, and the problem in the prior art that an eye problem is easily caused because the user blinks less when using a terminal, while existing intelligent terminals cannot monitor and urge the user to protect his/her eyesight so that the eyesight fades is solved.

Description

TECHNICAL FIELD The present invention relates to the field of communications, and in particular, to a method, a device, and a mobile terminal for detecting a healthy state of a human eye.

BACKGROUND OF THE INVENTION With the rapid development and popularization of smart phones in recent years, they have been integrated into various aspects of people's daily lives. More and more users like to watch e-fiction, books, news, movies, etc. on their mobile phones. Since the user often enters the mobile scene while playing and reading on the mobile phone, the light itself is not very good, and the radiation and damage of the mobile phone screen to the eyes, so when the user watches the mobile phone screen for a long time, usually With a certain amount of dependence and concentration, the frequency of blinking eyes will drop unconsciously. According to relevant information, the normal blink frequency of humans is blinking every 5 seconds. As an instinctive behavior of human beings, blinking is to increase the moisturization of the eyes and promote the secretion of mucus from the eyes to moisturize the eye mask. When the user concentrates on the screen for a long time, the blink frequency will drop to about 10 seconds or more. If the user maintains such bad habits for a long time, it may cause problems such as decreased vision, dry eyes, and even induce dry eye syndrome, lacrimal gland atrophy and other organic diseases of the eye. In the prior art, when the user uses the terminal, the number of blinks is small, which is likely to cause eye problems. Although the existing terminals are relatively smart, they cannot urge the user to protect the eyesight, resulting in a decrease in the user's vision. SUMMARY OF THE INVENTION The present invention provides a method, a device, and a mobile terminal for detecting a health state of a human eye, which are used to solve the problem in the prior art, when a user uses a terminal, because the number of blinks is small, an eye problem is easily caused. Although the terminals are relatively smart, they cannot urge users to protect their vision, which leads to the problem of decreased eyesight. In order to solve the above technical problem, in one aspect, the present invention provides a method for detecting a health state of a human eye, comprising: acquiring, by a camera, a number of blinks of an eye within a predetermined time period; comparing the number of blinks with a threshold of a preset number of blinks, The health state of the user's eyes is determined according to the comparison result, and a corresponding eye prompt is issued according to the health state. The obtaining the blinking times of the eyes in the predetermined time period by the camera includes: placing the eyes in the blinking state of the user in front of the camera, maintaining the first predetermined length of time, and acquiring the predetermined area in the blinking state by the camera. Gray scale information, wherein the predetermined area is a preset pattern that is taken out from the center of each eye; after the first predetermined time period, the gray in the preset area is collected according to the first preset time interval Degree information, and determining a closed state of the current eye of the user according to the changed value of the collected grayscale information, wherein, when the change value of the grayscale information is within a preset variation range, determining that the eye is in a state The eye state determines that the eye is in the closed eye state when the change value of the gray scale information exceeds the preset change range; and determines the number of blinks according to the closed state of the eye that is counted in the predetermined time period. The obtaining the blinking times of the eyes in the predetermined time period by the camera includes: placing the eyes in the blinking state of the user in front of the camera, maintaining the second predetermined duration, and acquiring the current image to record the grayscale information of the predetermined area in the blinking state. The predetermined area is a preset pattern that is taken out from the center of each of the eyes; after the second predetermined time length, the image corresponding to the preset area is collected according to the second preset time interval, and And averaging the gray level information corresponding to all the collected images, and determining an extreme point of the average value to determine a maximum value of the gray level change rate in the preset range of the extreme point; according to the gray level change The maximum value of the rate determines the closed state of the current eye of the user, wherein the image corresponding to the extreme value of the predetermined multiple of the maximum value of the gray-scale change rate is determined to be a closed-eye state, Determining that the image corresponding to the extreme value of the change range of the gray-scale change rate is equal to or smaller than the maximum value of the maximum value of the gray-scale change rate is a blink state; The closed state of the eye counted during the predetermined time period determines the number of blinks. Comparing the number of blinks with a preset threshold of blinks, and determining, according to the comparison result, a health state of the eye of the user includes: determining, in a case where the number of blinks is greater than or equal to a threshold of the preset number of blinks, The eye is in a healthy state; in a case where the number of blinks is less than the threshold of the preset number of blinks, it is determined that the eye is in a tired state. Wherein, the corresponding eye prompts are issued according to the health status: in the case that the user's eyes are in a tired state, an alarm sound and/or a prompt box is issued to prompt the user that the eyes need rest. Before the capturing the number of blinks of the eye in the predetermined time period by the camera, the method further includes: detecting whether face information appears in the camera; and detecting whether the camera detects the eye information in the case that the face information appears; In the case where the eye information is detected, the number of blinks of the eye within a predetermined period of time is acquired by the camera. In another aspect, the present invention provides an apparatus for detecting a health state of a human eye, comprising: an acquisition module configured to acquire a blink number of an eye within a predetermined time period by a camera; and a determining module configured to set the number of blinks and a preset The blink threshold is compared, and the health state of the user's eyes is determined according to the comparison result, and a corresponding eye prompt is issued according to the health state. The acquiring module includes: a first acquiring unit, configured to: place an eye in a blinking state of the user in front of the camera, maintain the first predetermined duration, and obtain gray information of a predetermined area in a blinking state by using the camera, where The predetermined area is a preset pattern that is taken out from the center of each of the eyes. The first determining unit is configured to collect the preset area according to the first preset time interval after the first predetermined time length. The gray scale information, and determining the closed state of the current eye of the user according to the changed value of the collected gray scale information, wherein when the change value of the gray scale information is within a preset variation range, determining the eye In a blinking state, when the change value of the gray scale information exceeds the preset change range, determining that the eye is in a closed eye state; the first statistical unit is configured to count the eye according to the predetermined time period The closed state determines the number of blinks. The acquiring module includes: a second acquiring unit, configured to place an eye in a blinking state in front of the camera, maintain a second predetermined duration, and acquire a current image to record grayscale information of a predetermined region in a blinking state. The predetermined area is a preset pattern that is taken out from the center of each eye; the second determining unit is configured to collect the preset according to the second preset time interval after the second predetermined time length An image corresponding to the region, and averaging the grayscale information corresponding to all the acquired images, and determining an extreme value of the average value to determine a maximum value of the grayscale change rate in the preset range of the extreme value point Determining, according to the maximum value of the gray-scale change rate, a closed state in which the user's current eye is located, wherein it is determined that the range of change of the gray-scale change rate exceeds an extreme value of a predetermined multiple of the maximum value of the gray-scale change rate The image is in the closed-eye state, and the image corresponding to the extreme value of the predetermined multiple of the maximum value of the gray-scale change rate is determined to be 睁State; a second counting unit arranged to determine a statistical time period according to the predetermined closed state of the wide open eye blinks. The determining module is further configured to issue an alert tone and/or a prompt box to prompt the user to rest when the user's eyes are in a tired state. In still another aspect, the present invention provides a mobile terminal, comprising: the apparatus for detecting a human eye health state according to any one of the preceding claims. The invention collects the number of blinks of the eye through the camera, and compares the data with a preset threshold of the number of blinks to determine the health state of the eye to present different eye tips, so that when the user uses the terminal, The user's eye is monitored by the camera corresponding to the terminal, and the user's eyesight is protected. In the prior art, when the user uses the terminal, the number of blinks is small, which may cause eye problems. Although the existing terminals are relatively smart, However, it is impossible to urge users to protect their vision, which leads to the problem of decreased vision. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a flow chart of a method for detecting a human eye health state according to an embodiment of the present invention; FIG. 2 is a schematic structural view of an apparatus for detecting a human eye health state according to an embodiment of the present invention; 3 is a schematic structural diagram of a device acquisition module for detecting a human eye health state according to an embodiment of the present invention; FIG. 4 is a schematic structural diagram of a device acquisition module for detecting a human eye health state according to an embodiment of the present invention; FIG. 6 is a flow chart of a method for detecting a healthy state of a human eye in a preferred embodiment of the present invention; FIG. 7 is a flowchart of extracting an eye ROI in a preferred embodiment of the present invention; FIG. FIG. 8 is a schematic diagram of human eye ROI cutting during extraction of eye ROI in a preferred embodiment of the present invention; FIG. 9 is a schematic diagram of determining human eye ROI during extraction of eye ROI in a preferred embodiment of the present invention; 10 is a schematic view of the eye in a half-open half-closed state in a preferred embodiment of the present invention; FIG. 11 is a schematic view showing only one eye detected in a closed-eye state in a preferred embodiment of the present invention; FIG. 12 is a closed view in a preferred embodiment of the present invention. A schematic diagram of two eyes detected in an eye state; FIG. 13 is a schematic diagram of simulation of detecting L=12.4 in a human eye ROI state in a preferred embodiment of the present invention; 14 is a simulation diagram for detecting L=2.4 in the ROI state of the human eye in a preferred embodiment of the present invention; and FIG. 15 is a schematic diagram showing the simulation of detecting L=3 in the ROI state of the human eye in a preferred embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In order to solve the problem in the prior art, when a user uses a terminal, since the number of blinks is small, eye problems are easily caused. Although the existing terminals are relatively smart, they cannot urge the user to protect vision, resulting in a decrease in visual acuity of the user. Problem, the present invention provides a method, device and mobile terminal for detecting a healthy state of a human eye, and the present invention will be further described in detail below with reference to the accompanying 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. An embodiment of the present invention provides a method for detecting a healthy state of a human eye. As shown in FIG. 1, the method includes steps S102 to S104:

S102. Obtain a blinking number of eyes in a predetermined time period by using a camera. In the process of implementation, the number of blinks of the eye can also be presented in various forms, for example, the number of times is presented in frequency. S104: Compare the number of blinks with a preset threshold of blinks, determine a health state of the user's eyes according to the comparison result, and issue a corresponding eye prompt according to the health state. In the embodiment of the present invention, the number of blinks of the eye is collected by the camera, and the data is compared with a preset threshold of the number of blinks to determine the health state of the eye to present different eye tips, so that when the user uses the terminal The camera can be supervised by the camera corresponding to the terminal to protect the user's eyesight. In the prior art, when the user uses the terminal, the number of blinks is small, which is easy to cause eye problems, and the existing terminals are relatively smart. However, it is impossible to urge users to protect their vision, which leads to the problem of decreased eyesight. During the implementation process, the number of blinks of the eye in the predetermined time period can be obtained by the camera. For example, the eye in the blinking state can be placed in front of the camera for the first predetermined time (for example, 1 second). Obtaining gray scale information of a predetermined area in a blinking state, wherein the predetermined area is a preset pattern taken out from the center of each eye, and may be a rectangle or a circle, etc.; after the first predetermined time period, according to the first The preset time interval is used to collect the gray scale information in the preset area, and the closed state of the current eye of the user is determined according to the changed value of the collected gray scale information, wherein when the change value of the gray scale information is in the preset variation range In the case of the inside, it is determined that the eye is in a blinking state, and when the change value of the grayscale information exceeds the preset variation range, the eye is determined to be in the closed eye state; and the blinking is determined according to the closed state of the eye counted in the predetermined time period. frequency. The number of blinks of the eye in the predetermined time period obtained by the camera may also be that the eye in the blinking state is placed in front of the camera for a second predetermined duration (the second predetermined duration may be the same as the first predetermined duration), obtaining the current The image is used to record grayscale information of a predetermined area in a blinking state, wherein the predetermined area is a preset pattern that is taken out from the center of each eye; after the second predetermined length of time, the preset is collected according to the second preset time interval. The image corresponding to the region, and averaging the grayscale information corresponding to all the acquired images, and determining the extreme value of the average value to determine the maximum value of the grayscale change rate in the preset range of the extreme value point; The maximum value of the degree of change of the degree of change determines the state of the closed state in which the user's current eye is located, wherein the image corresponding to the extreme value of the predetermined multiple of the maximum value of the gray-scale change rate is determined to be a closed-eye state, Determining that the image corresponding to the extreme value of the gray level change rate is equal to or smaller than the maximum value of the gray level change rate is a blinking state; After the closed state of eyes wide open in accordance with a predetermined time period to determine the statistical number of blinks. The above two implementations can determine the number of blinks, and those skilled in the art can also perform other methods based on the foregoing solution, and no further details are provided herein. When comparing the number of blinks with the threshold of the preset number of blinks, when the number of blinks is greater than or equal to the threshold of the preset number of blinks, it can be determined that the eye is in a healthy state; when the number of blinks is less than the threshold of the preset number of blinks, it can be determined that the eye is in Tired state. According to the needs, the health status of the eyes can be divided into various forms, for example, health status, sub-health status, fatigue status, etc., and different classification levels can be set according to needs and experience. During the implementation process, in order to further enhance the accuracy of the monitoring, it is possible to detect whether or not the face information appears in the camera before the number of blinks of the eye in the predetermined time period is obtained by the camera; in the case where the face information appears, the detection of the camera is detected. To the eye information, if the face information does not appear, the next operation is not performed; in the case where the eye information is detected, the number of blinks of the eye in the predetermined time period is acquired by the camera, and if the eye information is not detected, the next operation is not performed. One-step acquisition operation, at this time, you can remind the user to blink and other operations. When it is detected that the user's eyes are in a state of exhaustion, an alert tone and/or a prompt box may be issued to the user to prompt the user to rest the eye to further protect the eyesight. The embodiment of the present invention further provides a device for detecting a healthy state of a human eye, and the structure thereof is as shown in FIG. 2, including: an obtaining module 10, configured to acquire a blinking number of an eye in a predetermined time period by using a camera; and determining a module 20, The method is coupled to the acquisition module 10, and is configured to compare the number of blinks with a preset threshold of the number of blinks, determine a health state of the user's eyes according to the comparison result, and issue a corresponding eye prompt according to the health state. FIG. 3 shows a first structural diagram of the acquisition module 10, which includes: a first acquisition unit 101, configured to place an eye in a blinking state in front of the camera for a first predetermined duration, and obtain the image through the camera. The grayscale information of the predetermined area in the eye state, wherein the predetermined area is a preset pattern that is taken out from the center of each eye; the first determining unit 102 is coupled to the first acquiring unit 101, and is set to be in the first predetermined time period. After that, the grayscale information in the preset area is collected according to the first preset time interval, and the closed state of the current eye of the user is determined according to the changed value of the collected grayscale information, wherein when the grayscale information changes value In the case of the preset variation range, it is determined that the eye is in the blinking state, and when the change value of the grayscale information exceeds the preset variation range, determining that the eye is in the closed eye state; the first statistical unit 103, and the first determination The unit 102 is coupled to determine the number of blinks based on the closed state of the eye counted during the predetermined time period. FIG. 4 is a schematic structural diagram of the acquisition module 10, which includes: a second acquisition unit 104, configured to place an eye in a blinking state in front of the camera for a second predetermined duration, to obtain a current image. Recording the gradation information of the predetermined area in the blinking state, wherein the predetermined area is a preset pattern taken out from the center of each eye; the second determining unit 105 is coupled to the second obtaining unit 104, and is set to be in the second After the predetermined length of time, the image corresponding to the preset area is collected according to the second preset time interval, and the gray level information corresponding to all the collected images is averaged, and the extreme value is obtained for the average value to determine the extreme value point. The maximum value of the gray level change rate is set; the closed state of the current eye of the user is determined according to the maximum value of the gray rate change rate, wherein the range of the gray level change rate is determined to exceed the maximum value of the gray level change rate by a predetermined multiple The image corresponding to the extreme point is a closed-eye state, and the range of the change of the gray-scale change rate is determined to be equal to or smaller than the maximum value of the predetermined multiple of the maximum value of the gray-scale change rate. Open-eye image corresponding to the state; a second statistic unit 106, coupled to the second determination unit 105, is set to the closed state according to a predetermined time period wide open eye statistics to determine the number of blinks. A person skilled in the art can set the internal structures of the two acquisition modules in FIG. 3 and FIG. 4 in the acquisition module, and in different situations, different ways can be opened to obtain the number of blinks. FIG. 5 is a schematic diagram showing a preferred structure of a device for detecting a state of health of a human eye. On the basis of FIG. 2, the device may further include a detecting module 30 configured to detect whether face information appears in the camera, and a face appears. In the case of information, it is detected whether the camera detects eye information, and in the case where the eye information is detected, the number of blinks of the eye in the predetermined time period is acquired by the camera. In the above device, the acquisition module may be further configured to issue an alarm sound and/or a prompt box to prompt the user that the eye needs rest if the user's eyes are in a tired state. The embodiment of the invention further provides a mobile terminal, which may have a camera itself or may be connected to the camera through an external device. The mobile terminal is provided with the above-mentioned functions that can be implemented by the device for detecting the health state of the human eye, or integrates the device for detecting the health state of the human eye in the mobile phone. Therefore, the mobile terminal includes the respective modules of the device for detecting the health state of the human eye. The person skilled in the art knows how to set according to the content disclosed in the embodiment of the present invention, and details are not described herein. The preferred embodiment camera is one of the most notable modules of today's smartphones, usually with front and rear cameras. Its front camera can also reach 30 frames per second on a typical mobile phone, and get photos of about 1.3 million pixels. This makes it possible to perform face recognition on the image acquired by the front camera, further positioning the eyes, and judging the movement of the eyes. Embodiments of the present invention provide a method for detecting a blinking frequency of an eye by using a front camera to detect a healthy state of a human eye, and a person skilled in the art may apply the method to a terminal only (for example, a mobile phone), or separately Set to become a standalone software application (ie APP). It can be presented as a standalone app or integrated into mobile management software such as "Personal Manager". The user can detect the blink frequency by using the front camera provided by the mobile phone, and make suggestions for the user's eye habit using the mobile phone. When the user wants to detect the blink frequency of the mobile phone, the user can use the APP provided in this embodiment to look at the front camera. For a period of time, the system automatically detects the opening and closing action of the eye in the background, and counts the blink frequency by counting the number of times, which can help protect the eye health of the user. This embodiment can well solve the problem that people use smart phones and their vision is easy to drop. It can promptly feedback to the user, and currently read or use the blinking frequency of the mobile phone to protect the eye health of the user. The specific embodiments of the embodiments of the present invention are described below. In the method for detecting the health state of the human eye provided by the embodiment, the user first needs to turn on the detection mode, for example, open the APP corresponding to the function in the mobile phone, or in the mobile phone integrated with the function, the function in the mobile phone can be turned on. Then the user blinks in front of the front camera for a period of time (about 0.5 seconds bath), then blinks at the normal frequency; the system grabs the image in the background for face, human eye detection, and finally locates the human eye to the human eye Take a rectangle for the center. The opening and closing of the eye is judged by calculating the change in the gray value of the eye rectangle. These calculations are carried out in the background. During this period of time, the user uses the mobile phone according to the usual habits, such as reading e-books, chatting, watching news, shopping, etc., to ensure the authenticity of the system detection; finally, when the detection time reaches a certain time After that, the calculated blink frequency is displayed, and the blink frequency health value is given according to the user's previous blink frequency stored in the system. As shown in FIG. 6, a specific embodiment of the present invention may include steps S601 to S609:

5601, after the detection mode is turned on, the system automatically turns on the front camera, and the camera starts to detect.

5602. Determine whether the face information can be detected. If yes, go to step S603, otherwise go to S608.

5603. If a human face is detected, further human eye detection is performed to determine whether the number of human eyes is less than 1. If yes, go to step S605, otherwise go to step S604. S604, performing ROI longitudinal gray level average detection to determine whether the eye is in a blinking state. If yes, go to step S605, otherwise go to S607.

5605, Increase the number of blinks by one.

5606, determining whether the detection time is up. If yes, step S608 is performed, otherwise, S601 is continued.

5607, ignore this test. S608, if the face is not detected, the test process ends.

S609: Calculate the obtained blink data to determine the health status of the eye. In the above process, the user opens the eyes, and the system inputs the ROI (Region Of Interesting) information of the eyes when the eyes are opened, and then tests according to the normal frequency blink. The system grabs the preview frame every 200 milliseconds, and the entire algorithm takes less than 20 milliseconds. Since a person needs 0.2 seconds to 0.4 seconds in one eye, the system can only capture at most one frame of blinking images in one blinking process. Since the eye is in the closed state, the classifier may not be fully detected (as shown in Figure 3-2;), and in the blink state the system can be nearly 100% detected. Therefore, if it is detected that the number of human eyes is less than or equal to 1, it is determined to be a blinking motion. If two human eyes are detected, the human eye ROI matrix is extracted in accordance with the flow shown in FIGS. 7 to 9. For the two ROI matrices of the human eye, the gray average values of each column are respectively obtained to obtain a vertical gray average matrix M (M is a row vector). Find the extreme point for M, and calculate the maximum value of the gray-scale change rate near the extreme point. Make this indicator L. During the implementation process, the Camera first uses the Adabost+Haar classifier to detect the face after acquiring the preview frame, and extracts the face area if the face is detected. Then, the face area is subjected to preprocessing operations such as graying and brightness normalization, and the human eye detection is performed based on the Adabost+Haar classifier, and if the human eye is detected, the square area where the human eye is located is extracted (shown in FIG. 7). ), scale it to a standard size of 64 X 64. Taking the square center as the coordinate origin, a rectangular ROI region with a width of W=50 and a height of H=10 is cut out (as shown in FIG. 8), and finally a human eye ROI picture is obtained (as shown in FIG. 9). As shown in FIG. 10 and FIG. 12, when the eye is in a half-open half-closed state or a completely closed state, since the white phase of the ROI is greatly reduced compared with the open state, that is, the gray value is excessively gentle, the blinking state is The lower L will be much larger than the L in the half open half closed and closed state. According to this condition, if the L calculated by the ROI is smaller than a certain multiple of L of the blink state recorded by the system, it is considered that the frame picture is in the blink state, and the number of blinks is increased by one. Otherwise, it is considered to be blind. When the detection time reaches a certain time, the system stops working, and the time interval T from the detection of the face to the face of the face to the last time is calculated, and the blink frequency of the user is calculated by counting the number of blinks. According to the user's blink frequency and the normal blink frequency value, the user is given certain suggestions. During the implementation process, as shown in Fig. 3, when the eyes are in the semi-open and semi-closed state (as shown in Fig. 10), the white of the eyes is much less than that in the open state (as shown in Fig. 9). When the eyes are completely processed in the closed state (as shown in FIG. 11 and FIG. 12), the gray value of the extracted human eye ROI picture is close to the skin color, and the ROI of the human eye in the blinking state is greatly different, further demonstrating the present invention. Practicality. As shown in Figs. 13 to 15, the simulation of the vertical gray scale of the human eye ROI is obtained, L = 12.4 in the blinking state, L = 2.4 in the half-bow half-closed state, and L = 3 in the closed-eye state. When the eye is in the blinking state, the index L is much smaller than the L in the blinking state. Generally, the index L in the blinking state is less than 0.5 times the L in the blinking state, indicating the accuracy of the human eye state detection proposed by the present invention. high. 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 above embodiments and preferred embodiments not only solve the problem in the related art that when the user uses the terminal, the number of blinks is small, and the eye problem is easily caused. However, the existing terminals are smart, but the existing terminals are smart. However, it is impossible to urge users to protect their vision, which leads to the problem of decreased vision.

Claims

A claim for a claim, a method for detecting a state of health of a human eye, comprising: obtaining, by a camera, the number of blinks of an eye within a predetermined period of time;

Comparing the number of blinks with a preset threshold of blinks, determining a health state of the user's eyes based on the comparison result, and issuing a corresponding eye prompt according to the health state. The method according to claim 1, wherein the obtaining the number of blinks of the eye in the predetermined period of time by the camera comprises:

The eye in the blinking state is placed in front of the camera for a first predetermined length of time, and the grayscale information of the predetermined area in the blink state is obtained by the camera, wherein the predetermined area is taken out from the center of each eye. Presetting the graphics; after the first predetermined duration, collecting the grayscale information in the preset area according to the first preset time interval, and determining, according to the changed value of the collected grayscale information, the current eye of the user a closed state, wherein, when the change value of the gray scale information is within a preset variation range, determining that the eye is in a blink state, when the change value of the gray scale information exceeds the preset variation range In the case, it is determined that the eye is in a closed eye state; the number of blinks is determined according to the state of the eyelid closed in the predetermined time period. The method according to claim 1, wherein the obtaining the number of blinks of the eye in the predetermined period of time by the camera comprises:

The eye in the blinking state is placed in front of the camera for a second predetermined time period, and the current image is acquired to record the grayscale information of the predetermined region in the blink state, wherein the predetermined region is centered on each eye. The preset image is taken out; after the second predetermined time length, the image corresponding to the preset area is acquired according to the second preset time interval, and the gray level information corresponding to all the collected images is averaged. And determining an extreme point of the average value to determine a maximum value of the gray level change rate in the preset range of the extreme point;

Determining, according to the maximum value of the gray-scale change rate, a closed state in which the current eye of the user is located, wherein determining that the range of change of the gray-scale change rate exceeds an extreme value of a predetermined multiple of the maximum value of the gray-scale change rate The image is in a closed-eye state, and an image corresponding to an extreme value point in which the variation range of the gray-scale change rate is equal to or smaller than a maximum value of the maximum value of the gray-scale change rate is a blink state; The number of blinks is determined according to the closed state of the eye counted in the predetermined period of time. The method according to any one of claims 1 to 3, wherein comparing the number of blinks with a preset threshold of blinks, and determining the health status of the user's eyes according to the comparison result includes:

Determining that the eye is in a healthy state if the number of blinks is greater than or equal to the threshold of the preset number of blinks;

In the case where the blink number is less than the preset blink count threshold, it is determined that the eye is in a tired state. The method according to claim 4, wherein the issuing the corresponding eye prompt according to the health state comprises: in the case that the user's eyes are in a tired state, issuing an alert tone and/or a prompt box to prompt the user that the eye needs rest . The method according to any one of claims 1 to 3, wherein before the obtaining the number of blinks of the eye in the predetermined time period by the camera, the method further comprises: detecting whether face information appears in the camera;

In the case where the face information appears, it is detected whether the camera detects the eye information; in the case where the eye information is detected, the number of blinks of the eye in the predetermined time period is acquired by the camera. And a device for detecting a healthy state of the human eye, comprising: an obtaining module, configured to acquire a blinking number of the eye within a predetermined time period by the camera; and a determining module configured to compare the blinking number with a preset blinking threshold value, according to The comparison results determine the health status of the user's eyes and issue corresponding eye tips based on the health status. The device of claim 7, wherein the obtaining module comprises: a first acquiring unit, configured to place an eye in a blinking state of the user in front of the camera, to maintain a first predetermined duration, and obtain a blink through the camera The grayscale information of the predetermined area in the state, wherein the predetermined area is a preset pattern that is taken out from the center of each eye; the first determining unit is configured to follow the first predetermined time after the first predetermined time length Setting a time interval to collect grayscale information in the preset area, and determining a closed state of the current eye of the user according to the changed value of the collected grayscale information, wherein when the change value of the grayscale information is in advance Set within the range of variation a case where it is determined that the eye is in a blinking state, and when the change value of the grayscale information exceeds the preset variation range, determining that the eye is in a closed eye state; the first statistical unit is set to be according to the predetermined time The closed state of the eye counted in the segment determines the number of blinks. The device of claim 7, wherein the obtaining module comprises: a second acquiring unit, configured to place an eye in a blinking state of the user in front of the camera, maintain a second predetermined duration, and acquire a current image for recording Gray scale information of a predetermined area in a blinking state, wherein the predetermined area is a preset pattern taken outwardly from each eye;

The second determining unit is configured to: after the second predetermined duration, collect the image corresponding to the preset area according to the second preset time interval, and average the gray level information corresponding to all the collected images, And determining an extreme point of the average value to determine a maximum value of the gray level change rate in the preset range of the extreme value point; and determining a closed state of the current eye of the user according to the maximum value of the gray level change rate, Wherein, the image corresponding to the extreme value point whose variation range of the gray-scale change rate exceeds the maximum value of the maximum value of the gray-scale change rate is a closed-eye state, and the variation range of the gray-scale change rate is determined to be equal to or smaller than the grayscale The image corresponding to the extreme value of the predetermined multiple of the change rate is the blink state; the second statistical unit is configured to determine the number of blinks according to the closed state of the eye counted in the predetermined time period. The device according to any one of claims 7 to 9, wherein the determining module is further configured to issue an alert tone and/or a prompt box to prompt the user's eyes if the user's eyes are in a tired state. need to have a rest. A mobile terminal comprising: the device for detecting the health of the human eye according to any one of claims 7 to 10.