CN106446859A - Method for automatically identifying black spots and blood streaks in human eyes by using front-facing camera of mobile phone - Google Patents
Method for automatically identifying black spots and blood streaks in human eyes by using front-facing camera of mobile phone Download PDFInfo
- Publication number
- CN106446859A CN106446859A CN201610877173.0A CN201610877173A CN106446859A CN 106446859 A CN106446859 A CN 106446859A CN 201610877173 A CN201610877173 A CN 201610877173A CN 106446859 A CN106446859 A CN 106446859A
- Authority
- CN
- China
- Prior art keywords
- image
- point
- eye
- interpolation
- 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.)
- Granted
Links
- 239000008280 blood Substances 0.000 title claims abstract description 24
- 210000004369 blood Anatomy 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000003708 edge detection Methods 0.000 claims abstract description 5
- 238000010606 normalization Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 210000000162 simple eye Anatomy 0.000 claims description 3
- 210000000746 body region Anatomy 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 210000003128 head Anatomy 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- DWDGSKGGUZPXMQ-UHFFFAOYSA-N OPPO Chemical compound OPPO DWDGSKGGUZPXMQ-UHFFFAOYSA-N 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Medical Informatics (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for automatically identifying black spots and blood streaks in human eyes by using the front-facing camera of a mobile phone. The method includes the following steps that: 1) a distance d between a person image and the camera is identified through a distance sensor on a smart phone; 2) when the distance d is greater than the distance range of a threshold value D, the original resolution of an image obtained by mobile phone is maintained unchanged, when the distance d is smaller than the threshold value D, interpolation is carried out, so that the resolution of the image can be improved, and therefore, the camera can display a human eye image more accurately; 3) image graying, sobel edge detection, image segmentation and image binarization are performed on the interpolated human eye image sequentially; 4) a single-eye image is segmented from the processed human eye image; 5) blood streaks and black spots appearing in the single-eye image are identified; and 6) a user is informed automatically of the blood streaks and black spots. According to the method of the invention, the smart phone and healthy life are combined together, so that the functions of the mobile phone can be increased, and automatic identification and prompting for the tiny blood streaks and black spots appearing in the human eye can be realized.
Description
Technical field
The invention belongs to technical field of image processing, particularly to a kind of improve the become image resolution ratio of front-facing camera and
The method of stain and the trace of blood in automatic identification human eye, can be used for increasing the function of mobile phone.
With scientific and technical progress, have smart mobile phone and have become as universal phenomenon, and people want to healthy living
Seek also more and more higher.People, except carrying out in addition to Base communication with mobile phone, also often use mobile phone front-facing camera to autodyne, but are adjusting
Section focal length expectation obtain more the information of details when, but reduce definition, the image being apparent from can not be obtained.Additionally, people
Also commonly use front-facing camera and serve as mirror, not only wished to the overall situation and seen locally again, and seen local time it is desirable to more clear
Better, therefore adjust camera focal length, but the image equally cannot being apparent from, thus oneself face can not be observed well
Some information of portion's more details.
The height of main flow joins an edition mobile phone currently on the market, and the pixel of its front-facing camera mostly will be than post-positioned pick-up head pixel
Much lower, for example Huawei P9 front-facing camera pixel be 8,000,000 pixels, in emerging ZTE AKON nature's mystery 7 front-facing camera pixel be
8000000 pixels, iphone7 front-facing camera pixel is 7,000,000 pixels, and OPPO R9 front-facing camera pixel is 16,000,000 pixels,
High tennis partner's machine front-facing camera of these main flows all occurs tiny pit, particularly when people utilize hand when closely furthering
When machine front-facing camera shoot function serves as the detailed information that mirror will observe oneself eye, but can not be burnt by adjusting camera
Away from seeing clearly image, and the work(of the trace of blood for eye and these detailed information of stain also automatic identification of neither one
Can, far can not meet people growing to healthy demand.
Content of the invention
Present invention aims to above-mentioned the deficiencies in the prior art, provide a kind of automatic using mobile phone front-facing camera
Identification human eye in stain and the trace of blood method, with meet people growing to healthy demand.
For achieving the above object, technical scheme include as follows:
(1) pass through the range sensor on smart mobile phone and identify portrait and the distance between camera d;
(2) setpoint distance threshold value R=1m, portrait is compared with threshold value R setting with the distance between camera d:
If d>R, then keep the former resolution ratio of the become image of mobile phone constant;If d<R, then execution step (3);
(3) enter row interpolation using bilinear interpolation algorithm image become to front-facing camera, interpolation number N isWhole
Several times, make more accurately show eye image in camera;
(4) gray processing and sobel operator edge detection are carried out to the eye image after interpolation, and according to edge detection results
Find x, the region of y direction human eye, giving up is not the point of human eye area, completes human eye cutting, then to the eye image after cutting
Carry out binary conversion treatment and obtain binary image;
(5) binary image is carried out with horizontal and vertical calculating, scanning is partitioned into single eye images, and will with adjacent interpolation algorithm
Single eye images k is normalized to the single eye images h of 32*16 size;
(6) size is selected to be 32*16 and do not have the simple eye binary image of normal person of the trace of blood and stain, as template image
H, and make the difference acquisition human eye error image h ' with template image H with normalization single eye images h;
(7) peculiar dot image h is obtained to error image h ' cutting ", by adjacent interpolation algorithm by peculiar dot image h " normalizing
Turn to peculiar dot image h of 32*16 size " ';
(8) calculate peculiar dot image h after normalization " ' in white points C, and calculate the letter of white points C and 32*16
Breath compares g;
(9) setting judges stain and threshold value G=0.6835 of trace of blood point, compares the size of g and G, if g=<G, then be judged to
Eyes have stain, if 1>g>G, then being judged to eyes has trace of blood point, if g=1, is judged to eyes normal;
(10) display to the user that result of determination at front-facing camera photograph interface.
The invention has the advantages that:
1. the present invention, on the basis of the camera function of mobile phone front-facing camera, improves first with interpolation technique and takes pictures into
The resolution ratio of image, the trace of blood on the basis of become for mobile phone photograph image resolution ratio is improved, in automatic identification user's eye
And stain, the performance of existing mobile phone front-facing camera can not only be lifted, and more can increase user and take pictures experience, make the life of people
More intelligence of living is convenient;
2. the present invention can according to the distance between portrait and mobile phone, dynamic regulation mobile phone front-facing camera take pictures one-tenth figure
The resolution ratio of picture.Make this distance nearer, the resolution ratio of image is higher, and eye is thin thus can to allow one to apparent seeing
Little feature;
3. the present invention is capable of the small trace of blood and the stain of automatic identification people's eye presence, is that user understands oneself in time
Eye condition provides conveniently.
Brief description
Fig. 1 is the flowchart of the present invention;
Fig. 2 is bilinear interpolation schematic diagram in the present invention;
Fig. 3 is camera resolution and the graph of a relation apart from d in the present invention;
Specific embodiment
Below in conjunction with accompanying drawing, the present invention is elaborated:
With reference to Fig. 1, the present invention to realize step as follows:
Step 1, obtains the distance between portrait and camera, records portrait and takes the photograph by reading mobile phone range sensor
As the distance between head d.
Step 2, according to the resolution ratio judging whether change the become image of front-facing camera apart from d.
(2a) setpoint distance threshold value R=1m, portrait is compared with threshold value R setting with the distance between camera d:
If d>R, then keep become image resolution ratio constant;If d<R, then execution step (2b);
(2b) using bilinear interpolation algorithm, portrait formed by front-facing camera is entered with row interpolation, interpolation number N is
Integral multiple, make more accurately show eye image in camera;
(2c) start from coordinate (0, the 0) point of portrait image, scan all pixels point in this image successively, order scans
Pixel point coordinates be (x, y), then to obtain four scanning element points based on (x, y), respectively A (x, y), B (x+1, y), C
(x, y+1), D (x+1, y+1), make the size of these scanning element points be respectively f (A), f (B), f (C), f (D);
(2d) determine with A (x, y) according to the distance between portrait and camera d, and B (x+1, y), C (x, y+1), D (x+1, y
+ 1) number of the interpolation point in 4 points of square body region being surrounded is:Wherein constant δ=10;
(2e) utilize bilinear interpolation algorithm, determine A (x, y), (x+1, y), C (x, y+1), in 4 points of D (x+1, y+1) for B
The coordinate of interpolation point and the size of interpolation point pixel:
(2e1) set the coordinate of last interpolation point as (x ', y '), as shown in Figure 2.
(2e2) calculate the interpolation point in x-axis direction:
First calculate A (x, y), (x+1, (x ', y), the pixel size of interpolation point P1 is intermediate interpolated point P1 y) B:
F (P1)=(x+1-x ') * f (A)+(x '-x) * f (B);
Calculate C (x, y+1) again, (x ', y), the size of interpolation point pixel is the intermediate interpolated point P2 of D (x+1, y+1):
F (P2)=(x+1-x ') * f (C)+(x '-x) * f (D);
(2e3) use M (x ', y ') represent P1 (x ', y) with P2 (x ', y) between interpolation point, the size of this interpolation point pixel
For:
From above formula, when (x, y) determines, then interpolation point coordinates size x ' be value between (x, x+1), y ' be
Value between (y, y+1);
(2e4) further determine that A (x, y), and B (x+1, y), C (x, y+1), the coordinate of interpolation point in 4 points of D (x+1, y+1)
ForThe size of this interpolation point pixel is:
Wherein n=1,2...N;
(2e5) after completing interpolation, become image resolution ratio is as shown in Figure 3 with the graph of a relation apart from d.
Step 3, pre-processes to eye image after interpolation.
(3a) gray processing eye image, makes coloured image be changed into using the tool function rgb2gray function of image procossing
Gray level image;
(3b) detection image edge
Detection image edge can operator have robert operator, sobel operator, prewitt operator, krisch calculate
Son, laplacian operator, gauss-laplacian operator etc., this step is sobel rim detection.
Step 4, human eye cutting.
(4a) eye image detecting is corroded, removed in human eye with image procossing basic function imerode
Little subject area, remove segmentation distracter;
(4b) x, the region of y direction human eye are scanned for, giving up is not that the point of human eye area completes human eye cutting.
Step 5, the eye image after binaryzation cutting
(5a) obtain binaryzation optimal threshold T:
The algorithm obtaining threshold value has Two-peak method, P parametric method, Otsu method, max-thresholds method, best threshold method etc., this example
Binaryzation optimal threshold T is obtained using best threshold method;
(5b) coordinate (0, the 0) point of the eye image after cutting starts, and scans all pixels point in this image successively,
The pixel point coordinates scanning is made to be (x, y), pixel value size is f (x, y);
(5c) pixel value f (x, y) and threshold value T are compared, if pixel value f (x, y) is less than threshold value T, then f (x, y) is 0,
If pixel value f (x, y) is more than or equal to threshold value T, then f (x, y) is 1.
Step 6, splits single eye images.
After binaryzation, coordinate (0, the 0) point of eye image starts, and scans all pixels in this image successively, gives up respectively
Abandon the point that x direction pixel is summed to 0, and on y direction, pixel is summed to 0 point, be partitioned into two single eye images, i.e. left-eye image
K1 and eye image k2.
Step 7, normalizes left-eye image, left-eye image k1 is normalized to adjacent interpolation algorithm the left eye of 32*16 size
Image h1.
(7a) geometric transformation is done to left-eye image k1, obtain image k ' after the conversion that size is 32*16;
(7b) coordinate (0, the 0) point trying to achieve image k ' after conversion starts, and scans all pixels point in this image successively
(x ', y '), finds the nearest point (x, y) of distance in left-eye image k1 (x ', y '), makes pixel value k ' that (x ', y ') put (x ', y ')
Pixel value k (x, y) put equal to (x, y), the image k ' now obtaining is left-eye image h1;
Process eye image with same method to obtain being normalized to eye image h2 of 32*16 size.
Step 8, acquires human eye error image.
(8a) size is selected to be 32*16 and do not have normal person's left eye binary image of the trace of blood and stain, as left eye mould
Plate image H1, and make the difference acquisition left eye error image h1 ' with left eye template image H1 with normalization left-eye image h1;
(8b) size is selected to be 32*16 and do not have normal person's right eye binary image of the trace of blood and stain, as right eye mould
Plate image H2, and make the difference acquisition right eye error image h2 ' with right eye template image H2 with normalization eye image h2;
Step 9, obtains peculiar dot image.
(9a) left eye error image h1 ' cutting is obtained with left eye difference dot image h1 ", by adjacent interpolation algorithm, left eye is different
Sampling point image h1 " is normalized to left eye difference dot image h1 of 32*16 size " ';
(9a) right eye error image h2 ' cutting is obtained with right eye difference dot image h2 ", by adjacent interpolation algorithm by right difference
Dot image h2 " is normalized to right eye difference dot image h2 of 32*16 size " '.
Step 10, calculates information ratio.
(10a) calculate normalization after left eye difference dot image h1 " ' in white points C1, that is, from left eye difference dot image
Coordinate (0, the 0) point of h1 " ' starts, and scans all pixels point of this image, is 1 point summation to pixel value, obtains white in left eye
Color dot number C1, and the white information counting C1 and 32*16 in left eye that calculates compares g1;
(10b) calculate normalization after right eye difference dot image h2 " ' in white points C2, that is, from right eye difference dot image
Coordinate (0, the 0) point of h2 " ' starts, and scans all pixels point of this image, is 1 point summation to pixel value, obtains white in right eye
Color dot number C2, and the white information counting C2 and 32*16 in right eye that calculates compares g2;
Step 11, determines whether there is the trace of blood and stain.
(11a) setting judges stain and threshold value G=0.6835 of trace of blood point;
(11b) compare the size of g1 and G, if g1=<G, then be judged to there is stain in left eye, if 1>g1>G, then be judged to left eye
In have the trace of blood, if g1=1, be judged to left eye normal;
(11b) compare the size of g2 and G, if g2=<G, then be judged to there is stain in right eye, if 1>g2>G, then be judged to right eye
In have trace of blood point, if g2=1, be judged to right eye normal.
Step 12, prompts the user with result of determination at front-facing camera photograph interface.
User can go hospital admission to treat according to the prompting of mobile phone in time, in order to avoid delaying the state of an illness, protect eyes health.
Above description is only example of the present invention it is clear that for those skilled in the art, is understanding
After present invention and principle, all may carry out in form and details in the case of without departing substantially from the principle of the invention, structure
Various revise and change, but the correction of these basic inventive ideas and change still the present invention claims it
Interior.
Claims (5)
1. in a kind of utilization mobile phone front-facing camera automatic identification human eye stain and the trace of blood method, comprise the steps:
(1) pass through the range sensor on smart mobile phone and identify portrait and the distance between camera d;
(2) setpoint distance threshold value R=1m, portrait is compared with threshold value R setting with the distance between camera d:If d>
R, then keep the former resolution ratio of the become image of mobile phone constant;If d<R, then execution step (3);
(3) enter row interpolation using bilinear interpolation algorithm image become to front-facing camera, interpolation number N isInteger
Times, make more accurately show eye image in camera;
(4) gray processing and sobel operator edge detection are carried out to the eye image after interpolation, and found according to edge detection results
The region of x, y direction human eye, giving up is not the point of human eye area, completes human eye cutting, then the eye image after cutting is carried out
Binary conversion treatment obtains binary image;
(5) binary image is carried out with horizontal and vertical calculating, scanning is partitioned into single eye images, and will be simple eye with adjacent interpolation algorithm
Image k is normalized to the single eye images h of 32*16 size;
(6) size is selected to be 32*16 and do not have the simple eye binary image of normal person of the trace of blood and stain, as template image H, and
Make the difference acquisition human eye error image h ' with template image H with normalization single eye images h;
(7) peculiar dot image h is obtained to error image h ' cutting ", by adjacent interpolation algorithm by peculiar dot image h " be normalized to
Peculiar dot image h of 32*16 size " ';
(8) calculate peculiar dot image h after normalization " ' in white points C, and calculate the information ratio of white points C and 32*16
g;
(9) setting judges stain and threshold value G=0.6835 of trace of blood point, compares the size of g and G, if g=<G, then be judged to eyes
There is stain, if 1>g>G, then being judged to eyes has trace of blood point, if g=1, is judged to eyes normal;
(10) display to the user that result of determination at front-facing camera photograph interface.
2. using bilinear interpolation algorithm, front-facing camera is become in method according to claim 1, wherein step (3)
Image enter row interpolation, carry out as follows:
(3a) start from coordinate (0, the 0) point of portrait image, scan all pixels point in this image successively, make the picture scanning
Vegetarian refreshments coordinate is (x, y), then to obtain four scanning element points based on (x, y), respectively A (x, y), B (x+1, y), C (x, y
+ 1), D (x+1, y+1), makes the size of these scanning element points be respectively f (A), f (B), f (C), f (D);
(3b) determine with A (x, y) according to the distance between portrait and camera d, and B (x+1, y), C (x, y+1), D (x+1, y+1)
The number of the interpolation point in 4 points of square body region being surrounded is:Wherein constant δ=10, distance threshold R=
1m;
(3c) determine A (x, y), and B (x+1, y), C (x, y+1), in 4 points of D (x+1, y+1), the coordinate of interpolation point isCalculate interpolation point pixel size be:
Wherein n=1,2...N.
3. in method according to claim 1, wherein step (4), binary conversion treatment is carried out to the eye image after cutting,
Carry out as follows:
(4a) maximum variance thresholding method is utilized to obtain binaryzation optimal threshold T;
(4b) coordinate (0, the 0) point of the eye image after cutting starts, and scans all pixels point in this image successively, order is swept
The pixel point coordinates retouched is (x, y), and pixel value size is f (x, y);
(4c) pixel value f (x, y) and threshold value T are compared, if pixel value f (x, y) is less than threshold value T, then f (x, y) is 0, if picture
Plain value f (x, y) is more than or equal to threshold value T, then f (x, y) is 1.
4. in method according to claim 1, wherein step (5), with adjacent interpolation algorithm, single eye images are normalized to 32*
The single eye images h of 16 sizes, is carried out as follows:
(5a) single eye images k is done geometric transformation, obtain image k ' after the conversion that size is 32*16;
(5b) after conversion, coordinate (0, the 0) point of image k ' starts, and scans all pixels point in this image (x ', y ') successively,
Find the nearest point (x, y) of distance (x ', y ') in single eye images k, make pixel value k ' that (x ', y ') put (x ', y ') equal to (x, y)
Pixel value k (x, y) of point, the image k ' now obtaining is single eye images h.
5. calculate peculiar dot image h after normalization in method according to claim 1, wherein step (8) " ' in white
Points C, be from peculiar dot image h " ' coordinate (0,0) point start, scan all pixels point of this image, be 1 to pixel value
Point summation, obtains white points C.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610877173.0A CN106446859B (en) | 2016-10-08 | 2016-10-08 | Utilize the method for stain and the trace of blood in mobile phone front camera automatic identification human eye |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610877173.0A CN106446859B (en) | 2016-10-08 | 2016-10-08 | Utilize the method for stain and the trace of blood in mobile phone front camera automatic identification human eye |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106446859A true CN106446859A (en) | 2017-02-22 |
CN106446859B CN106446859B (en) | 2019-11-01 |
Family
ID=58171581
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610877173.0A Active CN106446859B (en) | 2016-10-08 | 2016-10-08 | Utilize the method for stain and the trace of blood in mobile phone front camera automatic identification human eye |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106446859B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109472772B (en) * | 2018-09-29 | 2020-12-01 | 歌尔光学科技有限公司 | Image stain detection method, device and equipment |
CN112022083A (en) * | 2020-07-31 | 2020-12-04 | 上海理工大学 | Fovea centralis positioning method and system based on bidirectional scanning |
CN113040704A (en) * | 2020-11-23 | 2021-06-29 | 泰州国安医疗用品有限公司 | Portable diagnosis platform and method based on blood silk distribution state |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104463102A (en) * | 2014-11-07 | 2015-03-25 | 中国石油大学(华东) | Human eye positioning method based on point-by-point scanning |
-
2016
- 2016-10-08 CN CN201610877173.0A patent/CN106446859B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104463102A (en) * | 2014-11-07 | 2015-03-25 | 中国石油大学(华东) | Human eye positioning method based on point-by-point scanning |
Non-Patent Citations (3)
Title |
---|
LU JING等: "An Improved Bilinear Interpolation Algorithm of Converting Standard-definition Television Images to High-definition Television Images", 《2009 WASE INTERNATIONAL CONFERENCE ON INFORMATION ENGINEERING》 * |
吴聪等: "基于卷积神经网络的眼球血丝诊断", 《软件导刊》 * |
马文刚: "基于计算机视觉的人眼行为识别算法分析", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109472772B (en) * | 2018-09-29 | 2020-12-01 | 歌尔光学科技有限公司 | Image stain detection method, device and equipment |
CN112022083A (en) * | 2020-07-31 | 2020-12-04 | 上海理工大学 | Fovea centralis positioning method and system based on bidirectional scanning |
CN113040704A (en) * | 2020-11-23 | 2021-06-29 | 泰州国安医疗用品有限公司 | Portable diagnosis platform and method based on blood silk distribution state |
Also Published As
Publication number | Publication date |
---|---|
CN106446859B (en) | 2019-11-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101390756B1 (en) | Facial feature detection method and device | |
KR100617390B1 (en) | Face identification apparatus, face identification method, and medium for recording face identification program | |
TWI224287B (en) | Iris extraction method | |
KR100682889B1 (en) | Method and Apparatus for image-based photorealistic 3D face modeling | |
JP4328286B2 (en) | Face area estimation device, face area estimation method, and face area estimation program | |
US8154591B2 (en) | Eyelid opening level determination device and computer readable medium storing computer program thereof | |
Luengo-Oroz et al. | Robust iris segmentation on uncalibrated noisy images using mathematical morphology | |
US20040037460A1 (en) | Method for detecting objects in digital images | |
CN105139404A (en) | Identification camera capable of detecting photographing quality and photographing quality detecting method | |
CN104318603A (en) | Method and system for generating 3D model by calling picture from mobile phone photo album | |
JP2007272435A (en) | Face feature extraction device and face feature extraction method | |
CN101615292A (en) | Human eye accurate positioning method based on half-tone information | |
TW200810518A (en) | System and method for boundary scan of an image | |
CN106446859A (en) | Method for automatically identifying black spots and blood streaks in human eyes by using front-facing camera of mobile phone | |
CN103218615B (en) | Face judgment method | |
CN102860814A (en) | OCT (Optical Coherence Tomography) synthetic fundus image optic disc center positioning method and equipment | |
JP4729188B2 (en) | Gaze detection device | |
GB2598016A (en) | Biometric authentication apparatus and biometric authentication method | |
CN110751690A (en) | Visual positioning method for milling machine tool bit | |
CN114980800A (en) | Dioptric pattern generation method and device and computer-readable storage medium | |
CN111476175A (en) | Adaptive topological graph matching method and system suitable for old people face comparison | |
TW200527319A (en) | Chin detecting method, chin detecting system and chin detecting program for a chin of a human face | |
JP2008084109A (en) | Eye opening/closing determination device and eye opening/closing determination method | |
CN102609698A (en) | Method for evaluating quality of side palm print acquired from living body | |
JP2005209137A (en) | Method and apparatus for object identification, and face direction identification apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
OL01 | Intention to license declared | ||
OL01 | Intention to license declared |