CN106650583B - Method for detecting human face, device and terminal device - Google Patents
Method for detecting human face, device and terminal device Download PDFInfo
- Publication number
- CN106650583B CN106650583B CN201610860342.XA CN201610860342A CN106650583B CN 106650583 B CN106650583 B CN 106650583B CN 201610860342 A CN201610860342 A CN 201610860342A CN 106650583 B CN106650583 B CN 106650583B
- Authority
- CN
- China
- Prior art keywords
- frame image
- region
- face
- human face
- candidate
- 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
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
- G06V40/161—Detection; Localisation; Normalisation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of method for detecting human face, device and terminal devices.Wherein, this method comprises: detecting the face in preview screen according to predetermined period, and the picture frame of label human face region is stored；If face is not detected in T moment in period corresponding k-th frame image, the skin pixels of the human face region in (T-1) moment in period corresponding (K-1) frame image are extracted；Detect k-th frame image in the matched position candidate of skin pixels, and in position candidate determine target position；Centered on target position, obtained in k-th frame image and the matched candidate region of human face region size in (K-1) frame image；If candidate region exceeds normal pictures, half face region is determined in k-th frame image according to position candidate.Through the embodiment of the present invention, it can be realized the identification of half face, avoid Face datection failure, improve face identification rate.
Description
Technical field
The present invention relates to technical field of mobile terminals more particularly to a kind of method for detecting human face, device and terminal device.
Background technique
In general, photographing device is easier to recognize whole face, and then shot.
However, certain user only claps half of face for specific demands such as shield portions facial defects, in such a scenario,
For photographing device, face can not be detected, it may appear that Face datection failure, face identification rate are low.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.
For this purpose, this method can be realized the identification of half face an object of the present invention is to provide a kind of method for detecting human face,
Face datection failure is avoided, face identification rate is improved.
Second object of the present invention is to propose a kind of human face detection device.
Third object of the present invention is to propose a kind of terminal device.
In order to achieve the above object, a kind of method for detecting human face that embodiment proposes according to a first aspect of the present invention, including it is following
Step:
The face in preview screen is detected according to predetermined period, and stores the picture frame of label human face region；
If the face is not detected in T moment corresponding k-th frame image, extract corresponding at (T-1) moment
The skin pixels of human face region in (K-1) frame image；
Detect in the k-th frame image with the matched position candidate of the skin pixels, and in the position candidate really
Set the goal position；
Centered on the target position, obtained in the k-th frame image and face area in (K-1) frame image
The matched candidate region of domain size；
If the candidate region exceeds normal pictures, determined in the k-th frame image according to the position candidate
Half face region.
The method for detecting human face of the embodiment of the present invention detects the face in preview screen according to predetermined period first, and deposits
The picture frame of storage label human face region, when face then is not detected in T moment in period corresponding k-th frame image, is extracted
(T-1) in moment in period corresponding (K-1) frame image human face region skin pixels, then detect k-th frame image in skin
The position candidate of skin pixel matching, and target position is determined in position candidate, finally centered on target position, in k-th frame
It is obtained in image with the matched candidate region of human face region size in (K-1) frame image and exceeds normal pictures in candidate region
When, half face region is determined in k-th frame image according to position candidate.Thereby, it is possible to realize that half face identifies, Face datection is avoided
Failure, improves face identification rate.
In order to achieve the above object, a kind of human face detection device that embodiment proposes according to the second aspect of the invention, comprising: place
Module is managed, for detecting the face in preview screen according to predetermined period, and stores the picture frame of label human face region；
Extraction module when for the face to be not detected in T moment in period corresponding k-th frame image, is extracted in (T-
1) in moment in period corresponding (K-1) frame image human face region skin pixels；
Detection module, for detect in the k-th frame image with the matched position candidate of the skin pixels,
First determining module, for determining target position in the position candidate；
Matching module, for being obtained and (K-1) in the k-th frame image centered on the target position
The matched candidate region of human face region size in frame image；
Second determining module is used for when the candidate region exceeds normal pictures, according to the position candidate described
Half face region is determined in k-th frame image.
The human face detection device of the embodiment of the present invention detects the face in preview screen according to predetermined period first, and deposits
The picture frame of storage label human face region, when face then is not detected in T moment in period corresponding k-th frame image, is extracted
(T-1) in moment in period corresponding (K-1) frame image human face region skin pixels, then detect k-th frame image in skin
The position candidate of skin pixel matching, and target position is determined in position candidate, finally centered on target position, in k-th frame
It is obtained in image with the matched candidate region of human face region size in (K-1) frame image and exceeds normal pictures in candidate region
When, half face region is determined in k-th frame image according to position candidate.Thereby, it is possible to realize that half face identifies, Face datection is avoided
Failure, improves face identification rate.
In order to achieve the above object, the terminal device that embodiment proposes according to the third aspect of the invention we, comprising: shell, processing
Device, memory, circuit board and power circuit, wherein the circuit board is placed in the space interior that the shell surrounds, the place
It manages device and the memory is arranged on the circuit board；The power circuit, for each circuit or device for terminal device
Part power supply；The memory is for storing executable program code；The processor is stored in the memory by reading
Executable program code runs program corresponding with the executable program code, for executing following steps:
The face in preview screen is detected according to predetermined period, and stores the picture frame of label human face region；
If the face is not detected in T moment corresponding k-th frame image, extract corresponding at (T-1) moment
The skin pixels of human face region in (K-1) frame image；
Detect in the k-th frame image with the matched position candidate of the skin pixels, and in the position candidate really
Set the goal position；
Centered on the target position, obtained in the k-th frame image and face area in (K-1) frame image
The matched candidate region of domain size；
If the candidate region exceeds normal pictures, determined in the k-th frame image according to the position candidate
Half face region.
The terminal device of the embodiment of the present invention detects the face in preview screen according to predetermined period first, and stores mark
The picture frame for remembering human face region when face then is not detected in T moment in period corresponding k-th frame image, is extracted at (T-1)
The skin pixels of human face region in moment in period corresponding (K-1) frame image, then detect k-th frame image in skin pixels
Matched position candidate, and target position is determined in position candidate, finally centered on target position, in k-th frame image
It obtains with the matched candidate region of human face region size in (K-1) frame image and when candidate region exceeds normal pictures, root
Half face region is determined in k-th frame image according to position candidate.Thereby, it is possible to realize that half face identifies, Face datection failure is avoided,
Improve face identification rate.
Detailed description of the invention
Fig. 1 is the flow chart of method for detecting human face according to an embodiment of the invention；
Fig. 2 is the schematic diagram of the picture frame of label human face region according to an embodiment of the invention；
Fig. 3 is the schematic diagram of the picture frame of label human face region in accordance with another embodiment of the present invention；
Fig. 4 is the schematic diagram of detection position candidate according to an embodiment of the invention；
Fig. 5 is the schematic diagram in half face region of determination according to an embodiment of the invention；
Fig. 6 is the schematic diagram in half face region of determination in accordance with another embodiment of the present invention；
Fig. 7 is the structural schematic diagram of human face detection device according to an embodiment of the invention；And
Fig. 8 is the structural schematic diagram of terminal device according to an embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings the Face datection, device and terminal device of the embodiment of the present invention are described.
Fig. 1 is the flow chart of method for detecting human face according to an embodiment of the invention.
As shown in Figure 1, the method for detecting human face of the embodiment of the present invention the following steps are included:
Step 101, the face in preview screen is detected according to predetermined period, and stores the picture frame of label human face region.
It is mechanical, electrical that the method for detecting human face of the embodiment of the present invention can be configured in the hand with either camera function of taking pictures
In the electronic equipments such as brain, intelligent wearable device.
In general, take pictures or photographic device in there is human-face detector or corresponding Face datection algorithm to pass through detection
The characteristic informations such as eyes, mouth in preview screen, the face location in lock preview picture, and automatically using face as taking pictures or
The main body of person's camera shooting, is arranged accurate focal length and light exposure.However, Face datection algorithm is in certain special cases, such as half
When face, face can not be detected, to Face datection failure occur, face identification rate is low.
To solve the above-mentioned problems, the embodiment of the present invention proposes a kind of method for detecting human face, can be realized the identification of half face, keeps away
Exempt from Face datection failure, improves face identification rate.
Firstly, according to the face in certain predetermined period detection preview screen.Wherein it is possible to pass through according to predetermined period
Face in the preview screen of front camera acquisition can also be drawn according to predetermined period by the preview that rear camera acquires
Face in face.
Wherein, predetermined period can carry out selection setting according to the actual application, and for example, 0.1 second, 0.5 second etc..With
Human face region in predetermined period lock preview picture, marks and stores.In order to which those skilled in the art more understand the above process, knot
Fig. 2 is closed to be described as follows:
Fig. 2 is the schematic diagram of the picture frame of label human face region according to an embodiment of the invention.
As shown in Fig. 2, Fig. 2 a is that current time detects the face in preview screen and stores the image of label human face region
Frame, Fig. 2 b are the picture frame for detecting the face in preview screen for 0.1 second after (predetermined period) again and storing label human face region.
Step 102, it if face is not detected in T moment in period corresponding k-th frame image, extracts in (T-1) week
The skin pixels of human face region in moment phase corresponding (K-1) frame image.
Specifically, face is not detected in T moment in period corresponding k-th frame image, that is, the feelings of face loss occur
When condition, need to extract (K-1) the frame image acquired relative to the upper a cycle in T period before face is lost, and search
The human face region in (K-1) frame image is stored, and then extracts the skin pixels of the human face region.
Wherein, skin pixels include the rgb value of human face region, i.e., the three of red pixel, green pixel and blue pixel are former
Color value.There are many kinds of the modes for extracting skin pixels, can be by application software such as Matlab, Opencv to (K-1) frame figure
Human face region carries out pixel extraction as in.
Fig. 3 is the schematic diagram of the picture frame of label human face region in accordance with another embodiment of the present invention.
As shown in figure 3, face is not detected in k-th frame image does not mark human face region, there is mark in (K-1) frame image
Human face region is remembered, so as to extract the skin pixels of the human face region by Opencv.
Step 103, detect k-th frame image in the matched position candidate of skin pixels, and in position candidate determine mesh
Cursor position.
Specifically, detect in k-th frame image with the mode of the matched position candidate of skin pixels there are many kinds of, user can be with
Selection setting is carried out according to the actual application.It is illustrated below:
The first example determines the region adjacent with human face region in (K-1) frame image, in phase in k-th frame image
Detection includes the target area of skin pixels in adjacent region, in the target area the determining and matched candidate bit of skin pixels
It sets.
Fig. 4 is the schematic diagram of detection position candidate according to an embodiment of the invention.
As shown in figure 4, can be detected in four adjacent regions of human face region in (K-1) frame image.In determination
With the target area of skin pixels in 4th adjacent region, and then the determining and matched time of skin pixels in the target area
Bit selecting is set.
It should be noted that being not limited to be divided into four adjacent regions shown in Fig. 4, the target area with skin pixels
It may also need to determine as the case may be in the first adjacent region, two adjacent regions etc..
Second of example reads the skin pixels in k-th frame image according to preset read direction.By the skin of reading
Pixel is matched with the skin pixels of the human face region in (K-1) frame image.From the corresponding position of matched skin pixels
Middle selection any position is as position candidate.
Wherein, preset read direction can select to be arranged according to actual needs, such as can be with k-th frame image in the vertical direction
Coordinate half be read starting point, and in the horizontal direction read one-row pixels data, with determine the reading side
Upward human face region, and the pixel data in human face region is skin pixels.The corresponding position conduct of the skin pixels
Position candidate.
Further, target position is determined in position candidate, it can be by calculating human face region in (K-1) frame image
Skin pixels pixel average, in position candidate detection with the matched target position of pixel average.
Specifically, the pixel average that the skin pixels of human face region in (K-1) frame image are obtained by calculation is A,
The matched position A is being detected in position candidate as target position.
Wherein, the calculating of pixel average can be by taking some scale, calculate with face area in (K-1) frame image
The pixel average for the human face region that the central point in domain is spread around.
Step 104, it centered on target position, is obtained in k-th frame image big with human face region in (K-1) frame image
Small matched candidate region.
Step 105, if candidate region exceeds normal pictures, half face is determined in k-th frame image according to position candidate
Region.
Specifically, it after determining target position, using target position as midpoint, is obtained and (K-1) in k-th frame image
The matched candidate region of human face region size in frame image.When candidate region exceeds normal pictures, according to position candidate in K
Half face region is determined in frame image.
It should be noted that if candidate region without departing from normal pictures, according to candidate region in k-th frame image really
Determine human face region.
Fig. 5 is the schematic diagram in half face region of determination according to an embodiment of the invention.
As shown in figure 5, candidate region in k-th frame image exceeds normal pictures, as a result, by k-th frame image with skin
The position candidate of pixel matching is as half face region.
Fig. 6 is the schematic diagram in half face region of determination in accordance with another embodiment of the present invention.
As shown in fig. 6, the candidate region in k-th frame image is without departing from normal pictures, as a result, by the time in k-th frame image
Favored area is as human face region.
The method for detecting human face of the embodiment of the present invention detects the face in preview screen according to predetermined period first, and deposits
The picture frame of storage label human face region, when face then is not detected in T moment in period corresponding k-th frame image, is extracted
(T-1) in moment in period corresponding (K-1) frame image human face region skin pixels, then detect k-th frame image in skin
The position candidate of skin pixel matching, and target position is determined in position candidate, finally centered on target position, in k-th frame
It is obtained in image with the matched candidate region of human face region size in (K-1) frame image and exceeds normal pictures in candidate region
When, half face region is determined in k-th frame image according to position candidate.Thereby, it is possible to realize that half face identifies, Face datection is avoided
Failure, improves face identification rate.
In order to realize above-described embodiment, the invention also provides a kind of human face detection devices.
Fig. 7 is the structural schematic diagram of human face detection device according to an embodiment of the invention.
As shown in fig. 7, the human face detection device includes: that processing module 10, extraction module 20, detection module 30, first are true
Cover half block 40, matching module 50, the second determining module 60 and third determining module 70.
Wherein, processing module 10 is used to detect the face in preview screen according to predetermined period, and stores label face area
The picture frame in domain.
Extraction module 20 is for extracting at (T-1) when face is not detected in T moment in period corresponding k-th frame image
The skin pixels of human face region in moment in period corresponding (K-1) frame image.
Detection module 30 is used to detect in k-th frame image and the matched position candidate of skin pixels.
First determining module 40 is used to determine target position in position candidate.
Matching module 50 is used for centered on target position, is obtained in k-th frame image and face in (K-1) frame image
The matched candidate region of area size.
Second determining module 60 is used for when candidate region exceeds normal pictures, according to position candidate in k-th frame image
Determine half face region.
Specifically, the face in preview screen is detected according to predetermined period, comprising: pass through according to predetermined period detection preposition
Face in the preview screen of camera acquisition, alternatively, being drawn according to predetermined period detection by the preview that rear camera acquires
Face in face.
Detection module 30 in k-th frame image for determining the area adjacent with human face region in (K-1) frame image
Domain, detection includes the target area of skin pixels in adjacent region, and determination is matched with skin pixels in the target area
Position candidate.
First determining module 40 is used to calculate the pixel average of the skin pixels of human face region in (K-1) frame image,
Detection and the matched target position of pixel average in position candidate.
Third determining module 70 is used for when candidate region is without departing from normal pictures, according to candidate region in k-th frame image
Middle determining human face region.
It should be noted that the aforementioned face for being also applied for the embodiment to the explanation of method for detecting human face embodiment
Detection device, realization principle is similar, and details are not described herein again.
The human face detection device of the embodiment of the present invention detects the face in preview screen according to predetermined period first, and deposits
The picture frame of storage label human face region, when face then is not detected in T moment in period corresponding k-th frame image, is extracted
(T-1) in moment in period corresponding (K-1) frame image human face region skin pixels, then detect k-th frame image in skin
The position candidate of skin pixel matching, and target position is determined in position candidate, finally centered on target position, in k-th frame
It is obtained in image with the matched candidate region of human face region size in (K-1) frame image and exceeds normal pictures in candidate region
When, half face region is determined in k-th frame image according to position candidate.Thereby, it is possible to realize that half face identifies, Face datection is avoided
Failure, improves face identification rate.
Fig. 8 is the structural schematic diagram of terminal device according to an embodiment of the invention.
Referring to Fig. 8, terminal device 1000 may include following one or more components: processor 1001, memory 1002,
Power circuit 1003, multimedia component 1004, audio component 1005, the interface 1006 of input/output (I/O), sensor module
1007 and communication component 1008.
Power circuit 1003, for each circuit or the device power supply for terminal device；Memory 1002 can for storing
Execute program code；Processor 1001 runs and can be performed by reading the executable program code stored in memory 1002
The corresponding program of program code, for executing following steps:
The face in preview screen is detected according to predetermined period, and stores the picture frame of label human face region.
If face is not detected in T moment in period corresponding k-th frame image, extract at (T-1) moment pair in period
The skin pixels of human face region in (K-1) the frame image answered.
Detect k-th frame image in the matched position candidate of skin pixels, and in position candidate determine target position.
Centered on target position, obtained in k-th frame image matched with human face region size in (K-1) frame image
Candidate region.
If candidate region exceeds normal pictures, half face region is determined in k-th frame image according to position candidate.
It should be noted that the aforementioned terminal for being also applied for the embodiment to the explanation of method for detecting human face embodiment
Equipment, realization principle is similar, and details are not described herein again.
The terminal device of the embodiment of the present invention detects the face in preview screen according to predetermined period first, and stores mark
The picture frame for remembering human face region when face then is not detected in T moment in period corresponding k-th frame image, is extracted at (T-1)
The skin pixels of human face region in moment in period corresponding (K-1) frame image, then detect k-th frame image in skin pixels
Matched position candidate, and target position is determined in position candidate, finally centered on target position, in k-th frame image
It obtains with the matched candidate region of human face region size in (K-1) frame image and when candidate region exceeds normal pictures, root
Half face region is determined in k-th frame image according to position candidate.Thereby, it is possible to realize that half face identifies, Face datection failure is avoided,
Improve face identification rate.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (11)
1. a kind of method for detecting human face, which comprises the following steps:
The face in preview screen is detected according to predetermined period, and stores the picture frame of label human face region；
If the face is not detected in T moment in period corresponding k-th frame image, extract at (T-1) moment pair in period
The skin pixels of human face region in (K-1) the frame image answered；
Detect in the k-th frame image with the matched position candidate of the skin pixels, and in the position candidate determine mesh
Cursor position；
Centered on the target position, obtained in the k-th frame image big with human face region in (K-1) frame image
Small matched candidate region；
If the candidate region exceeds normal pictures, half face is determined in the k-th frame image according to the position candidate
Region.
2. the method as described in claim 1, which is characterized in that the face detected according to predetermined period in preview screen,
Include:
The face in the preview screen acquired by front camera is detected according to predetermined period, alternatively,
The face in the preview screen acquired by rear camera is detected according to predetermined period.
3. the method as described in claim 1, which is characterized in that in the detection k-th frame image with the skin pixels
Matched position candidate, comprising:
The region adjacent with human face region in (K-1) frame image is determined in the k-th frame image；
Detection includes the target area of the skin pixels in the adjacent region；
The determining and matched position candidate of the skin pixels in the target area.
4. the method as described in claim 1, which is characterized in that determine target position in the position candidate, comprising:
Calculate the pixel average of the skin pixels of human face region in (K-1) frame image；
Detection and the matched target position of the pixel average in the position candidate.
5. the method as described in claim 1-4 is any, which is characterized in that further include:
If the candidate region determines people without departing from normal pictures, according to the candidate region in the k-th frame image
Face region.
6. a kind of human face detection device characterized by comprising
Processing module for detecting the face in preview screen according to predetermined period, and stores the picture frame of label human face region；
Extraction module when for the face to be not detected in T moment in period corresponding k-th frame image, extracts in (T-1) week
The skin pixels of human face region in moment phase corresponding (K-1) frame image；
Detection module, for detect in the k-th frame image with the matched position candidate of the skin pixels,
First determining module, for determining target position in the position candidate；
Matching module, for being obtained and (K-1) frame figure in the k-th frame image centered on the target position
The matched candidate region of human face region size as in；
Second determining module is used for when the candidate region exceeds normal pictures, according to the position candidate in the k-th frame
Half face region is determined in image.
7. device as claimed in claim 6, which is characterized in that the face detected according to predetermined period in preview screen,
Include:
The face in the preview screen acquired by front camera is detected according to predetermined period, alternatively,
The face in the preview screen acquired by rear camera is detected according to predetermined period.
8. device as claimed in claim 6, which is characterized in that the detection module is used for:
The region adjacent with human face region in (K-1) frame image is determined in the k-th frame image；
Detection includes the target area of the skin pixels in the adjacent region；
The determining and matched position candidate of the skin pixels in the target area.
9. device as claimed in claim 6, which is characterized in that first determining module is used for:
Calculate the pixel average of the skin pixels of human face region in (K-1) frame image；
Detection and the matched target position of the pixel average in the position candidate.
10. the device as described in claim 6-9 is any, which is characterized in that further include:
Third determining module is used for when the candidate region is without departing from normal pictures, according to the candidate region in the K
Human face region is determined in frame image.
11. a kind of terminal device characterized by comprising shell, processor, memory, circuit board and power circuit, wherein
The circuit board is placed in the space interior that the shell surrounds, and the processor and the memory are arranged in the circuit board
On；The power circuit, for each circuit or the device power supply for terminal device；The memory is for storing executable journey
Sequence code；The processor is run and the executable journey by reading the executable program code stored in the memory
The corresponding program of sequence code, for executing following steps:
The face in preview screen is detected according to predetermined period, and stores the picture frame of label human face region；
If the face is not detected in T moment corresponding k-th frame image, extract in (T-1) moment corresponding (K-
1) in frame image human face region skin pixels；
Detect in the k-th frame image with the matched position candidate of the skin pixels, and in the position candidate determine mesh
Cursor position；
Centered on the target position, obtained in the k-th frame image big with human face region in (K-1) frame image
Small matched candidate region；
If the candidate region exceeds normal pictures, half face is determined in the k-th frame image according to the position candidate
Region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610860342.XA CN106650583B (en) | 2016-09-28 | 2016-09-28 | Method for detecting human face, device and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610860342.XA CN106650583B (en) | 2016-09-28 | 2016-09-28 | Method for detecting human face, device and terminal device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106650583A CN106650583A (en) | 2017-05-10 |
| CN106650583B true CN106650583B (en) | 2019-07-23 |
Family
ID=58853576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610860342.XA Active CN106650583B (en) | 2016-09-28 | 2016-09-28 | Method for detecting human face, device and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106650583B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492266B (en) * | 2018-03-18 | 2020-10-09 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN109993061B (en) * | 2019-03-01 | 2021-12-07 | 珠海亿智电子科技有限公司 | Face detection and recognition method, system and terminal equipment |
| CN110472077A (en) * | 2019-07-12 | 2019-11-19 | 浙江执御信息技术有限公司 | The preposition method of calibration of Identification of Images, system, medium and electronic equipment |
| CN112712569B (en) * | 2020-12-25 | 2023-12-12 | 百果园技术(新加坡)有限公司 | Skin color detection method and device, mobile terminal and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006293783A (en) * | 2005-04-12 | 2006-10-26 | Fuji Photo Film Co Ltd | Image processing device and image processing program |
| CN103186763B (en) * | 2011-12-28 | 2017-07-21 | 富泰华工业（深圳）有限公司 | Face identification system and method |
| JP5978639B2 (en) * | 2012-02-06 | 2016-08-24 | ソニー株式会社 | Image processing apparatus, image processing method, program, and recording medium |
| CN104866805B (en) * | 2014-02-20 | 2020-09-11 | 腾讯科技（深圳）有限公司 | Method and device for real-time tracking of human face |
| CN105049711B (en) * | 2015-06-30 | 2018-09-04 | 广东欧珀移动通信有限公司 | A kind of photographic method and user terminal |
-
2016
- 2016-09-28 CN CN201610860342.XA patent/CN106650583B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106650583A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670397B (en) | Method and device for detecting key points of human skeleton, electronic equipment and storage medium | |
| US20230351805A1 (en) | Spoofing detection device, spoofing detection method, and recording medium | |
| CN107370942B (en) | Photographing method, photographing device, storage medium and terminal | |
| CN106650583B (en) | Method for detecting human face, device and terminal device | |
| US11004214B2 (en) | Image processing apparatus, image processing method, and storage medium | |
| US8928770B2 (en) | Multi-subject imaging device and imaging method | |
| CN107277479B (en) | White balance processing method and device | |
| CN109299658B (en) | Face detection method, face image rendering device and storage medium | |
| CN113408403A (en) | Living body detection method, living body detection device, and computer-readable storage medium | |
| CN107395957B (en) | Photographing method and device, storage medium and electronic equipment | |
| CN106161962B (en) | A kind of image processing method and terminal | |
| KR20120022512A (en) | Electronic camera, image processing apparatus, and image processing method | |
| CN109068058A (en) | Filming control method, device and electronic equipment under super night scene mode | |
| US9197818B2 (en) | Imaging apparatus | |
| CN105227855B (en) | A kind of image processing method and terminal | |
| CN110677592B (en) | Subject focusing method and device, computer equipment and storage medium | |
| CN112434546A (en) | Face living body detection method and device, equipment and storage medium | |
| CN112188091B (en) | Face information identification method and device, electronic equipment and storage medium | |
| CN109981989B (en) | Method and device for rendering image, electronic equipment and computer readable storage medium | |
| CN108154090B (en) | Face recognition method and device | |
| CN106851091A (en) | Control method of electronic device, device and electronic equipment | |
| CN114979487B (en) | Image processing method and device, electronic equipment and storage medium | |
| EP3273437A1 (en) | Method and device for enhancing readability of a display | |
| CN110121030B (en) | Method for storing shot image and electronic equipment | |
| CN109582811A (en) | Image processing method, device, electronic equipment and computer readable storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant after: OPPO Guangdong Mobile Communications Co., Ltd. Address before: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant before: Guangdong OPPO Mobile Communications Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |