CN106446859B - Utilize the method for stain and the trace of blood in mobile phone front camera automatic identification human eye - Google Patents
Utilize the method for stain and the trace of blood in mobile phone front camera automatic identification human eye Download PDFInfo
- Publication number
- CN106446859B CN106446859B CN201610877173.0A CN201610877173A CN106446859B CN 106446859 B CN106446859 B CN 106446859B CN 201610877173 A CN201610877173 A CN 201610877173A CN 106446859 B CN106446859 B CN 106446859B
- Authority
- CN
- China
- Prior art keywords
- image
- point
- eye
- interpolation
- stain
- 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.)
- Active
Links
- 239000008280 blood Substances 0.000 title claims abstract description 23
- 210000004369 blood Anatomy 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000003708 edge detection Methods 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000010606 normalization Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 210000000162 simple eye Anatomy 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 abstract 1
- 230000036541 health Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- DWDGSKGGUZPXMQ-UHFFFAOYSA-N OPPO Chemical compound OPPO DWDGSKGGUZPXMQ-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003128 head Anatomy 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 kind of methods using stain and the trace of blood in mobile phone front camera automatic identification human eye.Its scheme is: 1) identifying the distance between portrait and camera d by the range sensor on smart phone；2) it keeps mobile phone institute constant at image original resolution ratio in distance range of the distance d greater than threshold value D, interpolation is carried out when distance d is less than threshold value D, improving institute makes more accurately show eye image in camera at image resolution ratio；3) image gray processing, sobel edge detection, image segmentation, image binaryzation processing are taken turns doing to eye image after interpolation；4) single eye images are cut into from processed eye image；5) trace of blood and stain occurred in single eye images is identified；6) it and is automatically prompted to user.The present invention combines smart phone with healthy living, can be used for increasing the function of mobile phone, to provide the automatic identification and prompt of the small trace of blood and stain that occur to human body eye.
Description
Technical field
The invention belongs to technical field of image processing, in particular to a kind of raising front camera institute at image resolution ratio 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 the progress of science and technology, possesses smart phone and have become universal phenomenon, and people want healthy living
Ask also higher and higher.People also use mobile phone front camera self-timer other than carrying out Base communication with mobile phone often, but are adjusting
When section focal length it is expected to obtain the more information of details, clarity is but reduced, the image that can not be apparent.In addition, people
Also commonly use front camera and serve as mirror, not only wished to global but also seen part, and seen local time, it is desirable to is more clear
It is better, therefore camera focal length is adjusted, but the image that cannot be equally apparent, thus oneself face cannot be observed well
Some information of portion's more details.
The height of mainstream matches version mobile phone currently on the market, and the pixel of front camera mostly will be than rear camera pixel
It is much lower, for example, Huawei P9 front camera pixel be 8,000,000 pixels, in emerging 7 front camera pixel of ZTE AKON nature's mystery be
8000000 pixels, iphone7 front camera pixel are 7,000,000 pixels, and OPPO R9 front camera pixel is 16,000,000 pixels,
The height of these mainstreams will appear tiny point when closely furthering with mobile phone front camera, especially when people utilize hand
It, but cannot be burnt by adjusting camera when machine front camera shooting function, which serves as mirror, will observe the detailed information of oneself eye
The trace of blood away from seeing clearly image, and for eye and stain these detailed information also none function automatically identified
Can, it is far from satisfying the growing demand to health of people.
Summary of the invention
It is a kind of automatic using mobile phone front camera it is an object of the invention in view of the above shortcomings of the prior art, provide
The method for identifying stain and the trace of blood in human eye, to meet the growing demand to health of people.
To achieve the above object, technical solution of the present invention includes the following:
(1) the distance between portrait and camera d are identified by the range sensor on smart phone；
(2) portrait is compared with the distance between camera d with the threshold value R of setting by set distance threshold value R=1m:
If d > R, keep mobile phone institute constant at image original resolution ratio；If d < R, (3) are thened follow the steps；
(3) interpolation is carried out at image to front camera institute using bilinear interpolation algorithm, interpolation number N isIt is whole
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 the direction y human eye, give up be not human eye area point, complete human eye and cut, then to the eye image after cutting
It carries out binary conversion treatment and obtains binary image；
(5) horizontal and vertical calculating is carried out to binary image, 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) select size for 32*16 and without the simple eye binary image of the normal person of the trace of blood and stain, as template image
H, and made the difference with template image H and normalization single eye images h and obtained human eye error image h '；
(7) abnormal point image h " is obtained to error image h ' cutting, by adjacent interpolation algorithm by abnormal point image h " normalizing
Turn to the abnormal point image h " ' of 32*16 size；
(8) the white points C after normalizing in abnormal point image h " ' is calculated, and calculates the letter of white points C and 32*16
Breath compares g；
(9) setting judges the threshold value G=0.6835 of stain and trace of blood point, compares the size of g and G, if g=< G, is judged to
Eyes have stain, if 1 > g > G, being judged to eyes has trace of blood point, if g=1, it is normal to be judged to eyes；
(10) result is determined in front camera photograph circle's user oriented display.
The present invention has the advantage that
1. the present invention on the basis of camera function of mobile phone front camera, first with interpolation technique raising take pictures institute at
The resolution ratio of image, trace of blood on the basis of improving mobile phone photograph at image resolution ratio, in automatic identification user's eye
And stain, the performance of existing mobile phone front camera can not only be promoted, and more can increase user and take pictures experience, make the life of people
More intelligence living is convenient；
2. the present invention can take pictures according to the distance between portrait and mobile phone, dynamic regulation mobile phone front camera, institute is at figure
The resolution ratio of picture.So that this distance is closer, the resolution ratio of image is higher, can thus allow one to clearer see that eye is thin
Small feature；
3. the trace of blood and stain that the present invention can be small existing for automatic identification human eye portion understand oneself for user in time
Eye condition provides convenience.
Detailed description of the invention
Fig. 1 is implementation flow chart of the invention；
Fig. 2 is bilinear interpolation schematic diagram in the present invention；
Fig. 3 is the relational graph of camera resolution and distance d in the present invention；
Specific embodiment
It elaborates below in conjunction with attached drawing to the present invention:
Referring to Fig.1, steps are as follows for realization of the invention:
Step 1, the distance between portrait and camera are obtained, i.e., measures portrait by reading mobile phone range sensor and takes the photograph
As the distance between head d.
Step 2, according to distance d judge whether change front camera at image resolution ratio.
Portrait is compared with the distance between camera d with the threshold value R of setting by (2a) set distance threshold value R=1m:
If d > R, keep institute constant at image resolution ratio；If d < R, (2b) is thened follow the steps；
(2b) carries out interpolation to portrait formed by front camera using bilinear interpolation algorithm, and interpolation number N is
Integral multiple, make more accurately show eye image in camera；
(2c) starts from coordinate (0, the 0) point of portrait image, successively scans all pixels point in the image, and scanning is enabled to arrive
Pixel coordinate be (x, y), then to obtain four scanning element points, respectively A (x, y), B (x+1, y), C based on (x, y)
(x, y+1), D (x+1, y+1), enabling the size of these scanning element points is respectively f (A), f (B), f (C), f (D)；
(2d) is determined according to the distance between portrait and camera d with A (x, y), B (x+1, y), C (x, y+1), D (x+1, y
+ 1) number of the interpolation point in 4 points of square body regions surrounded are as follows:Wherein constant δ=10；
(2e) utilizes bilinear interpolation algorithm, determines A (x, y), B (x+1, y), C (x, y+1), in 4 points of D (x+1, y+1)
The coordinate of interpolation point and the size of interpolation point pixel:
(2e1) sets the coordinate of last interpolation point as (x ', y '), as shown in Figure 2.
The interpolation point of (2e2) calculating x-axis direction:
It first calculates A (x, y), the intermediate interpolated point P1 (x ', y) of B (x+1, y), the pixel size of interpolation point P1 are as follows:
F (P1)=(x+1-x ') * f (A)+(x '-x) * f (B)；
It calculates again C (x, y+1), the intermediate interpolated point P2 (x ', y) of D (x+1, y+1), the size of interpolation point pixel are as follows:
F (P2)=(x+1-x ') * f (C)+(x '-x) * f (D)；
(2e3) indicates the interpolation point between P1 (x ', y) and P2 (x ', y), the size of the interpolation point pixel with M (x ', y ')
Are as follows:
From the above equation, we can see that then interpolation point coordinate size x ' is the value between (x, x+1) when (x, y) is determined, y ' be
Value between (y, y+1)；
(2e4) is further determined that A (x, y), 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 the interpolation point pixel are as follows:
Wherein n=1,2...N；
(2e5) complete interpolation after it is as shown in Figure 3 at image resolution ratio and the relational graph of distance d.
Step 3, eye image after interpolation is pre-processed.
(3a) gray processing eye image becomes color image 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 edge detection.
Step 4, human eye is cut.
(4a) corrodes the eye image detected, i.e., is removed in human eye with image procossing basic function imerode
Small object region, remove segmentation distracter；
(4b) scans for x, the region of the direction y human eye, and giving up is not that the point of human eye area is completed human eye and cut.
Step 5, the eye image after binaryzation is cut
(5a) obtains binaryzation optimal threshold T:
The algorithm for 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) starts from coordinate (0, the 0) point of the eye image after cutting, successively scans all pixels point in the image,
Enabling the pixel coordinate scanned is (x, y), and pixel value size is f (x, y)；
(5c) compares pixel value f (x, y) and threshold value T, if pixel value f (x, y) is less than threshold value T, f (x, y) is 0,
If pixel value f (x, y) is more than or equal to threshold value T, f (x, y) is 1.
Step 6, divide single eye images.
Coordinate (0, the 0) point of eye image starts after binaryzation, successively scans all pixels in the image, gives up respectively
The point that pixel summation is 0 on the point and the direction y that pixel summation in the direction x is 0 is abandoned, two single eye images, i.e. left-eye image are partitioned into
K1 and eye image k2.
Step 7, left-eye image is normalized, left-eye image k1 is normalized to the left eye of 32*16 size with adjacent interpolation algorithm
Image h1.
(7a) does geometric transformation to left-eye image k1, obtains image k ' after the transformation that size is 32*16；
Coordinate (0, the 0) point that (7b) acquires image k ' after transformation starts, and successively scans all pixels point in the image
(x ', y ') finds the nearest point (x, y) of distance in left-eye image k1 (x ', y '), the pixel value k ' that enables (x ', y ') to put (x ', y ')
Equal to the pixel value k (x, y) of (x, y) point, the image k ' obtained at this time is left-eye image h1；
The eye image h2 for being normalized to 32*16 size is obtained with same method processing eye image.
Step 8, human eye error image is acquired.
(8a) selects size for 32*16 and without normal person's left eye binary image of the trace of blood and stain, as left eye mould
Plate image H1, and made the difference with left eye template image H1 and normalization left-eye image h1 and obtained left eye error image h1 '；
(8b) selects size for 32*16 and without normal person's right eye binary image of the trace of blood and stain, as right eye mould
Plate image H2, and made the difference with right eye template image H2 and normalization eye image h2 and obtained right eye error image h2 '；
Step 9, abnormal point image is obtained.
(9a) obtains the abnormal point image h1 " of left eye to left eye error image h1 ' cutting, by adjacent interpolation algorithm that left eye is different
Sampling point image h1 " is normalized to the abnormal point image h1 " ' of left eye of 32*16 size；
(9a) obtains the abnormal point image h2 " of right eye to right eye error image h2 ' cutting, will be right abnormal by adjacent interpolation algorithm
Point image h2 " is normalized to the abnormal point image h2 " ' of right eye of 32*16 size.
Step 10, information ratio is calculated.
White points C1 after (10a) calculating normalization in the abnormal point image h1 " ' of left eye, i.e., from the abnormal point image of left eye
Coordinate (0, the 0) point of h1 " ' starts, and scans all pixels point of the image, and the point for being 1 to pixel value is summed, and obtains white in left eye
Color dot number C1, and calculate the information ratio g1 of white points C1 and 32*16 in left eye；
White points C2 after (10b) calculating normalization in the abnormal point image h2 " ' of right eye, i.e., from the abnormal point image of right eye
Coordinate (0, the 0) point of h2 " ' starts, and scans all pixels point of the image, and the point for being 1 to pixel value is summed, and obtains white in right eye
Color dot number C2, and calculate the information ratio g2 of white points C2 and 32*16 in right eye；
Step 11, the trace of blood and stain are determined whether there is.
The threshold value G=0.6835 for judging stain and trace of blood point is arranged in (11a)；
(11b) compares the size of g1 and G, if g1=<G, is judged to have stain in left eye, if 1>g1>G, is judged to left eye
In have the trace of blood, if g1=1, it is normal to be judged to left eye；
(11b) compares the size of g2 and G, if g2=<G, is judged to have stain in right eye, if 1>g2>G, is judged to right eye
In have trace of blood point that it is normal to be judged to right eye if g2=1.
Step 12, judgement result is prompted the user at front camera photograph interface.
User can go hospital admission to treat in time according to the prompt of mobile phone, in order to avoid delaying the state of an illness, protect eye health.
Above description is only example of the present invention, it is clear that for those skilled in the art, is being understood
After the content of present invention and principle, all it may be carried out in form and details without departing substantially from the principle of the invention, structure
Various modifications and variations, but the modifications and variations of these basic inventive ideas still claims of the invention it
It is interior.
Claims (5)
1. a kind of system using stain and the trace of blood in mobile phone front camera automatic identification human eye, which executes following function
Step:
(1) the distance between portrait and camera d are identified by the range sensor on smart phone；
(2) portrait is compared with the distance between camera d with the threshold value R of setting by set distance threshold value R=1m: if d >
R then keeps mobile phone institute constant at image original resolution ratio；If d < R, (3) are thened follow the steps；
(3) interpolation is carried out at image to front camera institute using bilinear interpolation algorithm, interpolation number N is (1-dR) integer
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 is found according to edge detection results
The region of the direction x, y human eye, give up be not human eye area point, complete human eye cut, then to after cutting eye image carry out
Binary conversion treatment obtains binary image；
(5) horizontal and vertical calculating is carried out to binary image, 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) select size for 32*16 and without the simple eye binary image of the normal person of the trace of blood and stain, as template image H, and
It is made the difference with template image H and normalization single eye images h and is obtained human eye error image h '；
(7) abnormal point image h " is obtained to error image h ' cutting, is normalized to abnormal point image h " by adjacent interpolation algorithm
The abnormal point image h " ' of 32*16 size；
(8) the white points C after normalizing in abnormal point image h " ' is calculated, and calculates the information ratio of white points C and 32*16
g；
(9) setting judges the threshold value G=0.6835 of stain and trace of blood point, compares the size of g and G, if g=< G, is judged to eyes
There is stain, if 1 > g > G, being judged to eyes has trace of blood point that it is normal to be judged to eyes if g=1；
(10) result is determined in front camera photograph circle's user oriented display.
2. system according to claim 1, wherein in step (3) using bilinear interpolation algorithm to front camera institute at
Image carry out interpolation, as follows carry out:
(3a) starts from coordinate (0, the 0) point of portrait image, successively scans all pixels point in the image, enables the picture scanned
Vegetarian refreshments coordinate is (x, y), then to obtain four scanning element points, respectively A (x, y), B (x+1, y), C (x, y based on (x, y)
+ 1), D (x+1, y+1), enabling the size of these scanning element points is respectively f (A), f (B), f (C), f (D)；
(3b) is determined according to the distance between portrait and camera d with A (x, y), B (x+1, y), C (x, y+1), D (x+1, y+1)
The number of interpolation point in 4 points of square areas surrounded are as follows:Wherein constant δ=10, distance threshold R=
1m；
(3c) is determined A (x, y), B (x+1, y), C (x, y+1), and the coordinate of interpolation point is in 4 points of D (x+1, y+1)Calculate the size of interpolation point pixel are as follows:
Wherein n=1,2...N.
3. system according to claim 1 wherein carries out binary conversion treatment to the eye image after cutting in step (4),
It carries out as follows:
(4a) obtains binaryzation optimal threshold T using maximum variance thresholding method；
(4b) starts from coordinate (0, the 0) point of the eye image after cutting, successively scans all pixels point in the image, order is swept
The pixel coordinate retouched is (x, y), and pixel value size is f (x, y)；
(4c) compares pixel value f (x, y) and threshold value T, if pixel value f (x, y) is less than threshold value T, f (x, y) is 0, if picture
Element value f (x, y) is more than or equal to threshold value T, then f (x, y) is 1.
4. single eye images are wherein normalized to 32* with adjacent interpolation algorithm in step (5) by system according to claim 1
The single eye images h of 16 sizes is carried out as follows:
Single eye images k is done geometric transformation by (5a), obtains image k ' after the transformation that size is 32*16；
(5b) coordinate (0,0) point of image k ' after transformation starts, and successively scans all pixels point (x ', y ') in the image,
The point (x, y) that distance (x ', y ') is nearest in single eye images k is found, enables the pixel value k ' (x ', y ') of (x ', y ') point equal to (x, y)
The pixel value k (x, y) of point, the image k ' obtained at this time is single eye images h.
5. system according to claim 1 wherein calculates the white after normalizing in abnormal point image h " ' in step (8)
Count C, is to start from coordinate (0, the 0) point of abnormal point image h " ', scans all pixels point of the image, is 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 CN106446859A (en) | 2017-02-22 |
| CN106446859B true 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) |
Families Citing this family (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 |
| CN112022083B (en) * | 2020-07-31 | 2023-02-10 | 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 |
|---|
| An Improved Bilinear Interpolation Algorithm of Converting Standard-definition Television Images to High-definition Television Images;Lu Jing等;《2009 WASE International Conference on Information Engineering》;20091231;第441-444 * |
| 基于卷积神经网络的眼球血丝诊断;吴聪等;《软件导刊》;20160531;第15卷(第5期);第140-142页 * |
| 基于计算机视觉的人眼行为识别算法分析;马文刚;《中国优秀硕士学位论文全文数据库-信息科技辑》;20141015(第10期);第I138-1031页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106446859A (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106909875B (en) | Face type classification method and system | |
| KR101390756B1 (en) | Facial feature detection method and device | |
| CN108765273A (en) | The virtual lift face method and apparatus that face is taken pictures | |
| EP2923306B1 (en) | Method and apparatus for facial image processing | |
| KR100682889B1 (en) | Method and Apparatus for image-based photorealistic 3D face modeling | |
| US7970212B2 (en) | Method for automatic detection and classification of objects and patterns in low resolution environments | |
| CN104463159B (en) | A kind of image processing method and device for positioning iris | |
| US8154591B2 (en) | Eyelid opening level determination device and computer readable medium storing computer program thereof | |
| US20040037460A1 (en) | Method for detecting objects in digital images | |
| JP4445454B2 (en) | Face center position detection device, face center position detection method, and program | |
| JP4912206B2 (en) | Image processing method, image processing apparatus, image processing system, and computer program | |
| JP2005228042A (en) | Face identification device, face identification method, and face identification program | |
| WO2014186422A1 (en) | Image masks for face-related selection and processing in images | |
| CN106446859B (en) | Utilize the method for stain and the trace of blood in mobile phone front camera automatic identification human eye | |
| TW200414072A (en) | Iris extraction method | |
| CN111183630B (en) | Photo processing method and processing device of intelligent terminal | |
| CN105913373B (en) | Image processing method and device | |
| CN101642376A (en) | Device and method for detecting fatigue | |
| JP6885474B2 (en) | Image processing device, image processing method, and program | |
| CN114612939B (en) | Sitting posture identification method and device based on TOF camera and intelligent desk lamp | |
| CN111047619B (en) | Face image processing method and device and readable storage medium | |
| JP2006164133A (en) | Image processing method and device, and program | |
| CN111358421B (en) | Dioptric pattern generation method and device and computer-readable storage medium | |
| WO2017159215A1 (en) | Information processing device and information processing method | |
| CN105279764A (en) | Eye image processing device and eye image processing method |
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 |