CN107346408A - Age recognition methods based on face feature - Google Patents
Age recognition methods based on face feature Download PDFInfo
- Publication number
- CN107346408A CN107346408A CN201610291408.8A CN201610291408A CN107346408A CN 107346408 A CN107346408 A CN 107346408A CN 201610291408 A CN201610291408 A CN 201610291408A CN 107346408 A CN107346408 A CN 107346408A
- Authority
- CN
- China
- Prior art keywords
- region
- age
- nose
- eye
- midpoint
- 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
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- 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
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
A kind of age recognition methods based on face feature, comprises the following steps：Facial image is obtained, and captures face area；Characteristic point is set on the face area image of crawl；Age characteristics region is determined on face area according to the coordinate of characteristic point；The age characteristics in age characteristics region is extracted, and obtains corresponding age value；And age value is judged into the age compared with default threshold value.
Description
Technical field
The present invention relates to a kind of age recognition methods based on face feature.
Background technology
Existing face's age identification is carried out by way of handling whole face image mostly, but the acquisition of the whole image feature of face is very complicated, comprising information it is complicated and huge, associated picture processing operation it is cumbersome, cause that previous operations process is quite tediously long, and judging efficiency is relatively low.
The content of the invention
In view of the foregoing, it is necessary to provide it is a kind of can the efficient identification age method.
A kind of age recognition methods based on face feature, comprises the following steps：
Facial image is obtained, and captures face area；
Characteristic point is set on the face area image of crawl；
Age characteristics region is determined on face area according to the coordinate of characteristic point；
The age characteristics in age characteristics region is extracted, and obtains corresponding age value；And
Age value is judged into the age compared with default threshold value.
Preferably, it is described characteristic point is set on the face area image of crawl the step of including obtaining the position of eyebrow, eyes, nose, oral area this four organs in face area image, and these organs are indicated with characteristic point.
Preferably, left eyebrow eyebrow tail, left eyebrow brows, right eyebrow brows, right eyebrow eyebrow tail, the left eye tail of the eye, left eye center, left eye inner eye corner, right eye inner eye corner, right eye center, the right eye tail of the eye, the left nose wing, nose midpoint, the right wing of nose, the left corners of the mouth, mouth top midpoint, the right corners of the mouth and mouth bottom midpoint are indicated with characteristic point.
Preferably, before determining on face area age characteristics region according to the coordinate of characteristic point, two midpoint distances and the vertical range at two midpoints and nose midpoint are obtained by the position coordinates at left eye center, right eye center and nose midpoint, the abscissa that wherein two midpoints distance is equal to left eye midpoint subtracts the abscissa at right eye midpoint, the vertical range at two midpoints and nose midpoint be equal to nose midpoint ordinate subtract two midpoints ordinate draw value.
Preferably, region, the left nose wing to corners of the mouth region and the right wing of nose under region, right eye under left eye tail region domain, right eye tail region domain, left eye to corners of the mouth region are included according to the age characteristics region that the coordinate of characteristic point determines on face area.
Preferably, before the step of age characteristics in the extraction age characteristics region, the age characteristics region of same type is adjusted to an equal amount of region.
Preferably, left eye tail region domain and right eye tail region domain are the age characteristics region of same type, and region is the age characteristics region of same type, the left nose wing to corners of the mouth region and the right wing of nose to the age characteristics region that corners of the mouth region is same type under region and right eye under left eye.
Preferably, after the age characteristics region of same type being adjusted into an equal amount of region, the image in age characteristics region is converted into readily identified image by counting change scaling method.
Preferably, the default threshold value includes a first threshold and a Second Threshold, if the age value and the first threshold relatively after be more than the first threshold, by the age value compared with the Second Threshold.
Compared to prior art, in the above-mentioned age recognition methods based on face feature, by setting characteristic point on face area image, obtain age characteristics region, and the age is judged by the processing to a little age characteristics regions, the treating capacity of data is smaller, and judging efficiency is higher.
Brief description of the drawings
Fig. 1 is the flow chart of the age recognition methods of the invention based on face feature.
Fig. 2 is the schematic diagram that face area is captured in Fig. 1 age recognition methods.
Fig. 3 is the schematic diagram that characteristic point is set in Fig. 1 age recognition methods.
Fig. 4 is that two midpoint distances and two midpoints and the schematic diagram of the vertical range at nose midpoint are obtained in Fig. 1 age recognition methods.
Fig. 5 is the schematic diagram in the age characteristics region that face is determined in Fig. 1 age recognition methods.
Fig. 6 is the schematic diagram that eye tail region domain is determined in Fig. 1 age recognition methods.
Fig. 7 is the schematic diagram that region now is determined in Fig. 1 age recognition methods.
Fig. 8 is to determine the wing of nose to the schematic diagram in corners of the mouth region in Fig. 1 age recognition methods.
Main element symbol description
| Characteristic point | 1-17 |
| Two midpoint distances | W |
| The vertical range at two midpoints and nose midpoint | H |
| Eye tail region domain a and b | a、b |
| Region c and d now | c、d |
| The wing of nose is to corners of the mouth region e and f | e、f |
| End points | a1-a4、b1-b4、c1-c4、d1-d4、e1-e4、f1-f4 |
Following embodiment will combine above-mentioned accompanying drawing and further illustrate the present invention.
Embodiment
Fig. 1 is a kind of flow chart of the age recognition methods based on face feature of the present invention, and for identifying the age of people, the age recognition methods comprises the following steps：
Step 101, facial image is obtained, and captures face area.
Referring to Fig. 2, the facial image generally obtained can include the other parts of human body, such as neck etc., in a step 101, by the human face model pre-established and the facial image obtained, the image of face area is captured, and the image of other parts is removed.
Step 102, characteristic point is set on the face area image of crawl.
Refer to Fig. 3, it is compared by characteristic model with face area image, obtains the position of eyebrow, eyes, nose, oral area this four organs in face area image, and these organs is indicated with characteristic point, just as shown in Figure 3, left eyebrow eyebrow tail is indicated with characteristic point 1（Left and right definition is on the basis of the personnel for checking accompanying drawing）,Left eyebrow brows are indicated with characteristic point 2,Right eyebrow brows are indicated with characteristic point 3,Right eyebrow eyebrow tail is indicated with characteristic point 4,The left eye tail of the eye is indicated with characteristic point 5,Left eye center is indicated with characteristic point 6,Left eye inner eye corner is indicated with characteristic point 7,Right eye inner eye corner is indicated with characteristic point 8,Right eye center is indicated with characteristic point 9,The right eye tail of the eye is indicated with characteristic point 10,The left nose wing is indicated with characteristic point 11,Nose midpoint is indicated with characteristic point 12,The right wing of nose is indicated with characteristic point 13,The left corners of the mouth is indicated with characteristic point 14,Indicated with the lip-syncing top midpoint of characteristic point 15,The right corners of the mouth is indicated with characteristic point 16,Indicated with the lip-syncing bottom midpoint of characteristic point 17,Then face area image is indicated with 17 characteristic points in the present embodiment；In other embodiments, also eyebrow, eyes, nose, oral area this four organs can be indicated using more characteristic points or less characteristic point as needed, also according to judgement this organ to ear can be needed to carry out the mark of characteristic point, or other features of human body face are identified.
Step 103, two midpoint distance W and the vertical range H at two midpoints and nose midpoint are calculated according to the positional information of characteristic point.
Referring to Fig. 4, be typically that two midpoint distance W and the vertical range H at two midpoints and nose midpoint are calculated according to the coordinate of these characteristic points, such as the coordinate of characteristic point 6 is（X6, Y6）, the coordinate of characteristic point 9 is（X9, Y9）, the right of characteristic point 12 is（X12, Y12）, then two midpoint distance W=X9-X6, the vertical range H=Y12- (Y6+Y9)/2 at two midpoints and nose midpoint.
Step 104, the age characteristics region of face is determined according to the coordinate of each coordinate points and distance W, H.
Refer to Fig. 5, in the present embodiment, choose eye tail region domain a and b, now the age characteristics region of region c and d, the wing of nose to corners of the mouth region e and f as face, because the age characteristics in these regions of the face of people is more obvious, such as wrinkle difference of the face in these regions of the people of all ages and classes is larger；In other embodiments, also other face areas can be added according to different needs to be judged, such as forehead region etc..
Refer to Fig. 6, it is the schematic diagram for determining an a left eye tail region domain a and right eye tail region domain b, left eye tail region domain a is a square region, it includes upper left corner end points a1, upper right corner end points a2, lower left corner end points a3 and lower right corner end points a4, and the X-axis coordinate and Y-axis coordinate of each angle end points are calculated by formula listed in Table.
| Endpoint names | X-axis coordinate calculation | Y-axis coordinate calculation |
| Left eye tail region domain upper left corner end points a1 | X=X6–W*0.6 | Y=(Y6+Y9)/2 |
| Left eye tail region domain upper right corner end points a2 | X=X6–W*0.4 | Y=(Y6+Y9)/2 |
| Left eye tail region domain lower left corner end points a3 | X=X6–W*0.6 | Y=(Y6+Y9)+H*0.8 |
| Left eye tail region domain lower right corner end points a4 | X=X6–W*0.4 | Y=(Y6+Y9)+H*0.8 |
Equally, right eye tail region domain b is a square region, and it includes upper left corner end points b1, upper right corner end points b2, lower left corner end points b3 and lower right corner end points b4, and the X-axis coordinate and Y-axis coordinate of each angle end points are calculated by formula listed in Table.
| Endpoint names | X-axis coordinate calculation | Y-axis coordinate calculation |
| Right eye tail region domain upper left corner end points b1 | X=X9+W*0.4 | Y=(Y6+Y9)/2 |
| Right eye tail region domain upper right corner end points b2 | X=X9+W*0.6 | Y=(Y6+Y9)/2 |
| Right eye tail region domain lower left corner end points b3 | X=X9+W*0.4 | Y=(Y6+Y9)+H*0.8 |
| Right eye tail region domain lower right corner end points b4 | X=X9+W*0.6 | Y=(Y6+Y9)+H*0.8 |
Referring to Fig. 7, region c is a square region under left eye, it includes upper left corner end points c1, upper right corner end points c2, lower left corner end points c3 and lower right corner end points c4, and the X-axis coordinate and Y-axis coordinate of each angle end points are calculated by formula listed in Table.
| Endpoint names | X-coordinate calculation | Y-coordinate calculation |
| Region upper left corner end points c1 under left eye | X=X6–W*0.4 | Y=(Y6+Y9)/2+H*0.35 |
| Region upper right corner end points c2 under left eye | X=X6+W*0.3 | Y=(Y6+Y9)/2+H*0.35 |
| Region lower left corner end points c3 under left eye | X=X6–W*0.4 | Y=(Y6+Y9)/2+H*0.8 |
| Region lower right corner end points c4 under left eye | X=X6+W*0.3 | Y=(Y6+Y9)/2+H*0.8 |
Equally, region d is a square region under right eye, and it includes upper left corner end points d1, upper right corner end points d2, lower left corner end points d3 and lower right corner end points d4, and the X-axis coordinate and Y-axis coordinate of each angle end points are calculated by formula listed in Table.
| Endpoint names | X-coordinate calculation | Y-coordinate calculation |
| Region upper left corner end points d1 under right eye | X=X9–W*0.4 | Y=(Y6+Y9)/2+H*0.35 |
| Region upper right corner end points d2 under right eye | X=X9+W*0.3 | Y=(Y6+Y9)/2+H*0.35 |
| Region lower left corner end points d3 under right eye | X=X9–W*0.4 | Y=(Y6+Y9)+H*0.8 |
| Region lower right corner end points d4 under right eye | X=X9+W*0.3 | Y=(Y6+Y9)+H*0.8 |
Referring to Fig. 8, the left nose wing is a square region to corners of the mouth region e, it includes upper left corner end points e1, upper right corner end points e2, lower left corner end points e3 and lower right corner end points e4, and the X-axis coordinate and Y-axis coordinate of each angle end points are calculated by formula listed in Table.
| Endpoint names | X-coordinate calculation | Y-coordinate calculation |
| The left nose wing is to corners of the mouth region upper left corner end points e1 | X=X6–W*0.32 | Y=Y12 |
| The left nose wing is to corners of the mouth region upper right corner end points e2 | X=X6+W*0.05 | Y=Y12 |
| The left nose wing is to corners of the mouth region lower left corner end points e3 | X=X6–W*0.32 | Y=(Y14+Y16)/2 |
| The left nose wing is to corners of the mouth region lower right corner end points e4 | X=X6+W*0.05 | Y=(Y14+Y16)/2 |
Equally, the right wing of nose is a square region to corners of the mouth region f, and it includes upper left corner end points f1, upper right corner end points f2, lower left corner end points f3 and lower right corner end points f4, and the X-axis coordinate and Y-axis coordinate of each angle end points are calculated by formula listed in Table.
| Endpoint names | X-coordinate calculation | Y-coordinate calculation |
| The right wing of nose is to corners of the mouth region upper left corner end points e1 | X=X9+W*0.05 | Y=Y12 |
| The right wing of nose is to corners of the mouth region upper right corner end points e2 | X=X9+W*0.32 | Y=Y12 |
| The right wing of nose is to corners of the mouth region lower left corner end points e3 | X=X9+W*0.05 | Y=(Y14+Y16)/2 |
| The right wing of nose is to corners of the mouth region lower right corner end points e4 | X=X9+W*0.32 | Y=(Y14+Y16)/2 |
So as to which the method more than sets each age characteristics region a-f position and size.
Step 105, the age characteristics region of same type is adjusted to an equal amount of region.
In above-mentioned age characteristics region a, b, c, d, in e and f, left eye tail region domain a and right eye tail region domain b is the age characteristics region of same type, region d is the age characteristics region of same type under region c and right eye under left eye, age characteristics region of the left nose wing to corners of the mouth region e and the right wing of nose to corners of the mouth region f for same type, such as if left eye tail region domain a length is 9, height is 6, right eye tail region domain b length is 6, width is 8, then can be by the way that left eye tail region domain a length be shortened into 6 from 9, left eye tail region domain a height is stretched to 8 from 6, and make left eye tail region domain a identical with right eye tail region domain b size.
Step 106, readily identified image is converted into by counting change scaling method to the image in each age characteristics region.
It is that every 3*3 of image pixel is being divided into a region that statistics, which becomes scaling method, then calculate the pixel average of all pixels point in the region, then by the pixel value of each pixel in the region compared with the pixel average, if the pixel value of certain point is more than pixel average, the pixel value of the point is changed into 1；If the pixel value of certain point is less than pixel average, the pixel value of the point is changed into 0.
Step 107, the age characteristics of the image after extraction conversion, and corresponding age value is obtained, by the age value compared with a first threshold, if age value is more than or equal to first threshold, then to step 108；If age value is less than first threshold, to step 109.
Step 108, it is judged as the elderly, and by the age value compared with a Second Threshold；If age value is more than or equal to the Second Threshold, to step 110；If age value is more than or equal to the Second Threshold, to step 111.
Step 109, it is judged as young people.
Step 110, it is judged as the elderly.
Step 111, it is judged as a middle-aged person.
In the above-mentioned age recognition methods based on face feature, by setting characteristic point on face area image, age characteristics region is obtained, and judge that the treating capacity of data is smaller, and judging efficiency is higher to judge the age by the processing to a little age characteristics regions.
Claims (9)
1. a kind of age recognition methods based on face feature, comprises the following steps：
Facial image is obtained, and captures face area；
Characteristic point is set on the face area image of crawl；
Age characteristics region is determined on face area according to the coordinate of characteristic point；
The age characteristics in age characteristics region is extracted, and obtains corresponding age value；And
Age value is judged into the age compared with default threshold value.
2. age recognition methods as claimed in claim 1, it is characterised in that：It is described characteristic point is set on the face area image of crawl the step of including obtaining the position of eyebrow, eyes, nose, oral area this four organs in face area image, and these organs are indicated with characteristic point.
3. age recognition methods as claimed in claim 2, it is characterised in that：Left eyebrow eyebrow tail, left eyebrow brows, right eyebrow brows, right eyebrow eyebrow tail, the left eye tail of the eye, left eye center, left eye inner eye corner, right eye inner eye corner, right eye center, the right eye tail of the eye, the left nose wing, nose midpoint, the right wing of nose, the left corners of the mouth, mouth top midpoint, the right corners of the mouth and mouth bottom midpoint are indicated with characteristic point.
4. age recognition methods as claimed in claim 3, it is characterised in that：Before determining on face area age characteristics region according to the coordinate of characteristic point, two midpoint distances and the vertical range at two midpoints and nose midpoint are obtained by the position coordinates at left eye center, right eye center and nose midpoint, the abscissa that wherein two midpoints distance is equal to left eye midpoint subtracts the abscissa at right eye midpoint, the vertical range at two midpoints and nose midpoint be equal to nose midpoint ordinate subtract two midpoints ordinate draw value.
5. age recognition methods as claimed in claim 4, it is characterised in that：Region, the left nose wing to corners of the mouth region and the right wing of nose under region, right eye under left eye tail region domain, right eye tail region domain, left eye to corners of the mouth region are included according to the age characteristics region that the coordinate of characteristic point determines on face area.
6. age recognition methods as claimed in claim 5, it is characterised in that：Before the step of age characteristics in the extraction age characteristics region, the age characteristics region of same type is adjusted to an equal amount of region.
7. age recognition methods as claimed in claim 6, it is characterised in that：Left eye tail region domain and right eye tail region domain are the age characteristics region of same type, and region is the age characteristics region of same type, the left nose wing to corners of the mouth region and the right wing of nose to the age characteristics region that corners of the mouth region is same type under region and right eye under left eye.
8. age recognition methods as claimed in claim 6, it is characterised in that：After the age characteristics region of same type is adjusted into an equal amount of region, the image in age characteristics region is converted into readily identified image by counting change scaling method.
9. age recognition methods as claimed in claim 1, it is characterised in that：The default threshold value includes a first threshold and a Second Threshold, if the age value and the first threshold relatively after be more than the first threshold, by the age value compared with the Second Threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610291408.8A CN107346408A (en) | 2016-05-05 | 2016-05-05 | Age recognition methods based on face feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610291408.8A CN107346408A (en) | 2016-05-05 | 2016-05-05 | Age recognition methods based on face feature |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107346408A true CN107346408A (en) | 2017-11-14 |
Family
ID=60253135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610291408.8A Pending CN107346408A (en) | 2016-05-05 | 2016-05-05 | Age recognition methods based on face feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107346408A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932497A (en) * | 2018-07-03 | 2018-12-04 | 张廷敏 | Passen-gers' big data identification mechanism |
| CN109034138A (en) * | 2018-09-11 | 2018-12-18 | 湖南拓视觉信息技术有限公司 | Image processing method and device |
| CN109145865A (en) * | 2018-09-07 | 2019-01-04 | 北京相貌空间科技有限公司 | Face standard level calculating method and device |
| CN110287942A (en) * | 2019-07-03 | 2019-09-27 | 成都旷视金智科技有限公司 | Training method, age estimation method and the corresponding device of age estimation model |
| CN112883759A (en) * | 2019-11-29 | 2021-06-01 | 杭州海康威视数字技术股份有限公司 | Method for detecting image noise of biological characteristic part |
| CN117354417A (en) * | 2023-10-09 | 2024-01-05 | 深圳多为智联科技有限公司 | Smart phone screen closing method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100111375A1 (en) * | 2008-10-31 | 2010-05-06 | Michael Jeffrey Jones | Method for Determining Atributes of Faces in Images |
| CN102194131A (en) * | 2011-06-01 | 2011-09-21 | 华南理工大学 | Fast human face recognition method based on geometric proportion characteristic of five sense organs |
| US20140140584A1 (en) * | 2011-08-09 | 2014-05-22 | Pramor LLC | Method and apparatus for generating personal information of client, recording medium thereof, and pos systems |
| CN104143079A (en) * | 2013-05-10 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method and system for face attribute recognition |
| CN104391857A (en) * | 2014-10-17 | 2015-03-04 | 惠州Tcl移动通信有限公司 | Equipment terminal and method for displaying webpage content according to age information |
| CN105469064A (en) * | 2015-12-03 | 2016-04-06 | 广州市皓品信息科技有限公司 | Skin aging trend acquisition method and apparatus |
-
2016
- 2016-05-05 CN CN201610291408.8A patent/CN107346408A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100111375A1 (en) * | 2008-10-31 | 2010-05-06 | Michael Jeffrey Jones | Method for Determining Atributes of Faces in Images |
| CN102194131A (en) * | 2011-06-01 | 2011-09-21 | 华南理工大学 | Fast human face recognition method based on geometric proportion characteristic of five sense organs |
| US20140140584A1 (en) * | 2011-08-09 | 2014-05-22 | Pramor LLC | Method and apparatus for generating personal information of client, recording medium thereof, and pos systems |
| CN104143079A (en) * | 2013-05-10 | 2014-11-12 | 腾讯科技（深圳）有限公司 | Method and system for face attribute recognition |
| CN104391857A (en) * | 2014-10-17 | 2015-03-04 | 惠州Tcl移动通信有限公司 | Equipment terminal and method for displaying webpage content according to age information |
| CN105469064A (en) * | 2015-12-03 | 2016-04-06 | 广州市皓品信息科技有限公司 | Skin aging trend acquisition method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 胡德文 等: "《生物特征识别技术与方法》", 31 August 2013, 国防工业出版社 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932497A (en) * | 2018-07-03 | 2018-12-04 | 张廷敏 | Passen-gers' big data identification mechanism |
| CN109145865A (en) * | 2018-09-07 | 2019-01-04 | 北京相貌空间科技有限公司 | Face standard level calculating method and device |
| CN109034138A (en) * | 2018-09-11 | 2018-12-18 | 湖南拓视觉信息技术有限公司 | Image processing method and device |
| CN109034138B (en) * | 2018-09-11 | 2021-09-03 | 湖南拓视觉信息技术有限公司 | Image processing method and device |
| CN110287942A (en) * | 2019-07-03 | 2019-09-27 | 成都旷视金智科技有限公司 | Training method, age estimation method and the corresponding device of age estimation model |
| CN112883759A (en) * | 2019-11-29 | 2021-06-01 | 杭州海康威视数字技术股份有限公司 | Method for detecting image noise of biological characteristic part |
| CN112883759B (en) * | 2019-11-29 | 2023-09-26 | 杭州海康威视数字技术股份有限公司 | Method for detecting image noise of biological feature part |
| CN117354417A (en) * | 2023-10-09 | 2024-01-05 | 深圳多为智联科技有限公司 | Smart phone screen closing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107346408A (en) | Age recognition methods based on face feature | |
| US10783354B2 (en) | Facial image processing method and apparatus, and storage medium | |
| US11043011B2 (en) | Image processing method, apparatus, terminal, and storage medium for fusing images of two objects | |
| CN102521579B (en) | Method for identifying pushing action based on two-dimensional planar camera and system | |
| CN107316333B (en) | A method of it automatically generates and day overflows portrait | |
| TW201737159A (en) | Method for judgeing age based on face | |
| CN112384127B (en) | Eyelid sagging detection method and system | |
| CN106548165A (en) | A kind of face identification method of the convolutional neural networks weighted based on image block | |
| CN106447720B (en) | A method of building golden ratio shape of face | |
| CN104361131B (en) | The method for building up of four-dimensional faceform's database | |
| WO2020038312A1 (en) | Multi-channel tongue body edge detection device and method, and storage medium | |
| JP2007272435A (en) | Face feature extraction device and face feature extraction method | |
| CN106980845B (en) | Face key point positioning method based on structured modeling | |
| CN110648336B (en) | Method and device for dividing tongue texture and tongue coating | |
| CN106599826A (en) | Face 3D reconstruction method based on near-infrared light | |
| CN114511567B (en) | Tongue body and tongue coating image identification and separation method | |
| CN110688962B (en) | Face image processing method, user equipment, storage medium and device | |
| Sheu et al. | Automatic generation of facial expression using triangular geometric deformation | |
| CN102968636B (en) | A kind of extracting method of facial contour | |
| CN104573628A (en) | Three-dimensional face recognition method | |
| CN107093182A (en) | A kind of human height's method of estimation of feature based flex point | |
| CN112507766B (en) | Face image extraction method, storage medium and terminal equipment | |
| CN110472567A (en) | A kind of face identification method and system suitable under non-cooperation scene | |
| CN106846399A (en) | A kind of method and device of the vision center of gravity for obtaining image | |
| CN109711390A (en) | Face scratches the preferred method and device of figure picture |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180228 Address after: Haiyun Binhai Economic and Technological Development Zone, Tianjin City, No. 80 300457 Street Applicant after: Hongfujin Precision Electronics (Tianjin) Co., Ltd. Address before: Haiyun Binhai Economic and Technological Development Zone, Tianjin City, No. 80 300457 Street Applicant before: Hongfujin Precision Electronics (Tianjin) Co., Ltd. Applicant before: Hon Hai Precision Industry Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171114 |