CN113012407A - Eye screen distance prompt myopia prevention system based on machine vision - Google Patents
Eye screen distance prompt myopia prevention system based on machine vision Download PDFInfo
- Publication number
- CN113012407A CN113012407A CN202110187324.0A CN202110187324A CN113012407A CN 113012407 A CN113012407 A CN 113012407A CN 202110187324 A CN202110187324 A CN 202110187324A CN 113012407 A CN113012407 A CN 113012407A
- Authority
- CN
- China
- Prior art keywords
- eye
- standard
- face
- image
- screen distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000004379 myopia Effects 0.000 title claims abstract description 27
- 208000001491 myopia Diseases 0.000 title claims abstract description 27
- 230000002265 prevention Effects 0.000 title claims abstract description 27
- 238000012937 correction Methods 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 17
- 230000009466 transformation Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 3
- 230000004438 eyesight Effects 0.000 description 11
- 230000006378 damage Effects 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 230000036544 posture Effects 0.000 description 4
- 239000000243 solution Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000003889 eye drop Substances 0.000 description 1
- 229940012356 eye drops Drugs 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Geometry (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The invention relates to an eye-screen distance prompt myopia prevention system based on machine vision, which comprises a face recognition module, a user database and a control module, wherein a front camera of a smart phone is adopted to determine a prevention application object, and matched standard eye-screen distance data is determined in the established user database; the system comprises an image acquisition module, a database and a display module, wherein a target user shoots a human face picture at a standard eye screen distance through a front camera of the smart phone and stores the human face picture in the database; the monocular camera ranging module is used for measuring and calculating the pixel area of the face of the target user in the picture shot by the image acquisition module, acquiring a proportionality coefficient, and estimating the corresponding eye-screen distance according to the pixel area when the face deviates to other positions in the front camera; the timing prompting module is used for acquiring the portrait at regular time by the front camera and prompting the portrait which cannot be recognized by the face recognition module and the condition that the eye-screen distance measured by the monocular camera ranging module exceeds the standard eye-screen distance. Compared with the prior art, the invention has the advantages of portability, real-time performance, simple implementation condition and the like.
Description
Technical Field
The invention relates to the technical field of myopia preventers, in particular to an eye screen distance prompt myopia prevention system based on machine vision.
Background
Currently, myopia in China is more and more common and tends to be low-age. The eyesight protection is realized by reducing the time for watching an electronic screen, correcting the writing and reading postures under the supervision and urging of other people, dropping eye drops, eating eyesight protection medicines, doing eye exercises and other measures.
With the networking intellectualization of daily life, the smart phone becomes an indispensable link in daily life such as communication, education, work, leisure and entertainment, and the vision injury caused by the screen of the smart phone is obviously unrealistic by measures such as reducing watching of an electronic screen, reminding of other people, eating of vision protection medicines and the like. Although the depth detection method for measuring the distance by using the camera is proposed to prevent myopia, the method needs to be equipped with higher equipment environment requirements, is not portable for daily application, and is not easy to achieve implementation conditions.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an eye screen distance prompt myopia prevention system based on machine vision.
The purpose of the invention can be realized by the following technical scheme:
an eye screen distance prompt myopia prevention system based on machine vision, the system is realized based on a smart phone, and comprises:
and the user information creating module is used for creating corresponding user information for the user using the smart phone.
And the target user shoots a face picture in real time through a front monocular camera of the smart phone and stores the face picture in a database.
And the face recognition module is used for determining a prevention application object by adopting a front camera of the smart phone, confirming the identity of the object, determining matched standard eye-screen distance data in a created user database, and performing face recognition processing on user images under the standard eye-screen distance data and different eye-screen distances to obtain a face recognition image.
And the image processing module is used for processing the image acquired by the image acquisition module, acquiring real-time eye-screen distance data, comparing the real-time eye-screen distance data with standard eye-screen distance data and judging whether myopia prevention warning is needed or not. The standard eye-screen distance data corresponds to a standard proportionality coefficient, and the coefficient is the ratio of the area of the target user face pixel to the area of the full pixel of the shot picture.
And the timing prompt module is used for controlling the front camera to acquire the portrait at regular time and prompting the portrait which cannot be identified by the face identification module and the condition that the eye-screen distance measured by the monocular camera ranging module exceeds the standard eye-screen distance.
Specifically, the image acquisition module specifically performs the following operations:
after a user creates information, a front monocular camera of the smart phone is called first, and a standard focal length f is determined according to a contrast method under a standard eye-screen distanceStandard of meritThen, collecting a user image under the standard distance of the face, and sending the image to a face recognition module; when the face of a user moves to any position in the front monocular camera, the image acquisition module acquires user images at different eye screen distances after determining a real-time focal distance fi by using a contrast method, and sends the images to the face recognition module.
Further, the image processing module includes:
the image perspective correction unit is used for carrying out perspective transformation correction on the face picture acquired by the front camera of the smart phone and mapping all coordinate points of the corrected image to a new image;
and the monocular camera ranging unit is used for measuring and calculating the pixel area of the face of the target user in the picture shot by the image acquisition module, acquiring an implementation proportion coefficient, comparing the implementation proportion coefficient with a standard proportion coefficient and judging whether myopia prevention warning needs to be carried out or not. Specifically, the monocular camera ranging unit calculates a standard proportionality coefficient value according to standard eye-screen distance data and stores the standard proportionality coefficient value into a database; and for the received user images at different eye screen distances, calculating a real-time ratio coefficient value according to the face recognition images under different conditions, storing the data into a database, and comparing the real-time ratio coefficient value with a standard ratio coefficient value. If the real-time proportionality coefficient value is larger than the standard proportionality coefficient value, the face is judged to be too far away from the smart phone, and if the real-time proportionality coefficient value is smaller than the standard proportionality coefficient value, the face is judged to be too close to the smart phone, and the timing prompt module is triggered.
Further, the image perspective correction unit transforms the user imaging projection rule by using a perspective transformation principle, and repairs and corrects the distorted image. The specific contents of the perspective transformation correction performed by the image perspective correction unit are as follows:
calculating the corresponding relation between the coordinates of four corner points in a face picture acquired by a front camera of the smart phone and the coordinates of four corner points of a standard image by perspective correction, and mapping all coordinate points of the corrected image to a new image by matrix transformation.
Further, the face recognition module detects key parts of the face of the user images under standard eye-screen distance data and different eye-screen distances by using the DCNN, performs face recognition processing, and acquires face recognition images.
The invention relates to an eye screen distance prompt myopia prevention system based on machine vision, which specifically comprises the following steps of:
s1: acquiring a standard eye-screen portrait photo of a user under prompting through a front-facing camera of the smart phone, establishing a user personalized information database, measuring and calculating the pixel area of the face of a target user in the photo, and acquiring a proportionality coefficient K;
s2: when a target user allows to acquire a face image of the target user through a front-facing camera, firstly, face recognition is carried out, and standard eye-screen distance data which are correspondingly matched in a created user database are determined;
s3: performing perspective transformation correction on the face picture acquired in real time by the front camera, calculating the corresponding relation between the coordinates of the four corner points of the face picture and the coordinates of the four corner points of the standard image by utilizing the perspective correction, and mapping all coordinate points of the deformed image into a new image by utilizing matrix transformation;
s4: and comparing the area ratio of the human pixel obtained at the later period in a timing manner with the area ratio of the human pixel corresponding to the standard eye screen distance, and if the area ratios are not consistent, controlling the smart phone to prompt the situation that the eye screen distance is too close.
Compared with the prior art, the invention fully applies the monocular camera ranging function of machine vision, and the front camera of the smart phone is utilized to carry out portable real-time eye screen distance measurement prompt so as to reduce the damage of an electronic screen to the vision as much as possible, has simple realization conditions, can help people to correct the poor posture of holding the mobile phone when the electronic product is inevitably used, and reduces the harm of the electronic product to the vision to a certain extent; compared with other vision correction products applying machine vision, the vision correction system has the advantages of wider applicable environment, no need of additional large-scale equipment for assistance, convenience in operation and wider applicable population.
Drawings
FIG. 1 is a schematic diagram of a myopia prevention system based on machine vision for distance indication on an eye screen according to an embodiment;
fig. 2 is a schematic flow chart of the principle of the eye screen distance prompt myopia prevention system based on machine vision in the embodiment.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
Examples
Machine vision technology is now relatively mature, and the increasing computing power of smart phones and the increasing performance of sensors equipped on the phones enable the development of many applications, which can be turned into a distance measuring tool by installing applications. Based on the thought, the invention relates to an eye screen distance prompt myopia prevention system based on machine vision, which is used for measuring the eye screen distance of a handheld smart phone, correcting improper postures of reading an electronic screen in time and reducing the possibility of damaging eyesight.
As shown in fig. 1, the eye screen distance cue myopia prevention system based on machine vision includes:
1. and the user information creating module is used for creating corresponding user information for the user using the smart phone.
2. A database: the system is used for storing the created user information, establishing a user personalized information database according to the face data processed by the face recognition module, and storing standard eye-screen distance data. The standard eye-screen distance data is stored in a database in advance.
3. An image acquisition module: after a user creates information, the module firstly calls a monocular camera of the smart phone, and determines a focal length f according to a contrast method under a standard eye screen distanceStandard of meritAnd entered into the database. And then, acquiring a user image at a standard face distance, and sending the image to a face recognition module. When the face of a user moves to any position in the front camera, the image acquisition module determines a real-time focal length fi by using a contrast method, and the obtained real-time focal length fiAnd (5) entering a database. And collecting user images at different eye screen distances, and sending the images to a face recognition module.
4. A face recognition module: a front-facing camera of the smart phone is adopted to determine a prevention application object, the identity of the object is confirmed, and a DCNN is utilized to detect key parts of a human face of a user image under a standard human face distance, namely different eye screen distances, so as to obtain a human face recognition image.
5. An image processing module: the module comprises an image perspective correction module and a monocular camera ranging function module, wherein the image perspective correction module converts an object imaging projection rule by utilizing a perspective conversion principle, namely, an object is re-projected to a new imaging plane, and the distorted image is repaired and corrected.
Monocular camera range finding module:
in a created user databaseAnd (4) determining matched standard eye-screen distance data so as to calculate a standard K value (K is the pixel area of the face of the target user/the full pixel area of the photo), and then storing the standard K value into a database. In addition, for the received user images at different eye screen distances, the real-time K is calculated according to the face recognition images under different conditionsiValue, then K in real timeiStoring the value in a database and comparing the value to a real-time KiThe values are compared to standard K values.
When the human face moves to any position in the front camera, the corresponding eye-screen distance can be estimated according to the pixel area. Specifically, the method comprises the following steps: when the face is far away from the monocular camera, the area of the face pixels in the obtained image becomes smaller, and correspondingly, when the face is close to the monocular camera, the area of the face pixels in the obtained image becomes larger. The module obtains the proportionality coefficient K of the latest real-time imageiComparing the value with the standard K value of the standard eye-screen portrait photo stored in the system library, if K is not the samei>K, if the face is too far away from the smart phone, calculating the focal length difference delta f ═ fi-fStandard of meritAnd according to the focal length difference, carrying out inverse solution according to the needle model matrix operation to obtain the eye screen distance. If Ki<And K, if the face is too close to the smart phone, triggering the timing prompt module. By KiAnd obtaining the inverse solution of the focal length relation by correspondingly obtaining the relation between the value and the K value to obtain the eye screen distance. The invention utilizes that a three-dimensional object is changed into two-dimensional imaging through an image, the conversion between the three-dimensional object and the two-dimensional imaging can be obtained by a pinhole model, namely, the pinhole model is obtained by matrix operation based on the linear relation between the physical distance of the image and the pixel distance, and the matrix is related to the built-in parameters set by a camera of the smart phone. If the smart phones are different, the built-in parameters are different, and the corresponding matrixes are also different. The above-mentioned operation method is the prior art and will not be described herein.
The method for judging the eye screen distance by using the proportionality coefficient has the advantage of small error: firstly, the ratio coefficient value calculated by using pixel points is an accurate value; secondly, the gesture of the user using the smart phone is relatively fixed, the standard K value recorded into the database is used as a reference for comparison, larger errors cannot be generated, and the distance measured by the method is more accurate compared with the distance measuring tool carried by the smart phone; in addition, the meaning of the evaluation here indicates that some margin of error may be given.
6. The timing prompt module: the front-facing camera collects the portrait regularly when the user allows, and when the face of the user is too close to the screen of the mobile phone, the mobile phone sends out prompt tone or prompt short message. Or, if the distance of the eye screen is too short through the distance measurement result of the monocular camera, the mobile phone can also send out a prompt tone or a prompt short message. The module is provided with a timing controller, and the timing controller is connected with a loudspeaker of the smart phone.
The actual operation flow of the system of the invention is as follows:
I. creating user information, calling a front monocular camera of the smart phone, and determining a standard focal length f according to a contrast method under a standard eye-screen distanceStandard of meritAnd collecting face images (for example, according to the stipulation of the national health commission, the watching distance of children and teenagers is not less than 4 times of the diagonal distance of a screen, the horizontal watching distance of a computer is not less than 50 cm, the watching distance of a mobile phone is not less than 40 cm, the face images are shot at a standard distance, and then a standard proportionality coefficient K is obtained by calculation according to a calculation formula of a K value); the method for determining the focal length according to the contrast method is a common method for automatically determining the focal length by a software-controlled monocular camera, and has high accuracy.
And II, detecting key parts of the face image in the last step by using DCNN (digital-to-noise neural network), thereby measuring and calculating the pixel area of the face of the target user in the picture and obtaining a standard coefficient K. Data (f)Standard of meritStandard coefficient K) and the face image detected in this case to build a user personalized information database.
And III, when the face moves to any position in the front camera, determining a real-time focal distance fi by using a contrast method, acquiring face images at different eye screen distances according to different focal distances, detecting key positions of the face by using DCNN, calculating a real-time Ki value, and storing data (the real-time focal distance fi and the real-time Ki value) into a database.
VI, executing the judging step, if Ki>K, calculating the focus difference Δ f ═ fi-fStandard of meritAccording to the focal length difference, according to the inverse solution of the needle model matrix operationAnd if the distance to the eye screen is less than the threshold value, the timing prompt module is triggered.
In the above steps, although the handheld smart phone and the face of the user are almost horizontal and the eye-screen distance is not too far, the angle between the face and the screen of the mobile phone affects the pictures acquired by the camera, thereby affecting the measurement accuracy of the eye-screen distance. Therefore, the perspective transformation correction of the face picture acquired by the front camera is required. And calculating the corresponding relation between the coordinates of the four corner points of the portrait and the coordinates of the four corner points of the standard image by utilizing perspective correction, and mapping all coordinate points of the deformed image into a new image by utilizing matrix transformation. Perspective correction is a common machine vision correction technology, is widely applied to correction of images of smart phones and cameras, and is divided into horizontal correction and vertical correction, through the perspective correction, the distortion of pictures is improved, and the calculated eye screen distance is more reliable.
The invention fully applies the monocular camera ranging function of machine vision, and carries out portable real-time eye screen distance measurement prompt by utilizing the front camera of the smart phone so as to reduce the damage of an electronic screen to the vision as much as possible. Because the smart phone has portability and universality and becomes an indispensable important tool in daily life, and the time for people to read the smart phone is longer and longer, the smart phone can help people to correct poor posture of holding the smart phone when electronic products cannot be used, and the harm of the smart phone to the eyesight is reduced to a certain extent.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and those skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The utility model provides an eye screen distance suggestion prevention myopia system based on machine vision, this system is realized based on the smart mobile phone, a serial communication port, includes:
the user information creating module is used for creating corresponding user information for a user using the smart phone;
the system comprises an image acquisition module, a database and a display module, wherein a target user shoots a face picture in real time through a front monocular camera of a smart phone and stores the face picture in the database;
the face recognition module is used for determining a prevention application object by adopting a front camera of the smart phone, confirming the identity of the object, determining matched standard eye-screen distance data in a created user database, and performing face recognition processing on user images under the standard eye-screen distance data and different eye-screen distances to obtain a face recognition image;
the image processing module is used for processing the image acquired by the image acquisition module, acquiring real-time eye-screen distance data, comparing the real-time eye-screen distance data with standard eye-screen distance data and judging whether myopia prevention warning needs to be carried out or not;
and the timing prompt module is used for controlling the front camera to acquire the portrait at regular time and prompting the portrait which cannot be identified by the face identification module and the condition that the eye-screen distance measured by the monocular camera ranging module exceeds the standard eye-screen distance.
2. The machine-vision-based eye-screen distance cue myopia prevention system of claim 1, wherein the standard eye-screen distance data corresponds to a standard scaling factor that is a ratio of a target user face pixel area to a full pixel area of a captured picture.
3. The machine vision-based eye screen distance cue myopia prevention system of claim 2, wherein the image processing module comprises:
the image perspective correction unit is used for carrying out perspective transformation correction on the face picture acquired by the front camera of the smart phone and mapping all coordinate points of the corrected image to a new image;
and the monocular camera ranging unit is used for measuring and calculating the pixel area of the face of the target user in the picture shot by the image acquisition module, acquiring an implementation proportion coefficient, comparing the implementation proportion coefficient with a standard proportion coefficient and judging whether myopia prevention warning needs to be carried out or not.
4. The machine vision-based eye screen distance cue myopia prevention system of claim 3, wherein the image acquisition module specifically performs the following operations:
after a user creates information, a front monocular camera of the smart phone is called first, and a standard focal length f is determined according to a contrast method under a standard eye-screen distanceStandard of meritThen, collecting a user image under the standard distance of the face, and sending the image to a face recognition module; when the face of a user moves to any position in the front monocular camera, the image acquisition module acquires user images at different eye screen distances after determining a real-time focal distance fi by using a contrast method, and sends the images to the face recognition module.
5. The machine vision-based eye-screen distance cue myopia prevention system of claim 4, wherein the monocular camera ranging unit calculates a standard scale factor value from standard eye-screen distance data and stores it in the database; and for the received user images at different eye screen distances, calculating a real-time ratio coefficient value according to the face recognition images under different conditions, storing the data into a database, and comparing the real-time ratio coefficient value with a standard ratio coefficient value.
6. The machine vision-based eye screen distance cue myopia prevention system of claim 5, wherein if the real-time scale factor value > the standard scale factor value, it is determined that the face is too far from the smartphone, and if the real-time scale factor value < the standard scale factor value, it is determined that the face is too close to the smartphone, triggering the timing cue module.
7. The system of claim 3, wherein the image perspective correction unit transforms the user's imaging projection rules using perspective transformation principles and corrects the distorted image.
8. The system for preventing myopia based on machine vision distance prompt of claim 7, wherein the perspective transformation correction of the image perspective correction unit is specifically as follows:
calculating the corresponding relation between the coordinates of four corner points in a face picture acquired by a front camera of the smart phone and the coordinates of four corner points of a standard image by perspective correction, and mapping all coordinate points of the corrected image to a new image by matrix transformation.
9. The system of claim 1, wherein the face recognition module detects key portions of a face of the user images at standard eye distance data and different eye distances by using a DCNN, performs face recognition processing, and obtains a face recognition image.
10. The machine vision-based eye screen distance cue myopia prevention system of claim 6, wherein the specific steps of the system to perform the eye screen distance cue myopia prevention process include:
1) acquiring a standard eye-screen portrait photo of a user under prompting through a front-facing camera of the smart phone, establishing a user personalized information database, measuring and calculating the pixel area of the face of a target user in the photo, and acquiring a proportionality coefficient K;
2) when a target user allows to acquire a face image of the target user through a front-facing camera, firstly, face recognition is carried out, and standard eye-screen distance data which are correspondingly matched in a created user database are determined;
3) performing perspective transformation correction on the face picture acquired in real time by the front camera, calculating the corresponding relation between the coordinates of the four corner points of the face picture and the coordinates of the four corner points of the standard image by utilizing the perspective correction, and mapping all coordinate points of the deformed image into a new image by utilizing matrix transformation;
4) and comparing the area ratio of the human pixel obtained at the later period in a timing manner with the area ratio of the human pixel corresponding to the standard eye screen distance, and if the area ratios are not consistent, controlling the smart phone to prompt the situation that the eye screen distance is too close.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110187324.0A CN113012407A (en) | 2021-02-18 | 2021-02-18 | Eye screen distance prompt myopia prevention system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110187324.0A CN113012407A (en) | 2021-02-18 | 2021-02-18 | Eye screen distance prompt myopia prevention system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113012407A true CN113012407A (en) | 2021-06-22 |
Family
ID=76402553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110187324.0A Pending CN113012407A (en) | 2021-02-18 | 2021-02-18 | Eye screen distance prompt myopia prevention system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113012407A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114089655A (en) * | 2021-10-22 | 2022-02-25 | 西京学院 | Sitting posture monitoring and correcting device based on visual image processing |
| CN114530033A (en) * | 2022-02-18 | 2022-05-24 | 平安国际智慧城市科技股份有限公司 | Eye screen distance warning method, device, equipment and storage medium based on face recognition |
| CN114783085A (en) * | 2022-03-21 | 2022-07-22 | 南京信息工程大学 | Novel sharing bicycle based on face recognition |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662334A (en) * | 2012-04-18 | 2012-09-12 | 深圳市兆波电子技术有限公司 | Method for controlling distance between user and electronic equipment screen and electronic equipment |
| CN104809288A (en) * | 2015-04-24 | 2015-07-29 | 青岛尤尼科技有限公司 | Trying method or customizing nail art |
| CN106652253A (en) * | 2016-11-18 | 2017-05-10 | 上海电机学院 | Novel multifunctional ATM protective device |
| WO2017152649A1 (en) * | 2016-03-08 | 2017-09-14 | 珠海全志科技股份有限公司 | Method and system for automatically prompting distance from human eyes to screen |
| CN109508623A (en) * | 2018-08-31 | 2019-03-22 | 杭州千讯智能科技有限公司 | Item identification method and device based on image procossing |
| CN111780715A (en) * | 2020-06-29 | 2020-10-16 | 常州市盈能电气有限公司 | Visual ranging method |
| CN111860527A (en) * | 2019-10-24 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Image correction method, image correction device, computer device, and storage medium |
| CN112070021A (en) * | 2020-09-09 | 2020-12-11 | 深圳数联天下智能科技有限公司 | Distance measurement method, distance measurement system, distance measurement equipment and storage medium based on face detection |
-
2021
- 2021-02-18 CN CN202110187324.0A patent/CN113012407A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662334A (en) * | 2012-04-18 | 2012-09-12 | 深圳市兆波电子技术有限公司 | Method for controlling distance between user and electronic equipment screen and electronic equipment |
| CN104809288A (en) * | 2015-04-24 | 2015-07-29 | 青岛尤尼科技有限公司 | Trying method or customizing nail art |
| WO2017152649A1 (en) * | 2016-03-08 | 2017-09-14 | 珠海全志科技股份有限公司 | Method and system for automatically prompting distance from human eyes to screen |
| CN106652253A (en) * | 2016-11-18 | 2017-05-10 | 上海电机学院 | Novel multifunctional ATM protective device |
| CN109508623A (en) * | 2018-08-31 | 2019-03-22 | 杭州千讯智能科技有限公司 | Item identification method and device based on image procossing |
| CN111860527A (en) * | 2019-10-24 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Image correction method, image correction device, computer device, and storage medium |
| CN111780715A (en) * | 2020-06-29 | 2020-10-16 | 常州市盈能电气有限公司 | Visual ranging method |
| CN112070021A (en) * | 2020-09-09 | 2020-12-11 | 深圳数联天下智能科技有限公司 | Distance measurement method, distance measurement system, distance measurement equipment and storage medium based on face detection |
Non-Patent Citations (1)
| Title |
|---|
| 李贤辉等: "基于瞳孔定位的单目测距***", 《智能计算机与应用》, no. 02, 28 April 2016 (2016-04-28) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114089655A (en) * | 2021-10-22 | 2022-02-25 | 西京学院 | Sitting posture monitoring and correcting device based on visual image processing |
| CN114530033A (en) * | 2022-02-18 | 2022-05-24 | 平安国际智慧城市科技股份有限公司 | Eye screen distance warning method, device, equipment and storage medium based on face recognition |
| CN114783085A (en) * | 2022-03-21 | 2022-07-22 | 南京信息工程大学 | Novel sharing bicycle based on face recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113012407A (en) | Eye screen distance prompt myopia prevention system based on machine vision | |
| EP3447679A1 (en) | Facial in-vivo verification method and device | |
| CN104125327A (en) | Screen rotation control method and system | |
| CN111345029B (en) | Target tracking method and device, movable platform and storage medium | |
| TWI631506B (en) | Method and system for whirling view on screen | |
| CN106377264A (en) | Human body height measuring method, human body height measuring device and intelligent mirror | |
| US9642521B2 (en) | Automatic pupillary distance measurement system and measuring method | |
| WO2022037285A1 (en) | Camera extrinsic calibration method and apparatus | |
| CN105915803B (en) | Photographing method and system based on sensor | |
| US10991124B2 (en) | Determination apparatus and method for gaze angle | |
| CN107958223B (en) | Face recognition method and device, mobile equipment and computer readable storage medium | |
| CN108012026B (en) | Eyesight protection method and mobile terminal | |
| US20170351329A1 (en) | Gaze position detection apparatus and gaze position detection method | |
| CN112541400B (en) | Behavior recognition method and device based on sight estimation, electronic equipment and storage medium | |
| CN111860154B (en) | Forehead detection method and device based on vision and electronic equipment | |
| CN111627073B (en) | Calibration method, calibration device and storage medium based on man-machine interaction | |
| CN111354029B (en) | Gesture depth determination method, device, equipment and storage medium | |
| CN114290338B (en) | Two-dimensional hand-eye calibration method, device, storage medium, and program product | |
| CN115049738A (en) | Method and system for estimating distance between person and camera | |
| CN105824398A (en) | Incoming call processing method and mobile terminal | |
| CN112446251A (en) | Image processing method and related device | |
| CN112200002B (en) | Body temperature measuring method, device, terminal equipment and storage medium | |
| CN106406507B (en) | Image processing method and electronic device | |
| US20200293752A1 (en) | Method for automatically detecting and photographing face image | |
| CN116363174A (en) | Parameter calibration method, storage medium, co-processing chip and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210622 |
|
| RJ01 | Rejection of invention patent application after publication |