CN108634925A - A kind of vision testing system based on gesture identification - Google Patents
A kind of vision testing system based on gesture identification Download PDFInfo
- Publication number
- CN108634925A CN108634925A CN201810218289.2A CN201810218289A CN108634925A CN 108634925 A CN108634925 A CN 108634925A CN 201810218289 A CN201810218289 A CN 201810218289A CN 108634925 A CN108634925 A CN 108634925A
- Authority
- CN
- China
- Prior art keywords
- gesture
- test
- value
- image
- unit
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/02—Subjective types, i.e. testing apparatus requiring the active assistance of the patient
- A61B3/028—Subjective types, i.e. testing apparatus requiring the active assistance of the patient for testing visual acuity; for determination of refraction, e.g. phoropters
- A61B3/032—Devices for presenting test symbols or characters, e.g. test chart projectors
-
- 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
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- 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
- G06V40/107—Static hand or arm
- G06V40/117—Biometrics derived from hands
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Ophthalmology & Optometry (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of vision testing systems based on gesture identification, including the processing of test symbol display unit, gesture information collecting unit, gesture and recognition unit and test judging unit；Test symbol display unit, the character " E " at 0.8 eyesight value of random display, provides corresponding text information, according to the different corresponding characters of test random display according to gesture judging result；Gesture processing and recognition unit, including image binaryzation module and gesture recognition module；With test judging unit, judge whether gestures direction and direction " E " on display screen are consistent, shows the printed words of " correct " or " mistake " on the display screen；If to " E " of same size correct judgment twice in succession, then reduce the size of " E "；If misjudgment, then increase its size；It repeats the above steps until getting efficient visual acuity.The present invention has carried out binary conversion treatment to obtained images of gestures, simplifies subsequent identification judgement processing, accelerates speed.
Description
Technical field
The present invention relates to a kind of vision testing systems, and in particular to a kind of vision testing system based on gesture identification belongs to
In human-computer interaction technique field.
Background technology
Currently, the method for China's eyesight detection is varied, it has been summed up：(1) it is regarded with traditional manual method
Power is tested：That is a tester, a doctor, an indicating arm, a visual chart.Tester under the leading of doctor, point out to refer to by resolution
Show the direction of sighting target on the visual chart indicated by bar.But due to the influence of many factors, such as：Inspection condition, mode, speed etc.
Will causing result, there is any discrepancy.(2) by microcomputer whole-process control, one the photoelectric vision of test process independently can be completed
Autonomous detecting system.But the remote controler that this kind of system mostly uses greatly configuration realizes control to vision systems, and remote controler
Design comparison is complicated.
Invention content
In view of the deficienciess of the prior art, it is an object of the present invention to provide a kind of eyesight testing system based on gesture identification
System, through the invention user can carry out man-machine interaction in a manner of most natural by gesture recognition controller.Meanwhile image
Binaryzation is a kind of quantization method of analog picture signal, it is converted to the picture signal that a frame or a line continuous gray scale change
Non- black i.e. white two-value data, binaryzation have the characteristics that data volume is low, are conducive to simplify subsequent processing algorithm and hardware realization
Complexity, and bianry image memory space is small, and processing speed is fast.Therefore, the present invention carries out obtained images of gestures
Binary conversion treatment simplifies subsequent identification judgement processing, accelerates speed.
To achieve the goals above, the present invention is to realize by the following technical solutions：
A kind of vision testing system based on gesture identification of the present invention, including test symbol display unit, gesture information
Collecting unit, gesture processing and recognition unit and test judging unit；
Test symbol display unit, the first character " E " at 0.8 eyesight value of random display, judge gestures direction and character
Whether the direction " E " is consistent；Then corresponding text information is provided according to gesture judging result on a display screen, i.e., " correct " or
" mistake "；Finally according to the character " E " at the different corresponding eyesight values of test result random display；
Gesture information collecting unit, the gesture provided with camera collecting test person；
Gesture processing and recognition unit, including image binaryzation module and gesture recognition module；Described image binaryzation mould
Block finds optimal threshold with maximum variance between clusters, then by image binaryzation, whole image is made to show black and white effect；Institute
State gesture recognition module gesture and background segment come, then calculate every row, each column stain number, and obtain stain most
More row and columns, then centered on the most row and column of stain the gestures direction met is found respectively to upper and lower, lateral probe movement；
With test judging unit, judge whether gestures direction and direction " E " on display screen are consistent, on the display screen
Show the printed words of " correct " or " mistake "；If to " E " of same size correct judgment twice in succession, then reduce the size of " E "；
If misjudgment, then increase its size；Character " E " at 0.8 eyesight value of random display continues test and judges, until obtaining
Get efficient visual acuity.
Above-mentioned different test is to continue test or upgrading test at 0.8 eyesight value or the test that degrades.
By the acquisition, processing, identification of gesture information, judge whether gestures direction and the direction character " E " are consistent.
Above-mentioned black and white effect, that is, background parts are white, and gesture part is black.
Above-mentioned image binaryzation specifically refers to：
1a)：Optimal threshold T is determined with maximum variance between clusters；
2b)：By the gray value t of image pixel compared with threshold value T, every grey scale pixel value t is more than the pixel of threshold value T,
Gray value is set as 255 i.e. white, and every grey scale pixel value t is less than the pixel of threshold value T, and gray value is set as 0 i.e. black.
Step 1a) with maximum variance between clusters determine that optimal threshold T is specifically referred to：
Step1：It is 0~255 that image, which has 256 gray values, value range, gray value t is chosen within this range, by image
It is divided into two groups of G1And G2, G1Including grey scale pixel value ranging from 0~t, G2Including grey scale pixel value ranging from t+1~255；
Step2：Total number of image pixels is indicated with N, uses niIt indicates that gray value is the number of pixels of i, uses PiIndicate each ash
The probability that angle value i occurs, uses W1, W2Indicate G1And G2The number of two groups of pixels percentage shared in general image, uses U1, U2
Indicate two groups of average gray value；
Step3：Then Pi=ni/ N,
Step4：The overall average gray value of image is：U=W1*U1+W2*U2
Between class variance be：G (t)=W1(U1-U)2+W2(U2-U)2=W1W2(U1-U2)2
Step5：T values corresponding when as making a class variance g (t) maximum optimal threshold T.
A kind of vision testing system based on gesture identification provided by the invention, mainly uses image binaryzation method, and two
Value has the characteristics that data volume is low, is conducive to simplify subsequent processing algorithm and hard-wired complexity, and bianry image
Memory space is small, and processing speed is fast.Present system, which overcomes traditional artificial test method, will consider inspection condition, mode, speed
The influence of degree and test job person's working condition etc., also without as by microcomputer whole-process control, one independently can be complete
It is complicated at the autonomous detecting system design comparison of the photoelectric vision of test process.The test system based on gesture identification that this system uses
System is allowed to more intelligent, automation.Gesture Recognition user can be by gesture recognition controller in a manner of most natural
Man-machine interaction is carried out, for example musical composition can be carried out by the hand of user, realizes that finger is played in the air, medical is long-range
The operations such as operation, remote danger do industry, and threedimensional model is built.The present invention is by camera collecting test person in eyesight testing process
In four kinds of upper and lower, left and right gestures direction can preferably identify the gesture of tester by handling and optimizing, measure test
The eyesight of person, while human-computer interaction is enhanced, it can have a good application prospect extensively using field of virtual reality.
Description of the drawings
Fig. 1 is the system block diagram of the present invention；
Fig. 2 is the hardware module figure of the present invention；
Fig. 3 is the image binaryzation flow chart of the present invention；
Fig. 4 is the flow chart of the test judging unit of the present invention.
Specific implementation mode
To make the technical means, the creative features, the aims and the efficiencies achieved by the present invention be easy to understand, with reference to
Specific implementation mode, the present invention is further explained.
As shown in Figure 1, a kind of vision testing system based on gesture identification of the present invention, including test symbol display are single
Four part of member, the processing of gesture information collecting unit, gesture and recognition unit and test judging unit.Test symbol display unit,
Start the character " E " at 0.8 eyesight value of random display, corresponding text information and root are then provided according to gesture judging result
According to the test next to be carried out (continuing test or upgrading test at this eyesight value or the test that degrades) the corresponding word of random display
Symbol；Gesture information collecting unit, the gesture provided with camera collecting test person；Gesture processing and recognition unit include mainly
2 image binaryzation, gesture identification steps；Test judging unit, judge direction " E " on gestures direction and display screen whether one
Show and according to that next how should be tested, the corresponding symbol of random display continues test and judges, finally provides
Test result.
As shown in Fig. 2, the hardware module figure of the present invention, first opening by the switch control test in FPGA controller
Begin.FPGA can send signal after beginning, show " starting to test " printed words on a display screen, then show eyesight value on a display screen
For the random character " E " at 0.8, then camera acquires gesture, obtained image transmitting to FPGA, by image binaryzation
The direction of finger is obtained after processing and gesture identification, and then judges whether gestures direction is consistent with character side, on a display screen
Show the printed words of " correct " or " mistake ".If to " E " of same size correct judgment twice in succession, then reduce the size of " E "；
If misjudgment, then increase its size.Continue test according to above step until getting efficient visual acuity.
As shown in figure 3, image binaryzation flow chart in the gesture processing of the present invention and recognition unit, passes through side between maximum kind
Poor method finds out optimal threshold T, and then by the gray value t of image pixel compared with threshold value T, every grey scale pixel value t is more than threshold
The pixel of value T, gray value are set as 255 (whites), and every grey scale pixel value t is less than the pixel of threshold value T, and gray value is set as 0
(black).
The specific steps step of optimal threshold T determinations refers in the image binaryzation of the present invention：
Step1：It is 0~255 that image, which has 256 gray values, value range, gray value t is chosen within this range, by image
It is divided into two groups of G1And G2, G1Including grey scale pixel value ranging from 0~t, G2Including grey scale pixel value ranging from t+1~255；
Step2：Total number of image pixels is indicated with N, uses niIt indicates that gray value is the number of pixels of i, each is indicated with Pi
The probability that gray value i occurs, uses W1, W2Indicate G1And G2The number of two groups of pixels percentage shared in general image, uses U1,
U2Indicate two groups of average gray value；
Step3：Then Pi=ni/ N,
Step4：The overall average gray value of image is：U=W1*U1+W2*U2
Between class variance be：G (t)=W1(U1-U)2+W2(U2-U)2=W1W2(U1-U2)2
Step5：T values corresponding when as making a class variance g (t) maximum optimal threshold T.
As shown in figure 4, the test judging unit flow chart of the present invention.It is carried out for being tested from 0.8 eyesight value
Explanation.Just start to provide test symbol, then acquire gesture information and handle identification gesture, judges to accord with the test on display screen
Whether number direction " E " is consistent, if testing for the first time consistent, then display screen show " correct " printed words, and simultaneously random display is another later
Test symbol " E " at one 0.8 eyesight value acquires gesture and is judged after handling identification, if second is tested unanimously, then
Eyesight value is raised to 1.0 and continues to test, later at each eyesight value if fruit in succession it is consistent twice if carry out after eyesight value of continuing rising
Test, until mistake occur then shows the value of last eyesight value in display screen；If for the first time test it is inconsistent, then eyesight value drop
Continue to test to 0.5, continues drop eyesight value if malfunctioning if first time at each eyesight value later and tested, until
It ins succession at some eyesight value and unanimously then shows the value of eyesight value at this time on a display screen twice.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (6)
1. a kind of vision testing system based on gesture identification, it is characterised in that：Including test symbol display unit, gesture information
Collecting unit, gesture processing and recognition unit and test judging unit；
Test symbol display unit, the first character " E " at 0.8 eyesight value of random display judge gestures direction and character " E " side
To whether unanimously；Then corresponding text information is provided according to gesture judging result on a display screen, i.e. " correct " or " mistake "；
Finally according to the character " E " at the different corresponding eyesight values of test result random display；
Gesture information collecting unit, the gesture provided with camera collecting test person；
Gesture processing and recognition unit, including image binaryzation module and gesture recognition module；Described image binarization block is transported
Optimal threshold is found with maximum variance between clusters, then by image binaryzation, whole image is made to show black and white effect；The hand
Gesture identification module comes gesture and background segment, then calculate every row, each column stain number, and it is most to obtain stain
Row and column, then centered on the most row and column of stain the gestures direction met is found respectively to upper and lower, lateral probe movement；
With test judging unit, judge whether gestures direction and direction " E " on display screen are consistent, show on the display screen
The printed words of " correct " or " mistake "；If to " E " of same size correct judgment twice in succession, then reduce the size of " E "；If
Misjudgment then increases its size；Character " E " at 0.8 eyesight value of random display continues test and judges, until getting
Efficient visual acuity.
2. the vision testing system according to claim 1 based on gesture identification, it is characterised in that：The different test
That is continue test or upgrading test at 0.8 eyesight value or the test that degrades.
3. the vision testing system according to claim 1 based on gesture identification, it is characterised in that：Pass through gesture information
Acquisition, processing, identification, judge whether gestures direction and the direction character " E " are consistent.
4. the vision testing system according to claim 1 based on gesture identification, it is characterised in that：The black and white effect is
Background parts are white, and gesture part is black.
5. the vision testing system according to claim 1 based on gesture identification, it is characterised in that：Described image binaryzation
It specifically refers to：
1a)：Optimal threshold T is determined with maximum variance between clusters；
2b)：By the gray value t of image pixel compared with threshold value T, every grey scale pixel value t is more than the pixel of threshold value T, gray scale
Value is set as 255 i.e. white, and every grey scale pixel value t is less than the pixel of threshold value T, and gray value is set as 0 i.e. black.
6. the vision testing system according to claim 5 based on gesture identification, it is characterised in that：Step 1a) use maximum
Ostu method determines that optimal threshold T is specifically referred to：
Step1：It is 0~255 that image, which has 256 gray values, value range, chooses gray value t within this range, divides the image into
Two groups of G1And G2, G1Including grey scale pixel value ranging from 0~t, G2Including grey scale pixel value ranging from t+1~255；
Step2：Total number of image pixels is indicated with N, uses niIt indicates that gray value is the number of pixels of i, uses PiIndicate each gray value
The probability that i occurs, uses W1, W2Indicate G1And G2The number of two groups of pixels percentage shared in general image, uses U1, U2It indicates
Two groups of average gray value；
Step3：Then Pi=ni/ N,
Step4：The overall average gray value of image is：U=W1*U1+W2*U2
Between class variance be：G (t)=W1(U1-U)2+W2(U2-U)2=W1W2(U1-U2)2
Step5：T values corresponding when as making a class variance g (t) maximum optimal threshold T.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218289.2A CN108634925A (en) | 2018-03-16 | 2018-03-16 | A kind of vision testing system based on gesture identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810218289.2A CN108634925A (en) | 2018-03-16 | 2018-03-16 | A kind of vision testing system based on gesture identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108634925A true CN108634925A (en) | 2018-10-12 |
Family
ID=63744266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810218289.2A Pending CN108634925A (en) | 2018-03-16 | 2018-03-16 | A kind of vision testing system based on gesture identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108634925A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109431447A (en) * | 2018-12-28 | 2019-03-08 | 重庆远视科技有限公司 | It is a kind of for showing the Vission detector of eyesight detection image |
| CN110353622A (en) * | 2018-10-16 | 2019-10-22 | 武汉交通职业学院 | A kind of vision testing method and eyesight testing apparatus |
| WO2022111663A1 (en) * | 2020-11-30 | 2022-06-02 | 华为技术有限公司 | Visual acuity test method and electronic device |
| CN115251823A (en) * | 2022-06-23 | 2022-11-01 | 广东卫明眼视光研究院 | Intelligent vision detection system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103598870A (en) * | 2013-11-08 | 2014-02-26 | 北京工业大学 | Optometry method based on depth-image gesture recognition |
| CN106778597A (en) * | 2016-12-12 | 2017-05-31 | 朱明� | Intellectual vision measurer based on graphical analysis |
| CN107357421A (en) * | 2017-06-23 | 2017-11-17 | 中国地质大学（武汉） | A kind of PPT control method for playing back and system based on gesture identification |
-
2018
- 2018-03-16 CN CN201810218289.2A patent/CN108634925A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103598870A (en) * | 2013-11-08 | 2014-02-26 | 北京工业大学 | Optometry method based on depth-image gesture recognition |
| CN106778597A (en) * | 2016-12-12 | 2017-05-31 | 朱明� | Intellectual vision measurer based on graphical analysis |
| CN107357421A (en) * | 2017-06-23 | 2017-11-17 | 中国地质大学（武汉） | A kind of PPT control method for playing back and system based on gesture identification |
Non-Patent Citations (1)
| Title |
|---|
| 张国云: "《数字图像处理及工程应用》", 29 February 2016, 西安电子科技大学出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110353622A (en) * | 2018-10-16 | 2019-10-22 | 武汉交通职业学院 | A kind of vision testing method and eyesight testing apparatus |
| CN109431447A (en) * | 2018-12-28 | 2019-03-08 | 重庆远视科技有限公司 | It is a kind of for showing the Vission detector of eyesight detection image |
| WO2022111663A1 (en) * | 2020-11-30 | 2022-06-02 | 华为技术有限公司 | Visual acuity test method and electronic device |
| CN115251823A (en) * | 2022-06-23 | 2022-11-01 | 广东卫明眼视光研究院 | Intelligent vision detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108634925A (en) | A kind of vision testing system based on gesture identification | |
| CN108334814B (en) | Gesture recognition method of AR system | |
| CN110084241B (en) | Automatic ammeter reading method based on image recognition | |
| CN101886942B (en) | Water gauge marking method and water level detection method | |
| KR101298024B1 (en) | Method and interface of recognizing user's dynamic organ gesture, and electric-using apparatus using the interface | |
| CN103598870A (en) | Optometry method based on depth-image gesture recognition | |
| CN110460782A (en) | Information collecting device, method, crusing robot and storage medium | |
| CN207529219U (en) | A kind of camera emulation test system | |
| CN102622108A (en) | Interactive projecting system and implementation method for same | |
| CN110796018B (en) | Hand motion recognition method based on depth image and color image | |
| CN107103309A (en) | A kind of sitting posture of student detection and correcting system based on image recognition | |
| CN101853071A (en) | Gesture identification method and system based on visual sense | |
| US7787668B2 (en) | Method for capturing and mapping fingerprint images and the apparatus for the same | |
| CN106845545B (en) | Image recognition method and device in automatic digital electric meter calibration device | |
| CN111414837A (en) | Gesture recognition method and device, computer equipment and storage medium | |
| CN114299604B (en) | Two-dimensional image-based hand skeleton capturing and gesture distinguishing method | |
| CN103679266B (en) | A kind of automatic light source system of pipe video detection | |
| CN101110102A (en) | Game scene and role control method based on fists of player | |
| CN106778670A (en) | Gesture identifying device and recognition methods | |
| CN102495068A (en) | Method and system for detecting chalky rice on line | |
| CN115424598A (en) | Display screen brightness adjusting method and device and storage medium | |
| CN114627461A (en) | Method and system for high-precision identification of water gauge data based on artificial intelligence | |
| CN108537106A (en) | Fingerprint detection method and circuit thereof | |
| CN202584030U (en) | Interactive projection system and shooting game equipment | |
| CN103514596A (en) | Method and device for processing image |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181012 |